├── .gitignore
├── examples
    ├── README.md
    ├── test.md5
    └── test.sh
├── Makefile
├── scripts
    ├── plot2dSFS.R
    ├── plot2DSFS.R
    ├── README.md
    ├── samplingNCD.R
    ├── plotPCA.R
    ├── samplingSFS.R
    ├── plotFST.R
    ├── sampling2DSFS.R
    ├── getDxy.pl
    ├── calcDxy.R
    └── plotSS.R
├── ngs2dSFS.hpp
├── ngsStat.cpp
├── ngsCovar.hpp
├── ngs2dSFS.cpp
├── ngsStat.hpp
├── ngsFST.cpp
├── ngsFST.hpp
├── README.md
├── ngsCovar.cpp
├── shared.hpp
└── LICENSE


/.gitignore:
--------------------------------------------------------------------------------
1 | ngsFST
2 | ngsCovar
3 | ngs2dSFS
4 | ngsStat
5 | *.o
6 | examples/testA*
7 | examples/test.log
8 | 


--------------------------------------------------------------------------------
/examples/README.md:
--------------------------------------------------------------------------------
1 | 
2 | A tutorial on using ngsTools from BAM files can be found [here](https://github.com/mfumagalli/ngsTools/blob/master/TUTORIAL.md)).
3 | In most cases, it will contain all the information you need.
4 | The examples previously reported here are now deprecated.
5 | 
6 | 


--------------------------------------------------------------------------------
/Makefile:
--------------------------------------------------------------------------------
 1 | CXX ?= g++
 2 | 
 3 | TOOLS = ngs2dSFS ngsCovar ngsFST ngsStat
 4 | 
 5 | CXXFLAGS := -O3 -Wall $(CXXFLAGS)
 6 | LDLIBS = -lm
 7 | 
 8 | all: $(TOOLS)
 9 | 
10 | $(TOOLS): %: %.cpp %.hpp shared.hpp
11 | 	$(CXX) $(CXXFLAGS) $(CPPFLAGS) $@.cpp $(LDFLAGS) $(LDLIBS) -o $@
12 | 
13 | test:
14 | 	@cd examples/; bash test.sh 2> test.log; cd ../
15 | 
16 | clean:
17 | 	@rm -rf $(TOOLS) *.o examples/testA*
18 | 
19 | .PHONY: all clean test
20 | 


--------------------------------------------------------------------------------
/scripts/plot2dSFS.R:
--------------------------------------------------------------------------------
 1 | 
 2 | # Usage: Rscript infile.spec outfile.eps pop1 pop2
 3 | 
 4 | # Read parameters
 5 | args <- commandArgs(trailingOnly = TRUE);
 6 | infile <- args[1];
 7 | outfile <- args[2];
 8 | pop1 <- args[3];
 9 | pop2 <- args[4];
10 | rm(args);
11 | 
12 | # Read input file
13 | values <- as.matrix(read.table(infile, stringsAsFact=F));
14 | n1=nrow(values)-1;
15 | n2=ncol(values)-1;
16 | 
17 | # Plot
18 | pdf(outfile);
19 | image(x=seq(0,n1), y=seq(0,n2), z=-log10(values), xlab=pop1, ylab=pop2, main="Joint SFS")
20 | dev.off();
21 | 
22 | 


--------------------------------------------------------------------------------
/ngs2dSFS.hpp:
--------------------------------------------------------------------------------
 1 | #include "shared.hpp"
 2 | 
 3 | // comput 2d-sfs, adding each site the joint max post prob of allele frequencies
 4 | void sumSpectrum(matrix<double> &spec, matrix<double> &m1, matrix<double> &m2, int maxlike) {
 5 |   int nsites = 0;
 6 |   nsites = m1.x;
 7 |   if (maxlike==1) { // get the max like joint alle freq
 8 |     for (int s=0; s<nsites; s++) spec.data[maxposarr(m1,s,0,m1.y)][maxposarr(m2,s,0,m2.y)]+=1.0;
 9 |   } else { // sum the products
10 |    for (int s=0; s<nsites; s++) {
11 |     for (int i=0; i<m1.y; i++) {
12 |       for (int j=0; j<m2.y; j++) {
13 |         spec.data[i][j]+=(m1.data[s][i]*m2.data[s][j]); // in case of folded, the "derived" stated will have 0 frequency
14 |       }
15 |     }
16 |    }
17 |   }
18 | }
19 | 


--------------------------------------------------------------------------------
/scripts/plot2DSFS.R:
--------------------------------------------------------------------------------
 1 | 
 2 | ## Script provided by Dean Ousby and adapted
 3 | 
 4 | library(plot3D)
 5 | 
 6 | args <- commandArgs(T)
 7 | fin <- args[1]
 8 | pops <- unlist(strsplit(args[2],split="-")) # names
 9 | nchroms <- as.numeric(unlist(strsplit(args[3], split="-")))
10 | filtmono <- as.numeric(args[4])
11 | rm(args)
12 | 
13 | val <- scan(paste(fin, sep=""), quiet=T)
14 | sfs <- matrix(val, nrow=nchroms[1]+1, ncol=nchroms[2]+1, byrow=T)
15 | rm(val)
16 | 
17 | # mask non-variant sites
18 | if (filtmono) {
19 | 	sfs[1,1] <- 0
20 | 	sfs[nrow(sfs),ncol(sfs)] <- 0
21 | }
22 | 
23 | fout <- paste(fin,".pdf", sep="", collapse="")
24 | 
25 | pdf(file=fout)
26 | 
27 | hist3D(x = seq(0,1,length.out = nrow(sfs)), y = seq(0,1,length.out=ncol(sfs)), sfs, cex.lab=1.2, xlab=pops[1], ylab=pops[2], zlab="Frequency", main=paste("2D-SFS"),pin=c(10,0), cex.main=1.4, zlim=c(0,max(sfs)))
28 | 
29 | invisible(dev.off())
30 | 
31 | 
32 | 
33 | 


--------------------------------------------------------------------------------
/scripts/README.md:
--------------------------------------------------------------------------------
 1 | 
 2 | # R scripts to plot results from ngsPopGen program
 3 | 
 4 | ## Plot FST values
 5 | 
 6 |      Rscript plotFST.R -i infile.fst -o outfile -p positions.txt -w win -s step -th min_prob_variable      
 7 | 
 8 | where:
 9 |  `infile.fst` is the output of `ngsFST`, 
10 |  `positions.txt` is a single column new-line separated numbers of genomic position (on the same chromosome) for corresponding values of per-site FST,
11 |  `win` is the window size,
12 |  `step` is the step for the sliding windows,
13 |  'th` is the minimum threshold on the probability of being variable for a site to be kept in the analysis.
14 | 
15 | This will generate 2 files, a plot `outfile.eps` and a text file `outfile.txt` with all values for each window.
16 | 
17 | ## Plot summary statistics
18 | 
19 |      Rscript plotSS.R -i infile.stat -o outfile.eps -n name1-name2 # if 2 pops     
20 |      Rscript plotSS.R -i infile.stat -o outfile.eps -n name1 # if only 1 pop     
21 | 
22 | where `infile.stat` is the output of `ngsStat`.
23 | 
24 | ## Plot PCA
25 | 
26 |      Rscript plotPCA.R -i infile.covar -c component1-component2 -a annotation.file -o outfile.eps     
27 | 
28 | where `infile.covar` is the ouput of `ngsCovar`, `component1-component2` are the two components that user wants to plot, `annotation.file` is a [PLINK](http://pngu.mgh.harvard.edu/~purcell/plink/) cluster file.
29 | 
30 | ## Plot 2D-SFS
31 | 
32 |      Rscript plot2dSFS.R infile.spec outfile.eps pop1 pop2    
33 | 
34 | where `infile.spec` is the output of `ngs2dSFS`, and `pop1` and `pop2` are the populations labels.
35 | 
36 | 
37 | 
38 | 
39 | 


--------------------------------------------------------------------------------
/scripts/samplingNCD.R:
--------------------------------------------------------------------------------
 1 | 
 2 | args <- commandArgs(T)
 3 | 
 4 | if (length(args)==0) {
 5 |         stop("No arguments given.
 6 |         Aim: Estimate NCD statistics (Bittarello) by sampling from .saf files.
 7 |         Usage: Rscript NCD.R input.saf.idx.gz nr_chroms target_freq
 8 | 	Output is in stdout: nr_sites1 \t NCD1 \t nr_sites2 \t NCD2
 9 |         Info: this program take unfolded .saf.idx.gz data.\n")
10 | }
11 | 
12 | fin <- args[1] # saf.idx file, this must be unfolded
13 | nchroms <- as.numeric(args[2]) # how many chroms
14 | tf <- as.numeric(args[3]) # target balanced frequency
15 | type <- as.numeric(args[4]) # NCD1 NCD2
16 | rm(args)
17 | 
18 | nl <- 1000000
19 | 
20 | selpaste <- function(arr) {
21 |         paste(arr[1:2], sep="", collapse=":")
22 | }
23 | 
24 | expsam <- function(arr) {
25 |         probs <- exp(as.numeric(arr[c(-1,-2)]))
26 |         sample(x=seq(1,length(probs)), size=1, prob=probs)
27 | }
28 | 
29 | aaf <-c()
30 | con <- file(fin, "r")
31 | while (TRUE) {
32 |         mline <- readLines(con, n=nl)
33 |         if (length(mline)==0) {
34 |                 break
35 |         }
36 |         ss <- strsplit(mline, split="\t")
37 |         aaf <- c(aaf, (sapply(ss, expsam)-1))
38 | }
39 | close(con)
40 | 
41 | # fixed differences
42 | fd <- which(aaf==nchroms)
43 | 
44 | # snps
45 | snps <- which(aaf>0 & aaf<nchroms)
46 | 
47 | # maf
48 | aaf <- aaf/nchroms
49 | aaf[which(aaf>0.5)] <- 1 - aaf[which(aaf>0.5)]
50 | 
51 | # NCD1
52 | ind1 <- snps
53 | ncd1 <- sqrt(mean((aaf[ind1]-tf)^2))
54 | 
55 | # NCD2
56 | ind2 <- sort(unique(snps,fd))
57 | ncd2 <- sqrt(mean((aaf[ind2]-tf)^2))
58 | 
59 | cat(length(ind1),"\t",ncd1,"\t",length(ind2),"\t",ncd2,"\n")
60 | 
61 | 
62 | 
63 | 


--------------------------------------------------------------------------------
/examples/test.md5:
--------------------------------------------------------------------------------
 1 | 6415c5c0ecd371f03423adcd2bf8af70  testA1.geno.gz
 2 | e73e77e1f31e60a24efa10ae7d9150ca  testA1.mafs.gz
 3 | 18b55459de315b1b3360c3c531510869  testA1.rf.saf
 4 | c9bd6b093e88ca1d3e058a6066a46f5d  testA1.rf.saf.idx
 5 | 2ef0db351e1c2ab28ea069af4e1c8ed3  testA1.rf.saf.pos.gz
 6 | 217dbd841793795b532a0cf179f6782d  testA1.saf
 7 | c9bd6b093e88ca1d3e058a6066a46f5d  testA1.saf.idx
 8 | d803500150a8be988e35f0d9d72b2406  testA1.saf.ml
 9 | 2ef0db351e1c2ab28ea069af4e1c8ed3  testA1.saf.pos.gz
10 | 7bd842ca6ccba9454bdd3d1230bb7c45  testA2.geno.gz
11 | 40532e12753061f2bccc829e0e8ae817  testA2.mafs.gz
12 | 36003ad1694b3deae82dd91a700b098a  testA2.rf.saf
13 | 296e9560401bba06e57b66b8fced07f9  testA2.rf.saf.idx
14 | 2ef0db351e1c2ab28ea069af4e1c8ed3  testA2.rf.saf.pos.gz
15 | 382b583a4714ae321c41ed13cc443ae0  testA2.saf
16 | 296e9560401bba06e57b66b8fced07f9  testA2.saf.idx
17 | 9607f2ec5f82a4bf7ac1485617bfbdb2  testA2.saf.ml
18 | 2ef0db351e1c2ab28ea069af4e1c8ed3  testA2.saf.pos.gz
19 | ffff04476222b0fceb669a2f850f305b  testA.covar1
20 | 517f8fc6fe8677389922930434995119  testA.covar2
21 | a98275d44976dfab3a1943d479229ded  testA.covar3
22 | fe9a2245b034734dc9b3afa7f10e4369  testA.fst1
23 | e2e42e6c7de7f9d315eea7aed7f9b1bd  testA.fst2
24 | efed98d852aef895699922b227abff03  testA.fst3
25 | 9a46a6e8cce8b241fe51a5f5c21b34ee  testA.geno
26 | ea9aa8882271823dbe31f8947a3bf142  testA.joint.spec
27 | 4ad56bafab229c3e69bcff5c3d969119  testA.mafs.gz
28 | 325d650261660adff0c759d870d2eed8  testA.rf.saf
29 | 2f015df7d60fc930b55270407bb82924  testA.rf.saf.idx
30 | 2ef0db351e1c2ab28ea069af4e1c8ed3  testA.rf.saf.pos.gz
31 | 5799f1e3162c5c2f9e8680cf205f4953  testA.saf.gz
32 | 2f015df7d60fc930b55270407bb82924  testA.saf.idx
33 | 2f1a8eec14104cce565f056b8514e380  testA.saf.ml
34 | 2ef0db351e1c2ab28ea069af4e1c8ed3  testA.saf.pos.gz
35 | 9a15a4e873895e5ad53f7a4e144dc09f  testA.stat
36 | 


--------------------------------------------------------------------------------
/scripts/plotPCA.R:
--------------------------------------------------------------------------------
 1 | # Usage: Rscript -i infile.covar -c component1-component2 -a annotation.file -o outfile.eps
 2 | 
 3 | library(optparse)
 4 | library(ggplot2)
 5 | 
 6 | option_list <- list(make_option(c('-i','--in_file'), action='store', type='character', default=NULL, help='Input file (output from ngsCovar)'),
 7 |                     make_option(c('-c','--comp'), action='store', type='character', default=1-2, help='Components to plot'),
 8 |                     make_option(c('-a','--annot_file'), action='store', type='character', default=NULL, help='Annotation file with individual classification (2 column TSV with ID and ANNOTATION)'),
 9 |                     make_option(c('-o','--out_file'), action='store', type='character', default=NULL, help='Output file')
10 |                     )
11 | opt <- parse_args(OptionParser(option_list = option_list))
12 | 
13 | # Annotation file is in plink cluster format
14 | 
15 | #################################################################################
16 | 
17 | # Read input file
18 | covar <- read.table(opt$in_file, stringsAsFact=FALSE);
19 | 
20 | # Read annot file
21 | annot <- read.table(opt$annot_file, sep="\t", header=TRUE); # note that plink cluster files are usually tab-separated instead
22 | 
23 | # Parse components to analyze
24 | comp <- as.numeric(strsplit(opt$comp, "-", fixed=TRUE)[[1]])
25 | 
26 | # Eigenvalues
27 | eig <- eigen(covar, symm=TRUE);
28 | eig$val <- eig$val/sum(eig$val);
29 | cat(signif(eig$val, digits=3)*100,"\n");
30 | 
31 | # Plot
32 | PC <- as.data.frame(eig$vectors)
33 | colnames(PC) <- gsub("V", "PC", colnames(PC))
34 | PC$Pop <- factor(annot$CLUSTER)
35 | 
36 | title <- paste("PC",comp[1]," (",signif(eig$val[comp[1]], digits=3)*100,"%)"," / PC",comp[2]," (",signif(eig$val[comp[2]], digits=3)*100,"%)",sep="",collapse="")
37 | 
38 | x_axis = paste("PC",comp[1],sep="")
39 | y_axis = paste("PC",comp[2],sep="")
40 | 
41 | ggplot() + geom_point(data=PC, aes_string(x=x_axis, y=y_axis, color="Pop")) + ggtitle(title)
42 | ggsave(opt$out_file)
43 | unlink("Rplots.pdf", force=TRUE)
44 | 
45 | 


--------------------------------------------------------------------------------
/scripts/samplingSFS.R:
--------------------------------------------------------------------------------
 1 | 
 2 | args <- commandArgs(T)
 3 | 
 4 | if (length(args)==0) {
 5 | 	stop("No arguments given.\nAim: Estimate the SFS by sampling from .saf files. Fold it at the end if requested.\nUsage: Rscript fastSFS.R input.saf.idx.gz nr_chroms fold_it? plot.pdf\nInfo: Final sfs is in stdout and fold_it? is boolean (0 or 1) and nr_chroms is the number of chromosomes. This program take unfolded .saf.idx.gz data.\n")
 6 | }
 7 | 
 8 | fin <- args[1] # saf.idx file, this must be unfolded
 9 | nchroms <- as.numeric(args[2]) # how many chroms
10 | tofold <- as.numeric(args[3]) # fold it at the end?
11 | fout <- args[4] # plot in pdf
12 | rm(args)
13 | 
14 | # output is in stdout
15 | 
16 | saf <- rep(0, nchroms+1)
17 | 
18 | con <- file(fin, "r")
19 | 
20 | while (TRUE) {
21 | 	line <- readLines(con, n=1)
22 | 	if (length(line)==0) {
23 |       		break
24 |     	}
25 | 	probs <- exp(as.numeric(strsplit(line, split="\t")[[1]][c(-1,-2)]))
26 | 	probs <- probs/sum(probs) # perhaps not necessary
27 | 	if (length(probs)==length(saf)) {
28 | 		sampled <- sample(x=seq(1,length(probs)), size=1, prob=probs)
29 | 		saf[sampled] <- saf[sampled]+1
30 | 	} else {
31 | 		break("Error! Quit!")
32 | 	}
33 | }
34 | 
35 | close(con)
36 | 
37 | fold <- function(spec) {
38 | 	nt <- length(spec)
39 | 	ns <- (length(spec)-1)/2
40 | 	ff <- rep(NA, ns+1)
41 | 	for (i in 1:(length(ff))) {
42 | 		ff[i] <- spec[i]+spec[nt-i+1]
43 | 	}
44 | 	ff[length(ff)] <- spec[length(ff)]
45 | 	#print(sum(spec)==sum(ff))
46 | 	ff
47 | }
48 | 
49 | # fold the final sfs if required
50 | sfs <- saf
51 | if (tofold) sfs <- fold(saf)
52 | 
53 | pdf(file=fout)
54 | 
55 | if (tofold) {
56 | 	pvar <- sfs[1]/sum(sfs)
57 | 	barplot(sfs[-1], names.arg=1:(length(sfs)-1), sub=paste("variability: ", pvar))
58 | } else {
59 | 	pvar <- (sfs[1]+sfs[length(sfs)])/sum(sfs)
60 |         barplot(sfs[2:(length(sfs)-1)], names.arg=1:(length(sfs)-2), sub=paste("variability: ", pvar))
61 | }
62 | 
63 | invisible(dev.off())
64 | 
65 | cat(sfs,"\n")
66 | 
67 | 
68 | 
69 | 
70 | 
71 | 
72 | 
73 | 
74 | 
75 | 
76 | 
77 | 
78 | 
79 | 
80 | 
81 | 
82 | 
83 | 
84 | 
85 | 


--------------------------------------------------------------------------------
/scripts/plotFST.R:
--------------------------------------------------------------------------------
 1 | 
 2 | # Usage: Rscript -i infile.fst -o outfile.eps -w win -s step
 3 | 
 4 | library(optparse)
 5 | library(ggplot2)
 6 | 
 7 | option_list <- list(make_option(c('-i','--in_file'), action='store', type='character', default=NULL, help='Input file'),
 8 | make_option(c('-p','--pos_file'), action='store', type='character', default=NULL, help='Input position file'),
 9 | make_option(c('-w','--window'), action='store', type='character', default=1, help='Window length'),
10 | make_option(c('-s','--step'), action='store', type='character', default=1, help='Step size'),
11 | make_option(c('-t','--th'), action='store', type='character', default=0, help='Minimu probability of being variable'),
12 | make_option(c('-o','--out_file'), action='store', type='character', default=NULL, help='Output file')
13 |                     )
14 | opt <- parse_args(OptionParser(option_list = option_list))
15 | 
16 | # Read input file
17 | values <- read.table(opt$in_file, stringsAsFact=F);
18 | ind <- which(values[,5]>=as.numeric(opt$th))
19 | pos <- as.numeric(readLines(opt$pos_file))
20 | if (length(pos)!=nrow(values)) stop("Dimensions of fst values and positions must match. Terminate.\n");
21 | values <- values[ind,]
22 | pos <- pos[ind]
23 | cat("After removing sites, now there are",nrow(values),"sites going from",min(pos),"to",max(pos),"\n")
24 | cat("Overall FST:",sum(values[,1])/sum(values[,2]),"\n");
25 | 
26 | # Windows
27 | len=max(pos)
28 | win=as.numeric(opt$window);
29 | step=as.numeric(opt$step);
30 | start=seq(min(pos), len, step);
31 | end=start+win-1;
32 | wpos=round(start+(win/2)); # position of the window in the plot (center)
33 | fst=c(); 
34 | for (i in 1:length(start)) {
35 | 	ipos=which(pos>=start[i] & pos<=end[i])
36 | 	fst[i]=sum(values[ipos,1])/sum(values[ipos,2]);
37 | }
38 | 
39 | # Data
40 | df=data.frame(cbind(Pop=rep(1,length(wpos)), Pos=wpos, Value=fst));
41 | df[,2:3]=sapply(df[,2:3], as.character)
42 | df[,2:3]=sapply(df[,2:3], as.numeric)
43 | write.table(df, file=paste(opt$out_file,".txt",sep="",collapse=""), sep="\t", quote=F, row.names=F, col.names=F)
44 | 
45 | # Plot
46 | title = expression(F[ST]);
47 | ggplot(data=df, aes(x=Pos, y=Value)) + geom_line() + ggtitle(title);
48 | ggsave(paste(opt$out_file,".eps",sep="",collapse=""))
49 | unlink("Rplots.pdf", force=TRUE)
50 | 
51 | 
52 | 


--------------------------------------------------------------------------------
/scripts/sampling2DSFS.R:
--------------------------------------------------------------------------------
  1 | 
  2 | print(date())
  3 | 
  4 | args <- commandArgs(T)
  5 | 
  6 | if (length(args)==0) {
  7 | 	stop("No arguments given.
  8 | 	Aim: Estimate the 2DSFS by sampling from .saf files.
  9 | 	Usage: Rscript fast2DSFS.R input1.saf.idx.gz input1.saf.idx.gz nr_chroms1 nr_chroms2 prob_sampling_site 
 10 | 	Info: Final sfs is in last argument, nr_chroms is the number of chromosomes, prob_sampling_site is the chance of sampling the current site for the estimation. This program take unfolded .saf.idx.gz data.\n")
 11 | }
 12 | 
 13 | fin1 <- args[1] # saf.idx file, this must be unfolded
 14 | fin2 <- args[2]
 15 | nchroms1 <- as.numeric(args[3]) # how many chroms
 16 | nchroms2 <- as.numeric(args[4]) 
 17 | psam <- as.numeric(args[5])
 18 | fout <- args[6]
 19 | rm(args)
 20 | 
 21 | nl <- 1000000
 22 | 
 23 | selpaste <- function(arr) {
 24 | 	paste(arr[1:2], sep="", collapse=":")
 25 | }
 26 | 
 27 | expsam <- function(arr) {
 28 | 	probs <- exp(as.numeric(arr[c(-1,-2)]))
 29 | 	sample(x=seq(1,length(probs)), size=1, prob=probs)
 30 | }
 31 | 
 32 | # first file
 33 | pos <- saf <- c()
 34 | 
 35 | cat("Reading first file...\n")
 36 | con <- file(fin1, "r")
 37 | while (TRUE) {
 38 | 	mline <- readLines(con, n=nl)
 39 | 	if (length(mline)==0) {
 40 |       		break
 41 |     	}
 42 | 	ss <- strsplit(mline, split="\t")
 43 | 	pos <- c(pos, sapply(ss, selpaste))
 44 | 	saf <- c(saf, sapply(ss, expsam))
 45 | 	cat(pos[length(pos)],"\t")
 46 | }
 47 | close(con)
 48 | 
 49 | sfs <- matrix(0, nrow=(nchroms1+1), ncol=(nchroms2+1))
 50 | 
 51 | # second file
 52 | cat("\nReading second file...\n")
 53 | con <- file(fin2, "r")
 54 | while (TRUE) {
 55 |         mline <- readLines(con, n=nl)
 56 |         if (length(mline)==0) {
 57 |                 break
 58 |         }
 59 | 	ss <- strsplit(mline, split="\t")
 60 | 	pos2 <- sapply(ss, selpaste)
 61 | 
 62 | 	ind <- match(pos2, pos)
 63 | 
 64 | 	take <- (!is.na(ind))*(sample(c(0,1),length(pos2),T,c(1-psam,psam)))
 65 | 
 66 | 	saf2 <- sapply(ss, expsam)[which(take==1)]
 67 | 	
 68 | 	saf1 <- saf[ind[which(take==1)]]
 69 | 
 70 | 	for (j in 1:length(saf1)) sfs[saf1[j], saf2[j]] <- sfs[saf1[j], saf2[j]] + 1
 71 | 
 72 | 	cat(pos2[length(pos2)], "\t")
 73 | 
 74 | }
 75 | close(con)
 76 | 
 77 | final <- array(t(sfs))
 78 | 
 79 | cat("\nTotal sites:", sum(final))
 80 | cat("\nProportion (on pop1):", sum(final)/length(pos))
 81 | 
 82 | cat("\nNon-normalised SFS:\n")
 83 | cat(final)
 84 | 
 85 | final <- final/sum(final)
 86 | cat("\nNormalised SFS:\n")
 87 | cat(final)
 88 | 
 89 | cat(final, file=fout)
 90 | 
 91 | cat("\n")
 92 | print(date())
 93 | 
 94 | 
 95 | 
 96 | 
 97 | 
 98 | 
 99 | 
100 | 
101 | 


--------------------------------------------------------------------------------
/scripts/getDxy.pl:
--------------------------------------------------------------------------------
 1 | #!/usr/bin/perl
 2 | 
 3 | #use strict;
 4 | use warnings;
 5 | use Getopt::Long;
 6 | 
 7 | my $pop1maf;
 8 | my $pop2maf;
 9 | my $minInd;
10 | 
11 | &GetOptions( 'pop1maf=s' => \$pop1maf,
12 |              'pop2maf=s' => \$pop2maf,
13 |              'minInd=i' => \$minInd,
14 | 			 );
15 | 
16 | my $usage = <<_EOUSAGE_;
17 | #########################################################################################
18 | #this script updates 
19 | # getDxy.pl --pop1maf <FILE> --pop2maf <FILE> --nInd <Integer>
20 | # Required:
21 | #  --pop1maf        a text maf file output from ANGSD with apporpriate filtering for Population 1
22 | #  --pop2maf        a text maf file output from ANGSD with apporpriate filtering for Population 2
23 | #  --minInd         minimum number of individuals required per population
24 | #
25 | #This script assumes equal and corresponding lines in the two maf files. User needs to filter for variable sites using the SNP pval before running this script.
26 | #
27 | #
28 | #Following columns need to be present:
29 | #
30 | #chromo	position	major	minor	ref	knownEM	unknownEM	nInd
31 | #
32 | #
33 | #Dxy is reported only for the sites included in the MAF file. While calculating the value per window, the correct number of sites has to be used.
34 | #
35 | #Example command to run the script
36 | #perl getDxy.pl --pop1maf pop1.pop1_pop2.genotypes.mafs.txt --pop2maf pop2.pop1_pop2.genotypes.mafs.txt --minInd 5
37 | ###########################################################################################
38 | _EOUSAGE_
39 | 
40 | 	;
41 |  
42 | if (! defined $pop1maf) {print $usage;exit;}
43 | if (! defined $pop2maf) {print $usage;exit;}
44 | if (! defined $minInd) {print $usage;exit;}
45 | 
46 | open POP1MAF, $pop1maf or die $!;
47 | open POP2MAF, $pop2maf or die $!;
48 | 
49 | my $line1;
50 | my $line2;
51 | 
52 | my $dxy=0;
53 | #read in the header and do nothing
54 | my $header1=<POP1MAF>;my $header2=<POP2MAF>;
55 | 
56 | print "chromo\tposition\tDxy\n";
57 | 
58 | while($line1=<POP1MAF>){
59 |         #read in maf from pop1
60 |         chomp $line1;my @parts=split('\t',$line1);
61 |         
62 |         #read in maf from pop2
63 |         $line2=<POP2MAF>;chomp $line2;my @parts2=split('\t',$line2);
64 |         
65 | if(($parts[7]>=$minInd)&&($parts2[7]>=$minInd)){#use only sites that are covered by at least $minInd individuals in each population, in v2 updated the position of the nIND column in MAF file 
66 | 
67 |         #if($parts3[4]>0.99999999){#use only sites with pvar >0.99999999, same as criteria used for fst
68 | 
69 |                 if(($parts[2]=~/$parts2[2]/)&&($parts[3]=~/$parts2[3]/)){#check if the major and minor allele are matching
70 | 
71 |                 $dxy=$parts[5]*(1-$parts2[5])+($parts2[5]*(1-$parts[5])); # 
72 | 
73 |                 print "$parts[0]\t$parts[1]\t$dxy\n"; # print scaffold, position and per site dxy
74 | 
75 |                 }
76 | 
77 |                 if(($parts[2]=~/$parts2[3]/)&&($parts[3]=~/$parts2[2]/)){#check if the major and minor allele are NOT matching
78 | 
79 |                 $dxy=($parts[5]*$parts2[5])+((1-$parts2[5])*(1-$parts[5])); 
80 | 
81 |                 print "$parts[0]\t$parts[1]\t$dxy\n";# print scaffold, position and per site dxy
82 | 
83 |                 }
84 | }}
85 | close POP1MAF;
86 | close POP2MAF;
87 | 


--------------------------------------------------------------------------------
/scripts/calcDxy.R:
--------------------------------------------------------------------------------
 1 | #########################################
 2 | #                                       #
 3 | #   Calculates Dxy from mafs files      #
 4 | #                                       #
 5 | #   Author: Joshua Penalba              #
 6 | #   Date: 22 Oct 2016                   #
 7 | #                                       #
 8 | #########################################
 9 | 
10 | 
11 | # NOTES
12 | # * Prior to calculating Dxy the following steps are recommended:
13 | #   1. Run ANGSD with all populations with a -SNP_pval and -skipTriallelic flags.
14 | #   2. Rerun ANGSD per population 
15 | #       Use the -sites flag with a file corresponding to the recovered SNPs.
16 | #       This will guarantee that sites with an allele fixed in one population is still included.
17 | #       Remove the -SNP_pval flag.
18 | #       IMPORTANT: Include an outgroup reference to polarize alleles.
19 | #   3. Gunzip the resulting mafs files.
20 | # 
21 | # * Make sure the totLen only includes the chromosomes being analyzed.
22 | # * minInd flag not added, assuming already considered in the ANGSD run.
23 | # * Test for matching major and minor alleles not included as it would filter out sequencing errors. 
24 | #   This has been accounted for in the allele frequency calculations.
25 | #   This filter may give an underestimate of dxy.
26 | # * Per site Dxy of ~0 could be common if the alternate alleles are present in a population other than the two being included in the calculation.
27 | 
28 | 
29 | ### Creating an argument parser
30 | library("optparse")
31 | 
32 | option_list = list(
33 |   make_option(c("-p","--popA"), type="character",default=NULL,help="path to unzipped mafs file for pop 1",metavar="character"),
34 |   make_option(c("-q","--popB"), type="character",default=NULL,help="path to unzipped mafs file for pop 2",metavar="character"),
35 |   make_option(c("-t","--totLen"), type="numeric",default=NULL,help="total sequence length for global per site Dxy estimate [optional]",metavar="numeric")
36 | )
37 | opt_parser = OptionParser(option_list=option_list)
38 | opt = parse_args(opt_parser)
39 | 
40 | ### Troubleshooting input
41 | if(is.null(opt$popA) | is.null(opt$popB)){
42 |   print_help(opt_parser)
43 |   stop("One or more of the mafs paths are missing", call.=FALSE)
44 | }
45 | 
46 | if(grepl('.gz$',opt$popA) | grepl('.gz$',opt$popB)){
47 |   print_help(opt_parser)
48 |   stop("One or more of the mafs is gzipped.", call.=FALSE)
49 | }
50 | 
51 | if(is.null(opt$totLen)){
52 |   print("Total length not supplied. The output will not be a per site estimate.")
53 | }
54 | 
55 | ### Reading data in
56 | allfreqA <- read.table(opt$popA,sep='\t',row.names=NULL, header=T)
57 | allfreqB <- read.table(opt$popB,sep='\t',row.names=NULL, header=T)
58 | 
59 | ### Manipulating the table and print dxy table
60 | allfreq <- merge(allfreqA, allfreqB, by=c("chromo","position"))
61 | allfreq <- allfreq[order(allfreq$chromo, allfreq$position),]
62 | # -> Actual dxy calculation
63 | allfreq <- transform(allfreq, dxy=(knownEM.x*(1-knownEM.y))+(knownEM.y*(1-knownEM.x)))
64 | write.table(allfreq[,c("chromo","position","dxy")], file="Dxy_persite.txt",quote=FALSE, row.names=FALSE, sep='\t')
65 | print('Created Dxy_persite.txt')
66 | 
67 | ### Print global dxy
68 | print(paste0('Global dxy is: ',sum(allfreq$dxy)))
69 | if(!is.null(opt$totLen)){
70 |   print(paste0('Global per site Dxy is: ',sum(allfreq$dxy)/opt$totLen))
71 | }
72 | 
73 | 
74 | 


--------------------------------------------------------------------------------
/examples/test.sh:
--------------------------------------------------------------------------------
 1 | SCRIPTS=../scripts
 2 | SIM_DATA=../../ngsSim/examples
 3 | ANGSD=../../angsd
 4 | 
 5 | 
 6 | 
 7 | ##### Clean-up
 8 | rm -f testA*
 9 | touch -d 'next minute' $SIM_DATA/testAF.ANC.fas.fai
10 | 
11 | 
12 | ##### Genotypes' and sample allele frequencies' posterior probabilities
13 | $ANGSD/angsd -glf $SIM_DATA/testA.glf.gz -fai $SIM_DATA/testAF.ANC.fas.fai -nInd 24 -doMajorMinor 1 -doMaf 1 -doPost 1 -doGeno 32 -doSaf 1 -anc $SIM_DATA/testAF.ANC.fas -out testA
14 | $ANGSD/misc/realSFS testA.saf.idx -seed 12345 > testA.saf.ml
15 | $ANGSD/angsd -glf $SIM_DATA/testA.glf.gz -fai $SIM_DATA/testAF.ANC.fas.fai -nInd 24 -doSaf 1 -anc $SIM_DATA/testAF.ANC.fas -pest testA.saf.ml -out testA.rf
16 | 
17 | # Estimated and true pooled site frequency spectrum
18 | #Rscript --vanilla --slave -e 'barplot(rbind(as.numeric(scan("../../ngsSim/examples/testA.frq", what="char")), exp(as.numeric(scan("testA.saf.ml", what="char")))), beside=T, legend=c("True","Estimated"))'
19 | 
20 | 
21 | 
22 | 
23 | 
24 | ##### PCA
25 | # Get covariance matrix
26 | gunzip -f testA.geno.gz testA.rf.saf.gz
27 | ../ngsCovar -probfile testA.geno -outfile testA.covar1 -nind 24 -nsites 10000 -call 0 -sfsfile testA.rf.saf -norm 0
28 | ../ngsCovar -probfile testA.geno -outfile testA.covar2 -nind 24 -nsites 10000 -call 0 -minmaf 0.05
29 | ../ngsCovar -probfile testA.geno -outfile testA.covar3 -nind 24 -nsites 10000 -call 1 -minmaf 0.05
30 | 
31 | # Plot results
32 | #Rscript --vanilla --slave -e 'write.table(cbind(seq(1,24),rep(1,24),c(rep("A",10),rep("B",8),rep("C",6))), row.names=F, sep="\t", col.names=c("FID","IID","CLUSTER"), file="testA.clst", quote=F)'
33 | #Rscript --vanilla --slave $SCRIPTS/plotPCA.R -i testA.covar1 -c 1-2 -a testA.clst -o testA.pca.SAF.pdf
34 | #Rscript --vanilla --slave $SCRIPTS/plotPCA.R -i testA.covar2 -c 1-2 -a testA.clst -o testA.pca.MAF.pdf
35 | #Rscript --vanilla --slave $SCRIPTS/plotPCA.R -i testA.covar3 -c 1-2 -a testA.clst -o testA.pca.MAFcall.pdf
36 | 
37 | 
38 | 
39 | 
40 | 
41 | ##### Statistics
42 | # Pop 1
43 | $ANGSD/angsd -glf $SIM_DATA/testA1.glf.gz -fai $SIM_DATA/testAF.ANC.fas.fai -nInd 10 -doMajorMinor 1 -doMaf 1 -doPost 1 -doGeno 32 -doSaf 1 -anc $SIM_DATA/testAF.ANC.fas -out testA1
44 | $ANGSD/misc/realSFS testA1.saf.idx -seed 12345 > testA1.saf.ml
45 | $ANGSD/angsd -glf $SIM_DATA/testA1.glf.gz -fai $SIM_DATA/testAF.ANC.fas.fai -nInd 10 -doSaf 1 -anc $SIM_DATA/testAF.ANC.fas -pest testA1.saf.ml -out testA1.rf
46 | # Pop 2
47 | $ANGSD/angsd -glf $SIM_DATA/testA2.glf.gz -fai $SIM_DATA/testAF.ANC.fas.fai -nInd 8 -doMajorMinor 1 -doMaf 1 -doPost 1 -doGeno 32 -doSaf 1 -anc $SIM_DATA/testAF.ANC.fas -out testA2
48 | $ANGSD/misc/realSFS testA2.saf.idx -seed 12345 > testA2.saf.ml
49 | $ANGSD/angsd -glf $SIM_DATA/testA2.glf.gz -fai $SIM_DATA/testAF.ANC.fas.fai -nInd 8 -doSaf 1 -anc $SIM_DATA/testAF.ANC.fas -pest testA2.saf.ml -out testA2.rf
50 | 
51 | # Get stats
52 | gunzip -f testA1.rf.saf.gz testA2.rf.saf.gz
53 | ../ngsStat -npop 2 -postfiles testA1.rf.saf testA2.rf.saf -nsites 10000 -iswin 1 -nind 10 8 -outfile testA.stat -block_size 100
54 | 
55 | # Plot results
56 | #Rscript --vanilla --slave $SCRIPTS/plotSS.R -i testA.stat -o testA.stat.pdf -n pop1-pop2
57 | #Rscript --vanilla --slave $SCRIPTS/plotSS.R -i testA.stat -o testA.stat.pop1.pdf -n pop1
58 | 
59 | 
60 | 
61 | 
62 | 
63 | ##### Fst
64 | # 2D-SFS
65 | ../ngs2dSFS -postfiles testA1.rf.saf testA2.rf.saf -outfile testA.joint.spec -relative 1 -nind 10 8 -nsites 10000 -maxlike 1
66 | #Rscript --vanilla --slave $SCRIPTS/plot2dSFS.R testA.joint.spec testA.joint.spec.pdf pop1 pop2
67 | 
68 | # Estimate Fst
69 | gunzip -f testA1.saf.gz testA2.saf.gz
70 | ../ngsFST -postfiles testA1.saf testA2.saf -priorfile testA.joint.spec -nind 10 8 -nsites 10000 -outfile testA.fst1
71 | ../ngsFST -postfiles testA1.saf testA2.saf -priorfiles testA1.saf.ml testA2.saf.ml -nind 10 8 -nsites 10000 -outfile testA.fst2
72 | ../ngsFST -postfiles testA1.rf.saf testA2.rf.saf -nind 10 8 -nsites 10000 -outfile testA.fst3
73 | 
74 | # Plot
75 | #Rscript --vanilla --slave $SCRIPTS/plotFST.R -i testA.fst -o testA.fst.pdf -w 100 -s 50
76 | 
77 | 
78 | 
79 | 
80 | 
81 | ##### Check MD5
82 | rm -f *.arg
83 | TMP=`mktemp --suffix .ngsPopGen`
84 | md5sum testA* | sort -k 2,2 > $TMP
85 | if diff $TMP test.md5 > /dev/null
86 | then
87 |     echo "ngsPopGen: All tests OK!"
88 | else
89 |     echo "ngsPopGen: test(s) failed!"
90 | fi
91 | 


--------------------------------------------------------------------------------
/ngsStat.cpp:
--------------------------------------------------------------------------------
  1 | 
  2 | // this program receives as input the .sfs files from realSFS and sfstools and outputs several statistics for each window: expected number of segregating sites, expected average heterozygosity, expected number of fixed differendes (if 2 pops are provided)
  3 | 
  4 | #include <cstdio>
  5 | #include <cstdlib>
  6 | #include <sys/stat.h>
  7 | #include <cstring>
  8 | #include <vector>
  9 | #include <math.h>
 10 | #include "ngsStat.hpp"
 11 | 
 12 | // to compile: g++ -Wall -O0 -g ngsStat.cpp -o ngsStat
 13 | 
 14 | int main (int argc, char *argv[]) {
 15 | 
 16 |   if (argc==1) {
 17 |     info();
 18 |     return 0;
 19 |   }
 20 | 
 21 |   /// DECLARE AND INITIALIZE VARIABLES
 22 | 
 23 |   char *sfsfile1=NULL; // posterior probabilities or sample allele frequency likelihoods
 24 |   char *sfsfile2=NULL;
 25 | 
 26 |   FILE *outpost;
 27 |   char *outfile=NULL;
 28 |   char *foutpost=NULL;
 29 | 
 30 |   int argPos = 1, increment = 0, npop = 1, nind1 = 0, nind2 = 0, nsites = 0, verbose = 0, block_size = 20000, firstbase=1, iswin = 0;
 31 | 
 32 |   // if iswin==1 then block_size is the window size and print the valeus for each window
 33 |   // if iswin==0 then block_size is just for efficiency and print values for each site
 34 | 
 35 |   /// READ AND ASSIGN INPUT PARAMETERS
 36 | 
 37 |   while (argPos<argc) {
 38 |     increment = 0;
 39 |     if(strcmp(argv[argPos],"-postfiles")==0) {
 40 |       sfsfile1 = argv[argPos+1];
 41 |       if (npop==2) {
 42 |         sfsfile2 = argv[argPos+2];
 43 |         increment = 1;
 44 |       }
 45 |     }
 46 |     else if(strcmp(argv[argPos],"-outfile")==0) outfile = argv[argPos+1];
 47 |     else if(strcmp(argv[argPos],"-npop")==0) npop = atoi(argv[argPos+1]);
 48 |     else if(strcmp(argv[argPos],"-nind")==0) {
 49 |       nind1 = atoi(argv[argPos+1]);
 50 |       if (npop==2)  {
 51 |         nind2 = atoi(argv[argPos+2]);
 52 |         increment = 1;
 53 |       }
 54 |     }
 55 |     else if(strcmp(argv[argPos],"-nsites")==0) nsites = atoi(argv[argPos+1]);
 56 |     else if(strcmp(argv[argPos],"-verbose")==0) verbose = atoi(argv[argPos+1]);
 57 |     else if(strcmp(argv[argPos],"-block_size")==0) block_size = atoi(argv[argPos+1]);
 58 |     else if(strcmp(argv[argPos],"-firstbase")==0) firstbase = atoi(argv[argPos+1]);
 59 |     else if(strcmp(argv[argPos],"-iswin")==0) iswin = atoi(argv[argPos+1]);
 60 |     else {
 61 |       printf("\tUnknown arguments: %s\n",argv[argPos]);
 62 |       info();
 63 |       return 0; // terminate
 64 |     }
 65 |     argPos = argPos + 2 + increment;
 66 |   }
 67 | 
 68 |   /// CHECK INPUT
 69 |   if(sfsfile1 == NULL) {
 70 |     fprintf(stderr,"\nMust supply -postfiles.\n");
 71 |     info();
 72 |      return 0;
 73 |   }
 74 |   if(outfile == NULL) {
 75 |     fprintf(stderr,"\nMust supply -outfile.\n");
 76 |     info();
 77 |     return 0;
 78 |   }
 79 | 
 80 |   /// OUTPUT
 81 |   foutpost = append(outfile, "");
 82 |   if (verbose==1) fprintf(stderr,"\t->Dumping file: %s\n", foutpost);
 83 |   outpost = getFILE(foutpost, "w");
 84 | 
 85 |   /// GET POSITIONS OF BLOCKS
 86 |   // if block_size longer than nsites
 87 |   if (block_size>(nsites-firstbase+1)) block_size=(nsites-firstbase+1);
 88 |   if (block_size==0) block_size=nsites-firstbase+1;
 89 | 
 90 |   array<int> start; array<int> end;
 91 |   start=getStart(nsites, firstbase, block_size);
 92 |   end=getEnd(nsites, firstbase, block_size);
 93 |   int nwin= (nsites-firstbase+1)/block_size;
 94 |   if ( ( (nsites-firstbase+1) % block_size)>0) nwin=nwin+1;
 95 |   if (verbose==1) fprintf(stderr, "\nLen %d and win %d and rest is %d", (nsites-firstbase+1), block_size, ( (nsites-firstbase+1) % block_size));
 96 | 
 97 |   if (verbose==1) fprintf(stderr, "\nNum of win %d and win[0] is %d %d\n", nwin, start.data[0], end.data[0]);
 98 | 
 99 |   /// ITERATE OVER EACH BLOCK
100 |   for (int n=0; n<nwin; n++) {
101 | 
102 |     if (verbose==1) fprintf(stderr, "Block %d out of %d from %d to %d\n", n, (nwin-1), start.data[n], end.data[n]);
103 | 
104 |     // READ POSTERIOR PROBABILITIES FILES
105 |     matrix<double> post1;
106 |     matrix<double> post2;
107 |     post1 = readFileSub(sfsfile1, nind1, start.data[n], end.data[n]);
108 |     if (npop==2) {
109 |       post2 = readFileSub(sfsfile2, nind2, start.data[n], end.data[n]);
110 |     }
111 | 
112 |     // NORM from LOG
113 |     normSFS(post1, true);
114 |     if(npop==2) normSFS(post2, true);
115 | 
116 |     if (npop==1) computeStats(post1, verbose, outpost, iswin, start.data[n]);
117 |     if (npop==2) computeStats2Pops(post1, verbose, outpost, iswin, start.data[n], post2);
118 | 
119 |     cleanup(post1);
120 |     if (npop==2) cleanup(post2);
121 | 
122 |   } // end for n
123 | 
124 |   delete [] start.data;
125 |   delete [] end.data;
126 | 
127 |   fclose(outpost);
128 |   free(foutpost);
129 | 
130 |   return 0;
131 | 
132 | 
133 | } // end main
134 | 


--------------------------------------------------------------------------------
/ngsCovar.hpp:
--------------------------------------------------------------------------------
  1 | 
  2 | #include "shared.hpp"
  3 | 
  4 | // print help
  5 | void info() {
  6 |   fprintf(stdout, "\nInput:\n-probfile: file with genotype posterior probabilities [required]\n-outfile: name of output file [required], currently it is a text file, tab separated with n*n cells\n-sfsfile: file with SFS posterior probabilities [required if you want to weight each site by its probability of being variable]\n-nind: nr of individuals [required]\n-nsites: nr of sites [required]\n-norm: if 0 no normalization, if 1 matrix is normalized by (p(1-p)) as in Patterson et al 2006, if 2 normalization is 2p(1-p) [0]\n-verbose: level of verbosity [0]\n-block_size: how many sites per block when reading the input file [0]\n-call: whether calling genotypes (1) or not (0) [0]\n-offset: starting position of subset analysis [1]\n-minmaf: filter out sites with estimated MAF less than minmaf or greater than 1-minmaf [0] (this filtering will be ignored when using the weighting approach\n-genoquality: text file with nsites lines; each line has a 0 and 1; if 0 the program will ignore this site [NULL]\n\n");
  7 | }
  8 | 
  9 | // compute estimated allele frequencies from genotype posterior probabilities
 10 | array<double> getAlleFreq (matrix<double> &m) {
 11 |   // m is dimensions: nsites * (nind*3)
 12 |   int nsites = m.x;
 13 |   int nind = m.y/3;
 14 |   double somma;
 15 |   double *tmp = new double[nsites];
 16 |   for (int i=0; i<nsites; i++) {
 17 |     somma = 0.0;
 18 |     for (int j=0; j<nind; j++) {
 19 |       somma = somma + m.data[i][(j*3)+1] + (2*m.data[i][(j*3)+2]);
 20 |     }
 21 |     tmp[i] = somma / (nind*2);    
 22 |   }  
 23 |   array<double> ret;
 24 |   ret.x = nsites;
 25 |   ret.data = tmp;
 26 |   return ret;
 27 | }
 28 | 
 29 | // get the covariance for a pair of individual; output is the effective number of sites (expected or passed the filter)
 30 | double calcCovarUp (matrix<double> &m, array<double> a, matrix<double> &covar, double minmaf, array<int> good, int start, int norm) {
 31 |   int nsites = m.x;
 32 |   int nind = m.y/3;
 33 |   if (nsites != a.x) {
 34 |     fprintf(stderr, "\n prob file and alle freq dimensions disagree. Terminate.");
 35 |     exit(-1);
 36 |   }
 37 |   double eff_nsites=0.0;
 38 |   for (int s=0; s<nsites; s++) {
 39 |     if ((a.data[s]>minmaf) & (a.data[s]<(1-minmaf))) {
 40 |       eff_nsites=eff_nsites+1.0;
 41 |     }
 42 |   }
 43 |   double somma = 0.0, subsomma = 0.0;
 44 |   double **data = new double*[nind];
 45 |   for (int i=0; i<nind; i++) {
 46 |     double *tmp = new double[nind];
 47 |     for (int j=0; j<(i+1); j++) {
 48 |       somma = 0.0;
 49 |       for (int s=0; s<nsites; s++) {
 50 | 	subsomma = 0.0;
 51 |         if ((a.data[s]>minmaf) & (a.data[s]<(1-minmaf))) {
 52 | 	  for (int C1=0; C1<3; C1++) {
 53 |             for (int C2=0; C2<3; C2++) {
 54 |              subsomma = subsomma + (C1-(2*a.data[s]))*(C2-(2*a.data[s]))*m.data[s][(i*3)+C1]*m.data[s][(j*3)+C2];
 55 |             }
 56 | 	  }
 57 |           subsomma = subsomma * good.data[start+s];
 58 |           if (norm==1) subsomma = subsomma /  ((a.data[s]*(1-a.data[s])));
 59 |           if (norm==2) subsomma = subsomma /  (2*(a.data[s]*(1-a.data[s])));
 60 |         }
 61 | 	if (isnan(subsomma)==0) somma = somma + subsomma;
 62 |       }
 63 |       tmp[j] = somma;
 64 |     }
 65 |     data[i] = tmp;
 66 |   }
 67 |   fprintf(stderr, "Message (not error/warning): for this window nsites is %d and effective is %f\n", nsites, eff_nsites);
 68 |   matrix<double> ret;
 69 |   ret.x = nind;
 70 |   ret.y = nind;
 71 |   ret.data = data;
 72 |   for (int i=0;i<covar.x;i++) {
 73 |     for (int j=0;j<(i+1);j++) {
 74 |       covar.data[i][j]=covar.data[i][j]+ret.data[i][j];
 75 |       covar.data[j][i]=covar.data[j][i]+ret.data[i][j];
 76 |     }
 77 |   }
 78 |   cleanup(ret);
 79 |   return eff_nsites;  
 80 | }
 81 | 
 82 | 
 83 | // get the covariance for a pair of individual by weighting by
 84 | void calcCovarUpProb (matrix<double> &m, array<double> a, matrix<double> &covar, array<double> pvar, array<int> good, int start, int norm) {
 85 |   int nsites = m.x;
 86 |   int nind = m.y/3;
 87 |   if (nsites != a.x) {
 88 |     fprintf(stderr, "\n prob file and alle freq dimensions disagree. Terminate.");
 89 |     exit(-1);
 90 |   }
 91 |   double somma = 0.0, subsomma = 0.0;
 92 |   double **data = new double*[nind];
 93 |   for (int i=0; i<nind; i++) {
 94 |     double *tmp = new double[nind];
 95 |     for (int j=0; j<(i+1); j++) {
 96 |       somma = 0.0;
 97 |       for (int s=0; s<nsites; s++) {
 98 | 	    subsomma = 0.0;
 99 | 	    for (int C1=0; C1<3; C1++) {
100 |               for (int C2=0; C2<3; C2++) {
101 | 	        subsomma = subsomma + (C1-(2*a.data[s]))*(C2-(2*a.data[s]))*m.data[s][(i*3)+C1]*m.data[s][(j*3)+C2];
102 |               }
103 | 	    }
104 |             subsomma=subsomma * good.data[start+s] * pvar.data[s]; 
105 |             if (norm==1) subsomma = subsomma /  ((a.data[s]*(1-a.data[s])));
106 |             if (norm==2) subsomma = subsomma /  (2*(a.data[s]*(1-a.data[s])));
107 | 	    if (isnan(subsomma)==0) somma = somma + subsomma;
108 |       }
109 |       tmp[j] = somma;
110 |     }
111 |     data[i] = tmp;
112 |   }
113 |   matrix<double> ret;
114 |   ret.x = nind;
115 |   ret.y = nind;
116 |   ret.data = data;
117 |   for (int i=0;i<covar.x;i++) {
118 |     for (int j=0;j<(i+1);j++) {
119 |       covar.data[i][j]=covar.data[i][j]+(ret.data[i][j]);
120 |       covar.data[j][i]=covar.data[j][i]+(ret.data[i][j]);
121 |     }
122 |   }
123 |   cleanup(ret);
124 | }
125 | 
126 | 
127 | 


--------------------------------------------------------------------------------
/ngs2dSFS.cpp:
--------------------------------------------------------------------------------
  1 | 
  2 | // a program to estimate 2D-SFS from genotype posterior probabilities
  3 | 
  4 | #include <cstdio> //for stderr,stdout
  5 | #include <cstdlib> //for atoi
  6 | #include <sys/stat.h> //for getting file attributes
  7 | #include <cstring> //for str operations
  8 | #include <vector> 
  9 | #include <math.h> // for exponential and log
 10 | #include "ngs2dSFS.hpp" // include templates, functions
 11 | 
 12 | // input is the output of sfstools
 13 | 
 14 | // to compile: g++ -Wall -O0 -g ngs2dSFS.cpp -o ngs2dSFS
 15 | 
 16 | int main (int argc, char *argv[]) {
 17 |   
 18 |   if (argc==1) {
 19 |     fprintf(stdout, "\nInput:\n-postfiles: file with sample allele frequency posterior probabilities for each population\n-outfile: name of output file\n-nind: number of individuals per population\n    -nsites: number of sites, or upper limit in case of analyzing a subset\n-block_size: memory efficiency, number of sites for each chunk\n-offset: lower limit in case of analyzing a subset\n-maxlike: if 1 compute the most likely joint allele frequency and sum across sites, if 0 it computes the sum of the products of likelihoods\n-relative: boolean, if 1 number are relative frequencies from 0 to 1 which sum up 1; if 0 numbers are absolute counts of sites having a specific joint allele frequency\n-offset: lower limit of sites in case you want to analyze a subset\n\n");
 20 |     return 0;
 21 |   }
 22 | 
 23 |   /// DECLARE AND INITIALIZE VARIABLES
 24 |   
 25 |   char *sfsfile1=NULL;
 26 |   char *sfsfile2=NULL;
 27 |   
 28 |   FILE *outpost;
 29 |   char *outfile=NULL;
 30 |   char *foutpost=NULL;
 31 |   
 32 |   int argPos = 1;
 33 |   int increment = 0;
 34 |   int nind1 = 0, nind2 = 0, nsites = 0;
 35 |   int block_size = 10000;
 36 |   int firstbase = 1;
 37 |   int relative = 1;
 38 |   int maxlike=1;
 39 | 
 40 |   // READ AND ASSIGN INPUT PARAMETERS
 41 |   
 42 |    while (argPos<argc) {
 43 |     increment = 0;
 44 |     if(strcmp(argv[argPos],"-postfiles")==0) {
 45 |       sfsfile1 = argv[argPos+1];
 46 |       sfsfile2 = argv[argPos+2];
 47 |       increment = 1;
 48 |     }
 49 |     else if(strcmp(argv[argPos],"-outfile")==0) outfile = argv[argPos+1];
 50 |     else if(strcmp(argv[argPos],"-nind")==0) {
 51 |       nind1 = atoi(argv[argPos+1]);
 52 |       nind2 = atoi(argv[argPos+2]);
 53 |       increment = 1;
 54 |     }
 55 |     else if(strcmp(argv[argPos],"-nsites")==0) nsites = atoi(argv[argPos+1]);
 56 |     else if(strcmp(argv[argPos],"-block_size")==0) block_size = atoi(argv[argPos+1]);    
 57 |     else if(strcmp(argv[argPos],"-offset")==0) firstbase = atoi(argv[argPos+1]); 
 58 |     else if(strcmp(argv[argPos],"-maxlike")==0) maxlike = atoi(argv[argPos+1]);
 59 |     else if(strcmp(argv[argPos],"-relative")==0) relative = atoi(argv[argPos+1]);
 60 |     else {
 61 |       printf("\tUnknown arguments: %s\n",argv[argPos]);
 62 |       return 0;
 63 |     }
 64 |   
 65 |     argPos = argPos + 2 + increment;
 66 |   
 67 |   } // end while all inputs
 68 | 
 69 |   // check if there is the input file
 70 |   if((sfsfile1 == NULL) & (sfsfile2 == NULL) ) {
 71 |     fprintf(stderr,"\nMust supply -postfiles.\n");
 72 |     return 0;
 73 |   }
 74 |   // check if there is the output file
 75 |   if(outfile == NULL) {
 76 |     fprintf(stderr,"\nMust supply -outfile.\n");
 77 |     return 0;
 78 |   }
 79 | 
 80 |   // prepare output file
 81 |   foutpost = append(outfile, "");
 82 |   outpost = getFILE(foutpost, "w");
 83 | 
 84 |   // output
 85 |   matrix<double> spec;
 86 |   spec.x=(2*nind1)+1;
 87 |   spec.y=(2*nind2)+1;
 88 | 
 89 |   double **data = new double*[spec.x];
 90 |   for (int i=0; i<spec.x; i++) {
 91 |     double *tmp = new double[spec.y];
 92 |     for (int j=0; j<spec.y; j++) {
 93 |       tmp[j] = 0.0;
 94 |      }
 95 |     data[i] = tmp;
 96 |   }
 97 |   spec.data = data;
 98 | 
 99 | 
100 |   /// READ POSTERIOR PROBABILITY FILES
101 | 
102 |   // BLOCKS
103 |   /// GET POSITIONS OF BLOCKS
104 |   if (block_size>(nsites-firstbase+1)) block_size=(nsites-firstbase+1);
105 |   if (block_size==0) block_size=nsites-firstbase+1;
106 |   array<int> start; array<int> end;
107 |   start=getStart(nsites, firstbase, block_size);
108 |   end=getEnd(nsites, firstbase, block_size);
109 |   int nwin= (nsites-firstbase+1)/block_size;
110 |   if ( ( (nsites-firstbase+1) % block_size)!=0) nwin++;
111 | 
112 |   matrix<double> post1;
113 |   matrix<double> post2; 
114 | 
115 |   // for each block
116 |   for (int n=0; n<nwin; n++) {
117 |       
118 |     // fprintf(stderr, "win %d out of %d from %d to %d\n", n, (nwin-1), start.data[n], end.data[n]);
119 |     post1 = readFileSub(sfsfile1, nind1, start.data[n], end.data[n]);
120 |     post2 = readFileSub(sfsfile2, nind2, start.data[n], end.data[n]);
121 |     // Normalize SFS
122 |     normSFS(post1, true);
123 |     normSFS(post2, true);
124 | 
125 |     // COMPUTE SFS
126 |     sumSpectrum(spec, post1, post2, maxlike);
127 | 
128 |     // clean
129 |     cleanup(post1);
130 |     cleanup(post2);
131 | 
132 |   } // end for in nwin
133 | 
134 |   delete [] start.data;
135 |   delete [] end.data;
136 | 
137 |   // if relative divide by nsites
138 |   if (relative) {
139 |     if (maxlike) {
140 |      for (int i=0; i<spec.x; i++) {
141 |       for (int j=0; j<spec.y; j++) {
142 |         spec.data[i][j]=spec.data[i][j] / (nsites-firstbase);
143 |       }
144 |      }
145 |     } else {
146 | 
147 |      double sumspec=0.0;
148 |      for (int i=0; i<spec.x; i++) {
149 |       for (int j=0; j<spec.y; j++) {
150 |         sumspec=sumspec+spec.data[i][j];
151 |       }
152 |      }
153 |      for (int i=0; i<spec.x; i++) {
154 |       for (int j=0; j<spec.y; j++) {
155 |         spec.data[i][j]=spec.data[i][j] / sumspec;
156 |       }
157 |      }
158 | 
159 |     }
160 |   }
161 | 
162 |   // write
163 |   writematrix(spec, outpost);
164 |   cleanup(spec);
165 | 
166 |   // close file
167 |   fclose(outpost); 
168 |   free(foutpost);
169 | 
170 |   //return 0;
171 | 
172 | } // end main
173 | 


--------------------------------------------------------------------------------
/scripts/plotSS.R:
--------------------------------------------------------------------------------
  1 | 
  2 | # Usage: Rscript -i infile.stat -o outfile -p positions.txt -n name1-name2 -w window_size -s step_size
  3 | # Usage: Rscript -i infile.stat -o outfile -p positions.txt -n name1 -w window_size -s step_size # if only 1 pop
  4 | 
  5 | # Output:
  6 | # outfile.eps & output.txt: plot and text with sliding windows values
  7 | 
  8 | library(methods)
  9 | library(grid)
 10 | library(optparse)
 11 | library(ggplot2)
 12 | 
 13 | option_list <- list(make_option(c('-i','--in_file'), action='store', type='character', default=NULL, help='Input file'),
 14 |                     make_option(c('-n','--names'), action='store', type='character', default=1-2, help='Name(s) of population(s)'),
 15 |                     make_option(c('-o','--out_file'), action='store', type='character', default=NULL, help='Output file'),
 16 | 			make_option(c('-p','--pos_file'), action='store', type='character', default=NULL, help='Input position file'),
 17 | 			make_option(c('-w','--window'), action='store', type='character', default=1, help='Window length'),
 18 | 			make_option(c('-s','--step'), action='store', type='character', default=1, help='Step size')
 19 |                     )
 20 | opt <- parse_args(OptionParser(option_list = option_list))
 21 | 
 22 | # from: http://www.cookbook-r.com/Graphs/Multiple_graphs_on_one_page_(ggplot2)/
 23 | # Multiple plot function
 24 | #
 25 | # ggplot objects can be passed in ..., or to plotlist (as a list of ggplot objects)
 26 | # - cols:   Number of columns in layout
 27 | # - layout: A matrix specifying the layout. If present, 'cols' is ignored.
 28 | #
 29 | # If the layout is something like matrix(c(1,2,3,3), nrow=2, byrow=TRUE),
 30 | # then plot 1 will go in the upper left, 2 will go in the upper right, and
 31 | # 3 will go all the way across the bottom.
 32 | #
 33 | multiplot <- function(..., plotlist=NULL, file, cols=1, layout=NULL) {
 34 |   require(grid)
 35 | 
 36 |   # Make a list from the ... arguments and plotlist
 37 |   plots <- c(list(...), plotlist)
 38 | 
 39 |   numPlots = length(plots)
 40 | 
 41 |   # If layout is NULL, then use 'cols' to determine layout
 42 |   if (is.null(layout)) {
 43 |     # Make the panel
 44 |     # ncol: Number of columns of plots
 45 |     # nrow: Number of rows needed, calculated from # of cols
 46 |     layout <- matrix(seq(1, cols * ceiling(numPlots/cols)),
 47 |                     ncol = cols, nrow = ceiling(numPlots/cols))
 48 |   }
 49 | 
 50 |  if (numPlots==1) {
 51 |     print(plots[[1]])
 52 | 
 53 |   } else {
 54 |     # Set up the page
 55 |     grid.newpage()
 56 |     pushViewport(viewport(layout = grid.layout(nrow(layout), ncol(layout))))
 57 | 
 58 |     # Make each plot, in the correct location
 59 |     for (i in 1:numPlots) {
 60 |       # Get the i,j matrix positions of the regions that contain this subplot
 61 |       matchidx <- as.data.frame(which(layout == i, arr.ind = TRUE))
 62 | 
 63 |       print(plots[[i]], vp = viewport(layout.pos.row = matchidx$row,
 64 |                                       layout.pos.col = matchidx$col))
 65 |     }
 66 |   }
 67 | }
 68 | 
 69 | 
 70 | # How many pops
 71 | pops <- as.character(strsplit(opt$names, "-", fixed=TRUE)[[1]]);
 72 | npop=length(pops);
 73 | cat("Detected", npop, "populations.\n")
 74 | 
 75 | # Read input file
 76 | values <- read.table(opt$in_file, stringsAsFact=F);
 77 | # [old] pos=as.numeric(values[,1]+(values[,2]-values[,1])/2);
 78 | pos <- as.numeric(readLines(opt$pos_file))
 79 | if (length(pos)!=nrow(values)) stop("Dimensions of 1values and positions must match. Terminate.\n");
 80 | 
 81 | # create dataframe of windows values here
 82 | # Windows
 83 | len=max(pos)
 84 | win=as.numeric(opt$window);
 85 | step=as.numeric(opt$step);
 86 | start=seq(min(pos), len, step);
 87 | end=start+win-1;
 88 | wpos=round(start+(win/2)); # position of the window in the plot (center)
 89 | 
 90 | # windows values
 91 | sub=matrix(NA, nrow=length(start), ncol=(ncol(values)-2)); # S, pi (S2, pi2, diff, dxy)
 92 | for (i in 1:length(start)) {
 93 | 	ipos=which(pos>=start[i] & pos<=end[i])
 94 | 	sub[i,]=apply(MAR=2, X=values[ipos,3:(ncol(values))], FUN=sum, na.rm=T)
 95 | }
 96 | 
 97 | values=sub
 98 | pos=wpos
 99 | 
100 | # Plot
101 | 
102 | if (npop==2) {
103 |   title <- "";
104 | 
105 |   # Data
106 |   df = data.frame(cbind( Pop=c(rep(pops[1],length(pos)),rep(pops[2],length(pos))), Pos=pos, Segr.sites=c(values[,1], values[,3]), Exp.heterozygosity=c(values[,2],values[,4]), Fixed.differences=(rep(values[,5],2)), Dxy=(rep(values[,6],2)),  Pops=c(rep(paste(pops[1],"\n",pops[2]),length(pos)*2)) ) );
107 |   df[,2:5] = sapply(df[,2:5], as.character)
108 |   df[,2:5] = sapply(df[,2:5], as.numeric)
109 | 
110 |   p1 = ggplot(data=df, aes(x=Pos, y=Segr.sites, color=Pop)) + geom_line() + ggtitle(title)
111 |   p2 = ggplot(data=df, aes(x=Pos, y=Exp.heterozygosity, color=Pop)) + geom_line() + ggtitle(title)
112 |   p3 = ggplot(data=df, aes(x=Pos, y=Fixed.differences, color=Pops)) + geom_line() + ggtitle(title)
113 |   p4 = ggplot(data=df, aes(x=Pos, y=Dxy, color=Pops)) + geom_line() + ggtitle(title)
114 | 
115 |   pdf(paste(opt$out_file,".eps",sep="",collapse=""));
116 |   multiplot(p1, p2, p3, p4, ncol=2)
117 |   null <- dev.off();
118 | 
119 |   df=df[,2:6]
120 | 
121 | }
122 | 
123 | if (npop==1) {
124 |   df = data.frame(cbind( Pop=rep(pops[1],length(pos)), Pos=pos, Segr.sites=values[,1], Exp.heterozygosity=values[,2]));
125 |   df[,2:4] = sapply(df[,2:4], as.character)
126 |   df[,2:4] = sapply(df[,2:4], as.numeric)
127 | 
128 |   title <- "";
129 | 
130 |   p1 = ggplot(data=df, aes(x=Pos, y=Segr.sites, color=Pop)) + geom_line() + ggtitle(title)
131 |   p2 = ggplot(data=df, aes(x=Pos, y=Exp.heterozygosity, color=Pop)) + geom_line() + ggtitle(title)
132 | 
133 |   pdf(paste(opt$out_file,".eps",sep="",collapse=""));
134 |   multiplot(p1, p2, ncol=1)
135 |   null <- dev.off();
136 | 
137 |   df=df[,2:4]
138 | }
139 | 
140 | write.table(df, file=paste(opt$out_file,".txt",sep="",collapse=""), sep="\t", quote=F, row.names=F, col.names=T)
141 | 
142 | 


--------------------------------------------------------------------------------
/ngsStat.hpp:
--------------------------------------------------------------------------------
  1 | #include "shared.hpp"
  2 | 
  3 | // print help
  4 | void info() {
  5 |   fprintf(stdout, "\nInput:\n-npop: how many pops (1 or 2)\n-postfiles: .sfs files with posterior probabilities of sample allele frequencies for each population (with or without running sfstools)\n-outfile: name of the output file\n-nind: number of individuals for each population\n-nsites: total number of sites; in case you want to analyze a subset of sites this is the upper limit\n-verbose: level of verbosity, if 0 suppress all messages\n-block_size: to be memory efficient, set this number as the number of sites you want to analyze at each chunk\n-firstbase: in case you want to analyze a subset of your sites this is the lower limit\n-iswin: if 1 then print the value computed for each non-overlapping window defined by block_size\n\n");
  6 | }
  7 | 
  8 | 
  9 | // compute summary stats for each block in case of 1 pop and print the results
 10 | void computeStats(matrix<double> &post1, int verbose, FILE *outpost, int iswin, int start) {
 11 | 
 12 |   int nind = (post1.y-1)/2; // sample size
 13 |   int nsites = post1.x;
 14 | 
 15 |   // init
 16 |   array<double> segsites;
 17 |   segsites.x=nsites;
 18 |   double *tmp1 = new double [nsites];
 19 |   for (int i=0; i<nsites; i++) { 
 20 |     tmp1[i]=0.0; 
 21 |   }
 22 |   segsites.data=tmp1;
 23 | 
 24 |   array<double> hetero;
 25 |   hetero.x=nsites;
 26 |   double *tmp2 = new double [nsites];
 27 |   for (int i=0; i<nsites; i++) { 
 28 |     tmp2[i]=0.0; 
 29 |   }
 30 |   hetero.data=tmp2;
 31 | 
 32 |   double temp=0.0;
 33 | 
 34 |   // to convert from 0 base to 1 base  
 35 |   int start0=start+1;
 36 | 
 37 |   double sum_segsites = 0.0, sum_hetero = 0.0;
 38 | 
 39 |   for (int s=0; s<nsites; s++) {
 40 | 
 41 |     start++;
 42 | 
 43 |     segsites.data[s] = 1.0 - post1.data[s][0];
 44 | 
 45 |     if (verbose==2) fprintf(stderr, "\n%f %f", post1.data[s][0], segsites.data[s]);
 46 |     segsites.data[s] = segsites.data[s] - post1.data[s][post1.y-1];
 47 |     if (verbose==2) fprintf(stderr, " %f %f", post1.data[s][post1.y-1],  segsites.data[s]);
 48 | 
 49 |     temp=0.0;
 50 |     for (int j=0; j<post1.y; j++) { temp = temp+ 2.0*(j/(nind*2.0))*((nind*2.0-j)/(nind*2.0))*post1.data[s][j];  }
 51 |     hetero.data[s]=temp;
 52 | 
 53 |     if (iswin==0) fprintf(outpost, "%d\t%d\t%f\t%f\n", start, start, segsites.data[s], hetero.data[s]);
 54 | 
 55 |     sum_segsites=sum_segsites+segsites.data[s];
 56 |     sum_hetero=sum_hetero+hetero.data[s];
 57 | 
 58 |   } // end cycle s
 59 | 
 60 |   // compute sum across all sites 
 61 |   if (iswin==1) fprintf(outpost, "%d\t%d\t%f\t%f\n", start0, start, sum_segsites, sum_hetero);
 62 | 
 63 |   delete [] segsites.data;
 64 |   delete [] hetero.data;
 65 | 
 66 | }
 67 | 
 68 | 
 69 | // compute summary stats for each block in case of 2 pops and print the results
 70 | void computeStats2Pops(matrix<double> &post1, int verbose, FILE *outpost, int iswin, int start, matrix<double> &post2) {
 71 |   // sample sizes
 72 |   int nind1 = (post1.y-1)/2;
 73 |   int nind2 = (post2.y-1)/2;
 74 |   int nsites=post1.x;
 75 | 
 76 |   // init
 77 |   array<double> segsites1;
 78 |   segsites1.x=nsites;
 79 |   array<double> hetero1;
 80 |   hetero1.x=nsites;
 81 |   array<double> segsites2;
 82 |   segsites2.x=nsites;
 83 |   array<double> hetero2;
 84 |   hetero2.x=nsites;
 85 |   array<double> fixed;
 86 |   fixed.x=nsites;
 87 |   array<double> dxy;
 88 |   dxy.x=nsites;
 89 | 
 90 |   double *tmp1= new double [nsites];
 91 |   for (int i=0; i<nsites; i++) { tmp1[i]=0.0; }
 92 |   segsites1.data=tmp1;
 93 |   double *tmp2= new double [nsites];
 94 |   for (int i=0; i<nsites; i++) { tmp2[i]=0.0; }
 95 |   hetero1.data=tmp2;
 96 |   double *tmp3= new double [nsites];
 97 |   for (int i=0; i<nsites; i++) { tmp3[i]=0.0; }
 98 |   segsites2.data=tmp3;
 99 |   double *tmp4= new double [nsites];
100 |   for (int i=0; i<nsites; i++) { tmp4[i]=0.0; }
101 |   hetero2.data=tmp4;
102 |   double *tmp5= new double [nsites];
103 |   for (int i=0; i<nsites; i++) { tmp5[i]=0.0; }
104 |   fixed.data=tmp5;
105 |   double *tmp6= new double [nsites];
106 |   for (int i=0; i<nsites; i++) { tmp6[i]=0.0; }
107 |   dxy.data=tmp6;
108 | 
109 |   double temp=0.0;
110 | 
111 |   // to convert from 0 base to 1 base  
112 |   int start0=start+1;
113 | 
114 |   double sum_segsites1=0.0, sum_hetero1=0.0;
115 |   double sum_segsites2=0.0, sum_hetero2=0.0;
116 |   double sum_fixed=0.0;
117 |   double sum_dxy=0.0;
118 | 
119 |   for (int s=0; s<nsites; s++) {
120 | 
121 |     start++;
122 | 
123 |     segsites1.data[s]= 1.0 - post1.data[s][0];
124 |     segsites1.data[s]=segsites1.data[s] - post1.data[s][post1.y-1];
125 |     temp=0.0;
126 |     for (int j=0; j<post1.y; j++) { temp=temp + 2.0*(j/(nind1*2.0))*((nind1*2.0-j)/(nind1*2.0))*post1.data[s][j]; }
127 |     hetero1.data[s]=temp;
128 |     sum_segsites1=sum_segsites1+segsites1.data[s];
129 |     sum_hetero1=sum_hetero1+hetero1.data[s];
130 | 
131 |     segsites2.data[s]= 1.0 - post2.data[s][0];
132 |     segsites2.data[s]=segsites2.data[s] - post2.data[s][post2.y-1];
133 |     temp=0.0;
134 |     for (int j=0; j<post2.y; j++) { temp=temp + 2.0*(j/(nind2*2.0))*((nind2*2.0-j)/(nind2*2.0))*post2.data[s][j]; }
135 |     hetero2.data[s]=temp;
136 |     sum_segsites2=sum_segsites2+segsites2.data[s];
137 |     sum_hetero2=sum_hetero2+hetero2.data[s];
138 | 
139 |     fixed.data[s]=post1.data[s][0]*post2.data[s][post2.y-1] + post2.data[s][0]*post1.data[s][post1.y-1]; 
140 |     sum_fixed = sum_fixed + fixed.data[s];
141 | 
142 |     dxy.data[s]=0.0;
143 |     for (int i=0; i<post1.y; i++)
144 |       for (int j=0; j<post2.y; j++)
145 | 	dxy.data[s] = dxy.data[s] + ( ( (i/(nind1*2.0))*(((nind2*2.0)-j)/(nind2*2.0)) + (((nind1*2.0)-i)/(nind1*2.0))*(j/(nind2*2.0)) ) * post1.data[s][i] * post2.data[s][j] ) ;
146 |     sum_dxy = sum_dxy + dxy.data[s];
147 | 
148 | 
149 |     if (iswin==0) fprintf(outpost, "%d\t%d\t%f\t%f\t%f\t%f\t%f\t%f\n", start, start, segsites1.data[s], hetero1.data[s], segsites2.data[s], hetero2.data[s], fixed.data[s], dxy.data[s]);
150 | 
151 |   } // end cycle s
152 | 
153 |   // compute sum across all sites 
154 |   if (iswin==1) fprintf(outpost, "%d\t%d\t%f\t%f\t%f\t%f\t%f\t%f\n", start0, start, sum_segsites1, sum_hetero1, sum_segsites2, sum_hetero2, sum_fixed, sum_dxy);
155 | 
156 |   delete [] segsites1.data;
157 |   delete [] hetero1.data;
158 |   delete [] segsites2.data;
159 |   delete [] hetero2.data;
160 |   delete [] fixed.data;
161 |   delete [] dxy.data;
162 | 
163 | }
164 | 
165 | 


--------------------------------------------------------------------------------
/ngsFST.cpp:
--------------------------------------------------------------------------------
  1 | 
  2 | // ngsFST computes an approximation of the expected FST=a/(a+b) (see Reynolds et al 1983) from expected a and expected b and correct for the ratio of a and b; it works in blocks of sites so it is memory efficient; it can receive in input a file from ANGSD -realSFS 1 or ANGSD -realSFS1 + optimSFS + sfstools.
  3 | 
  4 | // Ouput: a text file, each row is a site and columsn are tab separated: a, a+b, FACT, theta, pvar
  5 | 
  6 | #include <cstdio>
  7 | #include <cstdlib>
  8 | #include <sys/stat.h>
  9 | #include <cstring>
 10 | #include <vector> 
 11 | #include <math.h>
 12 | 
 13 | #include "ngsFST.hpp"
 14 |  
 15 | // to compile: g++ ngsFST.cpp -Wall -o bin/ngsFST -lm -lz -O0 -g
 16 | 
 17 | int main (int argc, char *argv[]) {
 18 |   
 19 |    if (argc==1) {
 20 |     info();
 21 |    return 0;   
 22 |   }
 23 | 
 24 |   /// DECLARE AND INITIALIZE VARIABLES
 25 |   
 26 |   char *sfsfile1=NULL; // posterior probabilities or sample allele frequency likelihoods
 27 |   char *sfsfile2=NULL;
 28 |   char *priorfile1=NULL; // marginal priors
 29 |   char *priorfile2=NULL;
 30 |   char *priorfile12=NULL; // joint prior, it is 2D-SFS
 31 | 
 32 |   FILE *outpost;
 33 |   char *outfile=NULL;
 34 |   char *foutpost=NULL;
 35 |   
 36 |   int argPos = 1, increment = 0, nind = 0, nind1 = 0, nind2 = 0, nsites = 0, verbose = 0, nsums = 1, block_size = 20000, firstbase=1;
 37 | 
 38 |   /// READ AND ASSIGN INPUT PARAMETERS
 39 |   
 40 |    while (argPos<argc) {
 41 |     increment = 0;
 42 |     if(strcmp(argv[argPos],"-postfiles")==0) {
 43 |       sfsfile1 = argv[argPos+1];
 44 |       sfsfile2 = argv[argPos+2];
 45 |       increment = 1;
 46 |     }
 47 |     else if(strcmp(argv[argPos],"-priorfile")==0) {
 48 |       priorfile12 = argv[argPos+1];
 49 |     }
 50 |     else if(strcmp(argv[argPos],"-priorfiles")==0) {
 51 |       priorfile1 = argv[argPos+1];
 52 |       priorfile2 = argv[argPos+2];
 53 |       increment = 1;
 54 |     }     
 55 |     else if(strcmp(argv[argPos],"-outfile")==0) outfile = argv[argPos+1];
 56 |     else if(strcmp(argv[argPos],"-nind")==0) {
 57 |       nind1 = atoi(argv[argPos+1]);
 58 |       nind2 = atoi(argv[argPos+2]);
 59 |       nind = nind1 + nind2;
 60 |       increment = 1;
 61 |     }
 62 |     else if(strcmp(argv[argPos],"-nsites")==0) nsites = atoi(argv[argPos+1]);
 63 |     else if(strcmp(argv[argPos],"-verbose")==0) verbose = atoi(argv[argPos+1]);
 64 |     else if(strcmp(argv[argPos],"-block_size")==0) block_size = atoi(argv[argPos+1]);    
 65 |     else if(strcmp(argv[argPos],"-firstbase")==0) firstbase = atoi(argv[argPos+1]);
 66 |     else {
 67 |       printf("\tUnknown arguments: %s\n",argv[argPos]);
 68 |       info();
 69 |       return 0; // terminate
 70 |     }
 71 |     argPos = argPos + 2 + increment;
 72 |   }
 73 |   
 74 |   /// CHECK INPUT
 75 |   if((sfsfile1 == NULL) & (sfsfile2 == NULL) ) {
 76 |     fprintf(stderr,"\nMust supply -postfiles.\n");
 77 |     info();
 78 |      return 0;
 79 |   }
 80 |   if(outfile == NULL) {
 81 |     fprintf(stderr,"\nMust supply -outfile.\n");
 82 |     info();
 83 |     return 0;
 84 |   }
 85 | 
 86 |   if ((priorfile12==NULL) & (priorfile1==NULL)) {
 87 |     fprintf(stderr, "\nYou are not providing any prior information. Have you already run sfstools?\n");
 88 |   }
 89 | 
 90 |   /// OUTPUT
 91 |   foutpost = append(outfile, "");
 92 |   if (verbose==1) fprintf(stderr,"\t->Dumping file: %s\n", foutpost);
 93 |   outpost = getFILE(foutpost, "w");
 94 |   
 95 |   // print input arguments
 96 |   if(verbose==1) fprintf(stderr,"\t->Using some of these args: -nind %d -nind1 %d -nind2 %d -nsites %d -postfiles %s %s -priorfiles %s %s -priorfile %s -outfile %s -verbose %d -firstbase %d -block_size %d\n", nind, nind1, nind2, nsites, sfsfile1, sfsfile2, priorfile1, priorfile2, priorfile12, foutpost, verbose, firstbase, block_size);
 97 | 
 98 |   // READ PRIORS (if provided)
 99 |   // marginal spectra
100 |   array<double> prior1;
101 |   array<double> prior2;
102 |   if (priorfile1 != NULL) {
103 |     if (verbose==1) fprintf(stderr, "\nReading priors...");
104 |     prior1 = readArray(priorfile1, nind1);
105 |     prior2 = readArray(priorfile2, nind2);
106 |   }
107 |   // 2D-SFS
108 |   matrix<double> prior12;
109 |   if ((priorfile12==NULL)==0) {
110 |     if (verbose==1) fprintf(stderr, "\nReading 2D prior...");
111 |     prior12 = readPrior12(priorfile12, nind1*2+1, nind2*2+1);
112 |     if (verbose==2) {
113 |       fprintf(stderr, "\nPrior 2d:\n");
114 |       writematrix(prior12, stderr);
115 |     }
116 |     //// the difference with this prior is that I don't add the prior, but I add the prior directly at computeFST step
117 |   }
118 | 
119 |   /// GET POSITIONS OF BLOCKS
120 |   if (block_size>(nsites-firstbase+1)) block_size=(nsites-firstbase+1);
121 |   if (block_size==0) block_size=nsites-firstbase+1;
122 |   array<int> start; array<int> end;
123 |   start=getStart(nsites, firstbase, block_size);
124 |   end=getEnd(nsites, firstbase, block_size);
125 |   int nwin= (nsites-firstbase+1)/block_size;
126 |   if ( ( (nsites-firstbase+1) % block_size)!=0) nwin++;
127 | 
128 |   if (verbose==1) fprintf(stderr, "\n num win %d win0 is %d %d\n", nwin, start.data[0], end.data[0]);
129 | 
130 |   /// ITERATE OVER EACH BLOCK
131 |   for (int n=0; n<nwin; n++) {
132 | 
133 |     if (verbose==1) fprintf(stderr, "Block %d out of %d from %d to %d\n", n, (nwin-1), start.data[n], end.data[n]);
134 |   
135 |     // READ POSTERIOR PROBABILITIES FILES
136 |     matrix<double> post1;
137 |     matrix<double> post2;
138 |     post1 = readFileSub(sfsfile1, nind1, start.data[n], end.data[n]);
139 |     post2 = readFileSub(sfsfile2, nind2, start.data[n], end.data[n]);
140 | 
141 |    // print first post probs
142 |     if (verbose==1) {
143 |       fprintf(stderr, "initial post probs 1: %f %f %f\n", post1.data[0][0], post1.data[0][1], post1.data[0][nind1]);
144 |       fprintf(stderr, "initial post probs 2: %f %f %f\n", post2.data[0][0], post2.data[0][1], post2.data[0][nind2]);
145 |     }
146 | 
147 |     // NORM from LOG
148 |     normSFS(post1, 1);
149 |     normSFS(post2, 1);
150 | 
151 |    if (verbose==1) {
152 |       fprintf(stderr, "mid post probs 1: %f %f %f\n", post1.data[0][0], post1.data[0][1], post1.data[0][nind1]);
153 |       fprintf(stderr, "mid post probs 2: %f %f %f\n", post2.data[0][0], post2.data[0][1], post2.data[0][nind2]);
154 |     }
155 | 
156 |     // ADD PRIOR is marginal priors
157 |     if (priorfile1!=NULL) {
158 |       addPrior(post1, prior1);
159 |       addPrior(post2, prior2);
160 |       normSFS(post1, 0);
161 |       normSFS(post2, 0);
162 |     }
163 | 
164 |     // print first post probs
165 |     if (verbose==1) {
166 |       fprintf(stderr, "final post probs 1: %f %f %f\n", post1.data[0][0], post1.data[0][1], post1.data[0][nind1]);
167 |       fprintf(stderr, "final post probs 2: %f %f %f\n", post2.data[0][0], post2.data[0][1], post2.data[0][nind2]);
168 |     }
169 | 
170 |     // CALCULATE FST
171 |     if (verbose==1) fprintf(stderr,"Computing FST.\n");
172 |     if (priorfile12==NULL) {
173 |       computeVarRey(post1, post2, verbose, outpost, nsums);
174 |     } else {
175 |       if (verbose==1) fprintf(stderr,"Using 2D-SFS as prior.\n");
176 |       computeVarRey12(post1, post2, verbose, outpost, nsums, prior12);
177 |     }
178 | 
179 |     cleanup(post1);
180 |     cleanup(post2);
181 |     
182 |   } // end blocks iterations
183 |  
184 |   delete [] start.data;
185 |   delete [] end.data;
186 | 
187 |   if (priorfile12!=NULL) cleanup(prior12);
188 | 
189 |   if (priorfile1!=NULL) delete [] prior1.data;
190 |   if (priorfile2!=NULL) delete [] prior2.data;
191 | 
192 |   fclose(outpost);
193 |   free(foutpost);
194 |   
195 |   return 0;
196 | 
197 | } // end main
198 | 
199 | 
200 | 
201 | 
202 | 
203 | 


--------------------------------------------------------------------------------
/ngsFST.hpp:
--------------------------------------------------------------------------------
  1 | 
  2 | #include "shared.hpp"
  3 | 
  4 | // print help
  5 | void info() {
  6 |   fprintf(stdout, "\nInput:\n-postfiles: .sfs files with posterior probabilities of sample allele frequencies for each population [required]\n-priorfile: 2D-SFS to be used as a prior; you can use ngs2DSFS with parameter -relative set to 1 [NULL]\n-priorfiles: marginal spectra to be used as a prior; you can use optimSFS in ANGSD [NULL]\n-outfile: name of the output file [required]\n-nind: number of individuals for each population [required]\n-nsites: total number of sites; in case you want to analyze a subset of sites this is the upper limit [required]\n-verbose: level of verbosity [0]\n-block_size: to be memory efficient, set this number as the number of sites you want to analyze at each chunk [0]\n-firstbase: in case you want to analyze a subset of your sites this is the lower limit [1]\n\n");
  7 | }
  8 | 
  9 | /// 
 10 | 
 11 | // compute a and ab (using short-cut formulas) given allele frequencies and sample sizes
 12 | array<double> calcAB(int s1, int s2, int n1, int n2, int debug) {
 13 |   if (debug) fprintf(stderr, "\nInside calcAB");
 14 |   double alfa1 = 0.0, alfa2 = 0.0, p1 = 0.0, p2 = 0.0, a = 0.0, ab = 0.0;
 15 |   array<double> res; res.x = 2;
 16 |   double *values= new double [2];
 17 |   if (debug) fprintf(stderr, "%f\t%f\t%f\t%f\t%f\t%f\n", alfa1, alfa2, p1,p2,a,ab);
 18 |   p1 = static_cast<double>(s1) / (2*n1);
 19 |   p2 = static_cast<double>(s2) / (2*n2);
 20 |   if (debug) fprintf(stderr, "%f\t%f\n", p1, p2);
 21 |   alfa1 = 2*p1*(1-p1);  
 22 |   alfa2 = 2*p2*(1-p2);  
 23 |   if (debug) fprintf(stderr, "%f\t%f\n", alfa1, alfa2);
 24 |   a = ((p1-p2)*(p1-p2)) - (((n1+n2) * (n1 * alfa1 + n2 * alfa2)) / (4*n1*n2*(n1+n2-1)));
 25 |   ab = ((p1-p2)*(p1-p2)) + ( ( (4*n1*n2 - n1 - n2) * (n1 * alfa1 + n2 * alfa2) ) / ((4*n1*n2)*(n1+n2-1)) );
 26 |   values[0]=a;
 27 |   values[1]=ab;
 28 |   if (debug) fprintf(stderr, "%f\t%f\n", a, ab);
 29 |   res.data = values;
 30 |   return res;
 31 | }
 32 | 
 33 | // compute a and ab estimate for all possible combinations of sample size, then weight by their prob, but no correction from a first guess of fst
 34 | void computeVarRey(matrix<double> &m1, matrix<double> &m2, int verbose, FILE *fname, int nsums) {
 35 |   // m1 and m2 are post probs
 36 |   /// DEFINITION (DECLARATION AND INITIALIZATION)
 37 |   if (verbose==2) fprintf(stderr, "\nInside computeVarRey");
 38 |   int n1 = 0, n2 = 0; // sample sizes
 39 |   int nsites = 0; // nsites
 40 |   // estimates nsites and pop sizes from matrices
 41 |   n1 = (m1.y-1)/2; // nind1
 42 |   n2 = (m2.y-1)/2; // nind2
 43 |   nsites = m1.x; // nsites from file
 44 |   double VAR = 0.0, COVAR = 0.0, FACT = 0.0;
 45 |   matrix<double> A;
 46 |   matrix<double> AB;
 47 |   array<double> temp;
 48 |   for (int s=0; s<nsites; s++) {
 49 |     if (verbose==2) fprintf(stderr, "\t s %d", s);
 50 |     // for each possible value of freq 1 and freq 2 compute the FST, so compute A, AB, VAR, COVAR (see Price paper for its meaning)
 51 |     A.x=AB.x=(n1*2)+1;
 52 |     A.y=AB.y=(n2*2)+1;
 53 |     // FIRST CYCLE: get expected A and AB and retain matrices of A and AB
 54 |     double **dataA = new double*[(n1*2)+1];
 55 |     double **dataAB = new double*[(n1*2)+1];
 56 |     // get also the probability of site being variable
 57 |     double pvar = 0.0;
 58 |     pvar = 1 - m1.data[s][0]*m2.data[s][0] - m1.data[s][2*n1]*m2.data[s][2*n2];
 59 |     if (verbose==2) fprintf(stderr, "\t first cycle");
 60 |     double EA = 0.0, EAB = 0.0;
 61 |     for (int i=0; i<(2*n1+1); i++) {
 62 |       if (verbose==2) fprintf(stderr, "\ti%d",i);
 63 |       double *bufA = new double[(n2*2)+1];
 64 |       double *bufAB = new double[(n2*2)+1];
 65 |       for (int j=0; j<(2*n2+1); j++) {
 66 |        if (verbose==2) fprintf(stderr, "\tj%d",j);
 67 |         temp = calcAB(i, j, n1, n2, 0);
 68 |         bufA[j]=temp.data[0];
 69 |         bufAB[j]=temp.data[1];
 70 |         EA = EA + temp.data[0]*m1.data[s][i]*m2.data[s][j];
 71 |         EAB = EAB + temp.data[1]*m1.data[s][i]*m2.data[s][j];
 72 |         delete [] temp.data;
 73 |       } // end for in j
 74 |       dataA[i]=bufA;
 75 |       dataAB[i]=bufAB;
 76 |     } // end for in i
 77 |     A.data=dataA;
 78 |     AB.data=dataAB;
 79 |     if (EA<0.0) EA=0.0; // protect against -0.000 cases
 80 |     // SECOND CYCLE: get VAR and COVAR, and then the correcting FACTor, according to number of sums to retain
 81 |     VAR = 0.0, COVAR = 0.0, FACT = 0.0;
 82 |     if ((verbose==4) & (s==0)) fprintf(stderr, "\t second cycle %d", nsums);
 83 |     for (int q=1; q<=nsums; q++) {
 84 |       VAR = 0.0; COVAR = 0.0;
 85 |       for (int i=0; i<(2*n1+1); i++) {
 86 |         for (int j=0; j<(2*n2+1); j++) {
 87 |           VAR = VAR + pow((AB.data[i][j]-EAB), static_cast <double> (q) ) *m1.data[s][i]*m2.data[s][j];
 88 |           COVAR = COVAR + pow((AB.data[i][j]-EAB)*(A.data[i][j]-EA), static_cast <double> (q) ) *m1.data[s][i]*m2.data[s][j];
 89 |         } // end for in j
 90 |       } // end for in i
 91 |       FACT = FACT + pow( (-1.0), static_cast <double> (q)) *( (EA*VAR + COVAR) / pow(EAB, static_cast <double> (q+1)));
 92 |       if ((verbose==4) & (s==0)) fprintf(stderr, "\n q %d v %f c %f f %f",q,VAR,COVAR,FACT);
 93 |     } // end for in nsums
 94 |     // print results
 95 |     fprintf(fname, "%f\t%f\t%f\t%f\t%f\n", EA, EAB, FACT, (EA/EAB)+FACT, pvar);
 96 |     cleanup(A);
 97 |     cleanup(AB);
 98 |   } // end for s in nsites
 99 | } // end
100 | 
101 | 
102 | // compute a and ab estimate for all possible combinations of sample size, then weight by their prob12 computed from post1, pos12 and prior12 (normalize it)
103 | void computeVarRey12(matrix<double> &m1, matrix<double> &m2, int verbose, FILE *fname, int nsums, matrix<double> &p12) {
104 | 
105 |   int n1 = 0, n2 = 0; // sample sizes
106 |   int nsites = 0; // nsites
107 | 
108 |   // estimates nsites and pop sizes from matrices
109 |   n1 = (m1.y-1)/2; // nind1
110 |   n2 = (m2.y-1)/2; // nind2
111 |   nsites = m1.x; // nsites from file
112 | 
113 |   double VAR = 0.0, COVAR = 0.0, FACT = 0.0, pvar = 0.0;
114 | 
115 |   for (int s=0; s<nsites; s++) {
116 | 
117 |     // m1 and m2 are post probs, p12 is the 2d sfs
118 |     matrix<double> m12;
119 |     m12.x=m1.y;
120 |     m12.y=m2.y;
121 |     double **ddata = new double*[m12.x];
122 |       for(int i=0;i<m12.x;i++){
123 |         double *dtmp = new double[m12.y];
124 |         for(int k=0;k<m12.y;k++) {
125 |           dtmp[k]=0.0;
126 |         }
127 |         ddata[i]= dtmp;
128 |       }
129 |     m12.data=ddata;
130 | 
131 |     // multiply
132 |     for (int j=0; j<m12.x; j++) {
133 |       for (int i=0;i<m12.y; i++) {
134 |         m12.data[j][i] = m1.data[s][j]*m2.data[s][i]*p12.data[j][i];
135 |       }
136 |     }
137 | 
138 |     // get the sum
139 |     double somma=0.0;
140 |       for (int j=0; j<m12.x; j++) {
141 |         for (int i=0;i<m12.y; i++) {
142 |           somma=somma+m12.data[j][i];
143 |       }
144 |     }
145 | 
146 |     // divide
147 |     for (int j=0; j<m12.x; j++) {
148 |       for (int i=0;i<m12.y; i++) {
149 |         m12.data[j][i] = m12.data[j][i]/somma;
150 |       }
151 |     }
152 | 
153 |     //fprintf(stderr, "final2d %f %f %f %f\n", m12.data[0][0], m12.data[0][1], m12.data[1][0], m12.data[1][1]);  
154 | 
155 |     // for each possible value of freq 1 and freq 2 compute the FST, so compute A, AB, VAR, COVAR (see Price paper for its meaning)
156 |     matrix<double> A;
157 |     matrix<double> AB;
158 | 
159 |     A.x=AB.x=(n1*2)+1;
160 |     A.y=AB.y=(n2*2)+1;
161 | 
162 |     // FIRST CYCLE: get expected A and AB and retain matrices of A and AB
163 |     double **dataA = new double*[(n1*2)+1];
164 |     double **dataAB = new double*[(n1*2)+1];
165 | 
166 |     // get also the probability of site being variable
167 |     pvar = 1 - m12.data[0][0] - m12.data[2*n1][2*n2];
168 | 
169 |     if (verbose==2) fprintf(stderr, "\t first cycle");
170 | 
171 |     double EA = 0.0, EAB = 0.0;
172 | 
173 |     for (int i=0; i<(2*n1+1); i++) {
174 | 
175 |       if (verbose==2) fprintf(stderr, "\ti%d",i);
176 | 
177 |       double *bufA = new double[(n2*2)+1];
178 |       double *bufAB = new double[(n2*2)+1];
179 | 
180 |       for (int j=0; j<(2*n2+1); j++) {
181 | 
182 |         array<double> temp;
183 |         temp = calcAB(i, j, n1, n2, 0);
184 |         bufA[j]=temp.data[0];
185 |         bufAB[j]=temp.data[1];
186 | 
187 |         EA = EA + temp.data[0]*m12.data[i][j];
188 |         EAB = EAB + temp.data[1]*m12.data[i][j];
189 | 
190 |         delete [] temp.data;
191 | 
192 |       } // end for in j
193 | 
194 |       dataA[i]=bufA;
195 |       dataAB[i]=bufAB;
196 | 
197 |     } // end for in i
198 | 
199 |     A.data=dataA;
200 |     AB.data=dataAB;
201 | 
202 |     if (EA<0.0) EA=0.0; // protect against -0.000 cases
203 |     // SECOND CYCLE: get VAR and COVAR, and then the correcting FACTor, according to number of sums to retain
204 |     VAR = 0.0, COVAR = 0.0, FACT = 0.0;
205 | 
206 |     if ((verbose==4) & (s==0)) fprintf(stderr, "\t second cycle %d", nsums);
207 | 
208 |     for (int q=1; q<=nsums; q++) {
209 | 
210 |       VAR = 0.0; COVAR = 0.0;
211 |       for (int i=0; i<(2*n1+1); i++) {
212 |         for (int j=0; j<(2*n2+1); j++) {
213 | 
214 |           VAR = VAR + pow((AB.data[i][j]-EAB), static_cast <double> (q) )*m12.data[i][j];
215 | 
216 |           COVAR = COVAR + pow((AB.data[i][j]-EAB)*(A.data[i][j]-EA), static_cast <double> (q) ) *m12.data[i][j];
217 | 
218 |         } // end for in j
219 |       } // end for in i
220 | 
221 |       FACT = FACT + pow( (-1.0), static_cast <double> (q)) *( (EA*VAR + COVAR) / pow(EAB, static_cast <double> (q+1)));
222 | 
223 |       if ((verbose==4) & (s==0)) fprintf(stderr, "\n q %d v %f c %f f %f",q,VAR,COVAR,FACT);
224 | 
225 |     } // end for in nsums
226 | 
227 |     // print results
228 |     fprintf(fname, "%f\t%f\t%f\t%f\t%f\n", EA, EAB, FACT, (EA/EAB)+FACT, pvar);
229 | 
230 |     cleanup(A);
231 |     cleanup(AB);
232 |     cleanup(m12);
233 | 
234 |   } // end for s in nsites
235 | 
236 | 
237 | 
238 | } // end
239 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
  1 | 
  2 | # ngsPopGen
  3 | 
  4 | Several tools to perform population genetic analyses from NGS data:
  5 |  * ` ngsFst`   - Quantificate population genetic differentiation
  6 |  * ` ngsCovar` - Population structure via PCA (principal components analysis)
  7 |  * ` ngs2dSFS` - Estimate 2D-SFS from posterior probabilities of sample allele frequencies
  8 |  * ` ngsStat`  - Estimates number of segregating sites, expected average heterozygosity, and number of fixed differences and Dxy (if 2 populations provided).
  9 | 
 10 | IMPORTANT NOTE i): 
 11 | 
 12 | In all analises involving 2 populations, input data must refer to the exact same sites. If they differ (e.g. because of different filtering), you must first get the overlapping subset of sites for both populations.
 13 | To achieve this, you can follow instructions given in the tutorial ([here](https://github.com/mfumagalli/ngsTools/blob/master/TUTORIAL.md)).
 14 | 
 15 | IMPORTANT NOTE ii): 
 16 | 
 17 | The use of folded data (spectrum or sample allele frequencies probabilities) is no longer supported.
 18 | In case you do not have a reliable ancestral information, please use your reference sequence to polarise your data and follow all the steps as documented here. However, do not attempt to make any inference based on the resulting unfolded reference/non-reference based - site frequency spectrum.
 19 | 
 20 | IMPORTANT NOTE iii):
 21 | 
 22 | It may be practical to perform a non-stringent SNP calling before running the following analyses, in order to reduce the computational time and data dimensions.
 23 | Moreover, this will reduce noise due to monomorphic sites, especially when the species' polymorphic rate is very low.
 24 | 
 25 | 
 26 | ### Installation
 27 | 
 28 | To install the entire package just download the source code:
 29 | 
 30 |     % git clone https://github.com/mfumagalli/ngsPopGen.git
 31 | 
 32 | and run:
 33 | 
 34 |     % cd ngsPopGen
 35 |     % make
 36 | 
 37 | To run the tests (only if installed through [ngsTools](https://github.com/mfumagalli/ngsTools)):
 38 | 
 39 |     % make test
 40 | 
 41 | Executables are built into the main directory. If you wish to clean all binaries and intermediate files:
 42 | 
 43 |     % make clean
 44 | 
 45 | However, we recommend to download and install the whole [ngsTools](https://github.com/mfumagalli/ngsTools) package.
 46 | 
 47 | 
 48 | ---
 49 | 
 50 | ## ngsFST
 51 | 
 52 | Program to estimate FST from NGS data. It computes expected genetic variance components and estimate per-site FST from those using methods-of-moments estimator. See Fumagalli et al. Genetics 2013 for more details.
 53 | In input it receives sample allele frequencies likelihoods for each population and a 2D-SFS as a prior.
 54 | 
 55 | The output is a tab-separated text file. Each row represents a site. Columns are ordered as: A, AB, f, FST, Pvar; where A is the expectation of genetic variance between populations, AB is the expectation of the total genetic variance, f is the correcting factor for the ratio of expectations, FST is the per-site FST value, Pvar is the probability for the site of being variable.
 56 | 
 57 | ### Usage
 58 | #### Examples:
 59 | 
 60 |  * using a 2D-SFS as a prior, estimated using ngs2dSFS:
 61 | 
 62 | #
 63 | 
 64 |     % ./ngsFST -postfiles pop1.saf pop2.saf -priorfile spectrum2D.txt -nind 20 20 -nsites 100000 -outfile pops.fst -verbose 0
 65 | 
 66 | #### Parameters:
 67 | * `-postfiles FILE_1 FILE_2`: files with sample allele frequencies likelihoods for each population
 68 | * `-priorfile FILE`: 2D-SFS to be used as a prior; you can use ngs2dSfs with parameter -relative set to 1
 69 | * `-nind INT`: number of individuals for each population
 70 | * `-nsites INT`: total number of sites; in case of a site subset this is the upper limit
 71 | * `-firstbase INT`: in case of a site subset, this is the lower limit
 72 | * `-outfile FILE`: name of the output file
 73 | * `-block_size INT`: number of sites in each chunk (for memory reasons, increase it if you can use more RAM)
 74 | * `-verbose INT`: level of verbosity
 75 | 
 76 | ---
 77 | 
 78 | ## ngsCovar
 79 | 
 80 | Program to compute the expected correlation matrix between individuals from genotype posterior probabilities. It receives as input genotype posterior probabilities. It can receive in input also posterior probabilities of sample allele frequencies for computing the probability of each site to be variant.
 81 | 
 82 | ### Usage
 83 | 
 84 | #### Examples:
 85 | 
 86 | * not calling genotypes but with SNP calling (preferred way under most circumstances):
 87 | 
 88 | #
 89 | 
 90 |     % ./ngsCovar -probfile pop.geno -outfile pop.covar -nind 40 -nsites 100000 -block_size 20000 -call 0 -minmaf 0.05
 91 | 
 92 | * not calling genotypes and no SNP calling (weighting by each site's probability of being variable; recommended if depth is extremely low):
 93 | 
 94 | #
 95 | 
 96 |     % gunzip -f pop.saf.gz
 97 |     % ./ngsCovar -probfile pop.geno -outfile pop.covar -nind 40 -nsites 100000 -block_size 20000 -call 0 -norm 0 -sfsfile pop.saf
 98 |     
 99 | * calling genotypes (this is kept for compatibility but should not be used unless you have high-depth data, > 20X):
100 | 
101 | #
102 | 
103 |     % ./ngsCovar -probfile pop.geno -outfile pop.covar -nind 40 -nsites 100000 -block_size 20000 -call 1
104 | 
105 | 
106 | #### Parameters:
107 | * `-probfile FILE`: file with genotype posterior probabilities
108 | * `-sfsfile FILE`: file with per site allele frequency posterior probabilities
109 | * `-nind INT`: number of individuals
110 | * `-nsites INT`: total number of sites; in case of a site subset this is the upper limit
111 | * `-offset INT`: in case of a site subset, this is the lower limit
112 | * `-genoquality FILE`: text file with 'nsites' lines stating whether to use (1) or ignore (0) the site
113 | * `-norm INT`: normalization procedure; either "0" for no normalization (recommended if no SNP calling was performed), "1" for normalization by `p(1-p)` (Patterson et al, 2006) or "2" for normalization by `2p(1-p)`
114 | * `-minmaf FLOAT`: ignore sites below this threshold of minor allele frequency
115 | * `-call`: call genotypes based on the maximum posterior probability
116 | * `-outfile FILE`: name of output file
117 | * `-block_size INT`: number of sites in each chunk (for memory reasons)
118 | * `-verbose INT`: level of verbosity
119 | 
120 | ---
121 | 
122 | ## ngs2dSFS
123 | 
124 | Program to estimate 2D-SFS from posterior probabilities of sample allele frequencies. Output file reports the occurrence of sites at distinct joint allele frequencies. This spectrum is a (2N1+1)x(2N2+2) matrix with N1 and N2 number of individuals at the two populations. Please note that cells are zero-based ordered. As an example, value reported in the cell [4,3] represents the frequency of sites with allele frequency 3 and 2 at population 1 and 2 respectively.
125 | 
126 | #### Example:
127 | 
128 |     % ./ngs2dSFS -postfiles pop1.saf pop2.saf -outfile spectrum.txt -relative 1 -nind 20 20 -nsites 100000
129 | 
130 | #### Parameters:
131 | * `-postfiles FILE`: file with sample allele frequency posterior probabilities (or likelihoods) for each population
132 | * `-nind INT`: number of individuals
133 | * `-nsites INT`: total number of sites; in case of a site subset this is the upper limit
134 | * `-offset INT`: in case of a site subset, this is the lower limit
135 | * `-outfile FILE`: name of output file
136 | * `-maxlike INT`: how to compute the MLE; either, "1" (preferred) to sum across sites' joint allele frequency, or "0" to sum of the products of likelihoods
137 | * `-relative INT`: whether input are absolute counts of sites with a specific joint allele frequency (0) or relative frequencies (1)
138 | * `-block_size INT`: number of sites for each chunk (for memory efficiency only)
139 | 
140 | ANGSD can compute a ML estimate of the 2D-SFS which should be preferred when many sites are available. However, ANGSD output file should be transformed (from log to un-log and from space-separated to tab-separated) before being used in ngsFST.
141 | 
142 | 
143 | ---
144 | 
145 | ## ngsStat
146 | 
147 | Program to compute estimates of the number of segregating sites, the expected average heterozygosity, and the number of fixed differences (if 2 populations data is provided). It receives as input sample allele frequency posterior probabilities (from ANGSD) from 1 or 2 populations. Output is a text file with columns: start, end, segregating sites (pop 1), heterozygosity (pop 1), segregating sites (pop 2), heterozygosity (pop 2), fixed differences, dxy.
148 | 
149 | #### Example:
150 | 
151 | * 2 populations, sliding windows of 100 sites (latter recommended only if no missing data is present, however in most cases you will have some missing sites so this command should not be used):
152 | 
153 | #
154 | 
155 |     ./ngsStat -npop 2 -postfiles pop1.saf pop2.saf -nsites 1000 -iswin 1 -nind 10 10 -outfile pops.stat -verbose 0 -block_size 100
156 |     
157 | * 1 populations, sliding windows of 100 sites (latter recommended only if no missing data is present, so again in many cases this should not be used):
158 | 
159 | # 
160 | 
161 |     ./ngsStat -npop 1 -postfiles pop1.saf -nsites 1000 -iswin 1 -nind 10 -outfile pops.stat -block_size 100
162 |     
163 | * 1 population, values estimated at each site (recommended in case of missing data, and then the computation of values in sliding windows will be performed using the R script provided):
164 | 
165 | #
166 | 
167 |     ./ngsStat -npop 1 -postfiles pop1.saf -nsites 1000 -iswin 0 -nind 10 -outfile pops.stat
168 | 
169 | #### Parameters:
170 | * `-npop INT`: number of populations (should be the first one to be specified)
171 | * `-postfiles`: file with sample allele frequency posterior probabilities for each population
172 | * `-nind INT`: number of individuals
173 | * `-nsites INT`: total number of sites; in case of a site subset this is the upper limit
174 | * `-firstbase INT`: in case of a site subset, this is the lower limit
175 | * `-iswin INT`: if set to 1, chuncks are considered non-overlapping sliding-windows
176 | * `-outfile FILE`: name of output file
177 | * `-block_size INT`: number of sites in each chunk (for memory reasons)
178 | * `-verbose INT`: level of verbosity
179 | 
180 | 
181 | Further examples can be found in the [Tutorial](https://github.com/mfumagalli/ngsTools/blob/master/TUTORIAL.md).
182 | 
183 | 


--------------------------------------------------------------------------------
/ngsCovar.cpp:
--------------------------------------------------------------------------------
  1 | #include <cstdio>
  2 | #include <cstdlib>
  3 | #include <sys/stat.h>
  4 | #include <cstring>
  5 | #include <vector>
  6 | #include <math.h>
  7 | #include "ngsCovar.hpp"
  8 | 
  9 | // to compile: g++ -Wall -O0 -g ngsCovar.cpp -o ngsCovar
 10 | 
 11 | // implement offset
 12 | 
 13 | int main (int argc, char *argv[]) {
 14 |   
 15 |   // CALL HELP FUNCTION
 16 |   if (argc==1) {
 17 |     info();
 18 |     return 0; // terminate
 19 |   }
 20 |  
 21 |   // DECLARE
 22 |  
 23 |   // possible inputs
 24 |   char *estfile=NULL; // estimated genotypes with probs (from angsd -doGeno 64)
 25 |   char *sfsfile=NULL; // sfs probs (-realSFS 1 + optimSFS = sfstools)
 26 |   char *genoquality=NULL; // list of boolean, whether to keep or not each site
 27 |   
 28 |   FILE *outest;
 29 |   char *outfiles=NULL;
 30 |   char *foutest=NULL;
 31 |   
 32 |   int argPos = 1, increment = 0, nind = 0, nsites = 0, debug = 0, block_size = 20000, call=0, offset=1, maxgeno=0, norm=0;
 33 |   double esites = 0.0, minmaf = 0.0;
 34 |  
 35 |   /// READ AND ASSIGN INPUT PARAMETERS
 36 |   
 37 |   while (argPos<argc) {
 38 |     increment = 0; // leave this in case of future implementation of more parameters per argument
 39 |     if(strcmp(argv[argPos],"-probfile")==0) 
 40 |       estfile = argv[argPos+1];
 41 |     else if(strcmp(argv[argPos],"-sfsfile")==0) 
 42 |       sfsfile = argv[argPos+1];
 43 |     else if(strcmp(argv[argPos],"-nind")==0) 
 44 |       nind = atoi(argv[argPos+1]);
 45 |     else if(strcmp(argv[argPos],"-nsites")==0) 
 46 |       nsites = atoi(argv[argPos+1]);
 47 |     else if(strcmp(argv[argPos],"-outfile")==0) 
 48 |       outfiles = argv[argPos+1];
 49 |     else if(strcmp(argv[argPos],"-minmaf")==0) 
 50 |       minmaf = atof(argv[argPos+1]);
 51 |     else if(strcmp(argv[argPos],"-block_size")==0)
 52 |       block_size = atoi(argv[argPos+1]);
 53 |     else if(strcmp(argv[argPos],"-offset")==0)
 54 |       offset = atoi(argv[argPos+1]);
 55 |     else if(strcmp(argv[argPos],"-call")==0)
 56 |       call = atoi(argv[argPos+1]);
 57 |     else if(strcmp(argv[argPos],"-norm")==0) // 0 nothing, 1 p(1-p), 2 2p(1-p)
 58 |       norm = atoi(argv[argPos+1]);
 59 |     else if(strcmp(argv[argPos],"-genoquality")==0)
 60 |       genoquality = argv[argPos+1];
 61 |     else if(strcmp(argv[argPos],"-verbose")==0) 
 62 |       debug = atoi(argv[argPos+1]);
 63 |     else { // input is not a valid one 
 64 |       printf("\tUnknown arguments: %s\n",argv[argPos]);
 65 |       info();
 66 |       return 0; // terminate
 67 |     }
 68 |     argPos = argPos + 2 + increment;
 69 |   } // end while all inputs
 70 | 
 71 | 
 72 |   // print input arguments
 73 |   if (debug) fprintf(stderr,"\t->Using args: -nind %d -nsites %d -probfile %s -sfsfile %s -outfile %s -verbose %d -minmaf %f -block_size %d -call %d -offset %d\n", nind, nsites, estfile, sfsfile, foutest, debug, minmaf, block_size, call, offset); 
 74 |   
 75 |   // check if there is the input file
 76 |   if (estfile == NULL) {
 77 |     fprintf(stderr,"\nMust supply -probfile.\n");
 78 |     info();
 79 |     return 0;
 80 |   }
 81 | 
 82 |   // check if there is the sfs file
 83 |   if ((sfsfile != NULL) & (minmaf>0)) {
 84 |     fprintf(stderr,"\n-sfsfile and -minmaf are in conflict! If use use -sfsfile to weight each file there is no need (theoretically) to filter out sites with low maf. In this case -minmaf won't be applied and the program terminates here.\n");
 85 |     info();
 86 |     return 0;
 87 |   }
 88 |   
 89 |   // check if there is the output file
 90 |   if (outfiles == NULL) {
 91 |     fprintf(stderr,"\nMust supply -outfile.\n");
 92 |     info();
 93 |     return 0;
 94 |   }
 95 | 
 96 |   // if block_size longer than nsites
 97 |   if (block_size>(nsites-offset+1)) block_size=(nsites-offset+1);
 98 |   if (block_size==0) block_size=nsites-offset+1;
 99 | 
100 |   // When reading from stdin, reading in blocks is not supported
101 |   if ( (strcmp(estfile,"-")==0 || (sfsfile!=NULL && strcmp(sfsfile,"-")==0)) && block_size != nsites ) {
102 |     fprintf(stderr,"\nInput in blocks is not supported when using piped input (either -postfile or -sfsfile).\n");
103 |     exit(-1);
104 |   }
105 | 
106 |   // prepare output files
107 |   foutest = append(outfiles, "");
108 |   
109 |  
110 |   // BLOCKS
111 |   /// GET POSITIONS OF BLOCKS
112 |   array<int> start; array<int> end;
113 |   start=getStart(nsites, offset, block_size);
114 |   end=getEnd(nsites, offset, block_size);
115 |   int maxlen=end.data[0]-start.data[0]+1; // len for each win, it will never be greater than this
116 |   double temp_sum=0.0; // check at each iteration not NA, for debug 
117 |   int nwin= (nsites-offset+1)/block_size;
118 |   if ( ( (nsites-offset+1) % block_size)!=0) nwin++;
119 | 
120 |   // prepare out
121 |   if (debug) fprintf(stderr,"\t->Dumping file: %s\n", foutest);
122 |   outest = getFILE(foutest, "w");
123 | 
124 |   // initialize covariance matrix  
125 |   matrix<double> covar;
126 |   double **cdata = new double*[nind];
127 |   for(int i=0;i<nind;i++){
128 |     double *ctmp = new double[nind];
129 |     cdata[i]= ctmp;
130 |   }
131 |   covar.x = nind;
132 |   covar.y = nind;
133 |   covar.data = cdata;
134 |   for (int i=0;i<nind;i++) {
135 |     for (int j=0;j<nind;j++) {
136 |       covar.data[i][j]=0.0;
137 |     }
138 |   }
139 | 
140 |   // initialize pvar
141 |   array<double> pvar;
142 |   double *temp2 = new double [maxlen]; // init to the size of the largest window
143 |   for (int i=0; i<maxlen; i++)
144 |    temp2[i]=0.0;
145 |   pvar.x=maxlen;
146 |   pvar.data=temp2;
147 | 
148 |   // SITES to be retained
149 |   array<int> good;
150 |   if (genoquality!=NULL) {
151 |     good = readGenoQuality(genoquality, nsites);
152 |   } else {
153 |     good.x=nsites;
154 |     int *good_tmp = new int [nsites];
155 |     for (int i=0; i<nsites; i++) good_tmp[i]=1;
156 |     good.data=good_tmp;
157 |   }
158 | 
159 |   // ITERATING for each block
160 |   for (int n=0; n<nwin; n++) {
161 | 
162 |     matrix<double> sfs;
163 |     matrix<double> esti;
164 |     array<double> pp;
165 | 
166 |     if (debug) fprintf(stderr, "\nBlock %d out of %d from %d to %d\n", n, (nwin-1), start.data[n], end.data[n]);
167 | 
168 |     // compute esti
169 |     if (debug==1) fprintf(stderr, "\nGetting esti...");
170 |     esti = readEstiSub(estfile, nind, start.data[n], end.data[n]);
171 |     if (debug==2) writematrix(esti, stderr);
172 |     if (debug==1) fprintf(stderr, ": %d %d , %f %f", esti.x, esti.y, esti.data[0][0], esti.data[1][1]);  
173 | 
174 |     // IF CALL GENOTYPES, set max prob to 1
175 |     if (call) {
176 |  
177 |       if (debug==1) fprintf(stderr, "\nCalling genotypes...");
178 |       for (int i=0; i<esti.x; i++) { // for each site/row
179 | 
180 |         for (int h=0; h<esti.y; h=h+3) { // for each individual
181 | 
182 |           //fprintf(stderr, "\nindiv: %d",h);
183 | 
184 |           maxgeno=maxposarr(esti, i, h, h+3);
185 | 
186 |           //fprintf(stderr, "\nindiv %d and maxgeno %d", h, maxgeno);
187 | 
188 |           //fprintf(stderr, "\nGen likes:%f %f %f", esti.data[i][h],esti.data[i][h+1],esti.data[i][h+2]);
189 | 
190 |           for (int j=h; j<(h+3); j++) esti.data[i][j]=0.0;
191 |           esti.data[i][maxgeno]=1.0;
192 | 
193 |           //fprintf(stderr, "\nNew likes:%f %f %f", esti.data[i][h],esti.data[i][h+1],esti.data[i][h+2]);
194 | 
195 |         }
196 |       }
197 |     }
198 | 
199 |     /// COMPUTE ALLELE FREQUENCIES
200 |     if (debug==1) fprintf(stderr, "\nGetting mu...");
201 |     pp = getAlleFreq(esti);
202 |     if (debug==3) writearray(pp, stderr);
203 |     // this is NOT strictly the alle freq, is mu in Patterson notation, thus it's the average number of derived alleles per individual; the allele freq p is simply mu/2
204 |     if (debug==2) {
205 |       for (int i=0; i<pp.x; i++)
206 |        if (pp.data[i]<0) fprintf(stderr, "\n %d %f", i, pp.data[i]);
207 |     }
208 |     if (debug==1) fprintf(stderr, ": %d, %f %f ", pp.x, pp.data[0], pp.data[4]);
209 |  
210 |     /// COMPUTE COVARIANCE, here simply update
211 |     if (debug==1) fprintf(stderr, "\nUpdating covar...");
212 |     if (sfsfile!=NULL) {
213 |       // read sfs
214 |       if (debug) fprintf(stderr, "...weighting...");
215 |       sfs = readFileSub(sfsfile, nind, start.data[n], end.data[n]);
216 |       normSFS(sfs, true);
217 |       if (debug==1) fprintf(stderr, "\nGot  sfs: %d %d, e.g. %f %f", sfs.x, sfs.y, sfs.data[0][0], sfs.data[1][1]);
218 |       if (debug==1) fprintf(stderr, "\nGetting pvar...");
219 |       getPvar(sfs, pvar);
220 |       if (debug==1) fprintf(stderr, ": %d , %f %f", pvar.x, pvar.data[0], pvar.data[1]);
221 |       cleanup(sfs);
222 |       if (debug==1) fprintf(stderr, "\nUpdating covar...");
223 |       calcCovarUpProb(esti, pp, covar, pvar, good, start.data[n], norm);
224 |       if (debug==1) fprintf(stderr, "\nUpdating esite...");
225 |       // divide by expected nr of segr sites -1 in case of pvar
226 |       for (int i=0;i<pvar.x;i++) esites = esites + pvar.data[i];
227 |       if (debug==1) fprintf(stderr, ": %f", esites);
228 |     } else {
229 |       if (debug==1) fprintf(stderr, "\n I am using this minmaf %f ", minmaf);
230 |       if (debug) fprintf(stderr, "...no weighting..."); 
231 |       double tmp_eff_nsites=calcCovarUp(esti, pp, covar, minmaf, good, start.data[n], norm);
232 |       esites=esites+tmp_eff_nsites;
233 |     }
234 |        
235 |     cleanup(esti);
236 | 
237 |     delete [] pp.data;
238 |  
239 |     if (debug==1) {
240 |       temp_sum=0.0;
241 |       for (int i=0;i<nind;i++) {
242 |        for (int j=0;j<nind;j++) {
243 |         //fprintf(stderr, "\t %d %d %f", i, j, covar.data[i][j]);
244 |         temp_sum=temp_sum+covar.data[i][j];
245 |        }
246 |       }
247 |       if (debug) fprintf(stderr, "\t Sum:%f", temp_sum);
248 | 
249 |       //if (temp_sum==(-nan)) {
250 |       //  for (int i=0; i<pvar.x; i++) fprintf(stderr, "\t %d %f", i, pvar.data[i]);
251 |         //exit(0);
252 |       //}
253 | 
254 |     }
255 | 
256 |   } // end for n in nwin block
257 | 
258 |   if (debug) fprintf(stderr, "\n(Exp/eff) nr sites: %f\n", esites);
259 | 
260 |   delete [] pvar.data;
261 | 
262 |   delete [] start.data;
263 |   delete [] end.data;
264 | 
265 |   delete [] good.data;
266 | 
267 |   // divide
268 |   for (int i=0;i<nind;i++) {
269 |     for (int j=0;j<nind;j++) {
270 |         covar.data[i][j]=covar.data[i][j]/(esites);
271 |     }
272 |   }
273 | 
274 |   writematrix(covar, outest);  
275 |   
276 |   // free
277 |   cleanup(covar);
278 |   free(foutest);
279 |   fclose(outest);  
280 | 
281 |   return 0;
282 |   
283 | } // end main
284 | 
285 | 


--------------------------------------------------------------------------------
/shared.hpp:
--------------------------------------------------------------------------------
  1 | /// TEMPLATES
  2 | 
  3 | #include <string> //for str operations
  4 | #include <unistd.h>
  5 | 
  6 | // a general matrix style structure
  7 | template <typename T>
  8 | struct matrix{
  9 |   int x;
 10 |   int y;
 11 |   T** data;
 12 | };
 13 | 
 14 | // a general array style structure
 15 | template <typename T>
 16 | struct array{
 17 |   int x;
 18 |   T* data;
 19 | };
 20 | 
 21 | template <typename T>
 22 | T *collapse(std::vector<T> &v){
 23 |   T *tmp = new T[v.size()];
 24 |   for(int i=0;i<v.size();i++)
 25 |     tmp[i] = v[i];
 26 |   return tmp;
 27 | }
 28 | 
 29 | //function to cleanup our generic matrix structure
 30 | template <typename T>
 31 | void cleanup(matrix<T> &m){//using a reference to avoid copying the data
 32 |   for(int i=0;i<m.x;i++)
 33 |     delete [] m.data[i];
 34 |   delete [] m.data;
 35 | }
 36 | 
 37 | /// FUNCTIONS
 38 | 
 39 | array<int> getStart(int nsites, int firstbase, int block_size) {
 40 |   // note that firstbase and nsites are 1-based
 41 |   int len = nsites-firstbase+1;
 42 |   int nwin = len/block_size;
 43 |   if ( (len % block_size)!=0) nwin=nwin+1;
 44 | 
 45 |   array<int> start;
 46 |   start.x=nwin;
 47 |   
 48 |   int *tStart= new int [nwin];
 49 |   for (int i=0; i<nwin; i++) {
 50 |     tStart[i]=(i)*block_size;
 51 |   }
 52 | 
 53 |   // if you dont start from beginning
 54 |   if (firstbase>1) {
 55 |     for (int i=0; i<nwin; i++) {
 56 |       tStart[i]=tStart[i]+firstbase-1; // -1 because firstbase is 1-based
 57 |     }
 58 |   }
 59 |   start.data=tStart;
 60 |   return start;
 61 | }
 62 | 
 63 | array<int> getEnd(int nsites, int firstbase, int block_size) {
 64 |   // note that firstbase and nsites are 1-based
 65 |   int len = nsites-firstbase+1;
 66 | 
 67 |   int nwin = len/block_size;
 68 |   if ( (len % block_size)!=0) nwin=nwin+1;
 69 |   
 70 |   array<int> end;
 71 |   end.x=nwin;
 72 | 
 73 |   int *tEnd= new int [nwin];
 74 |   for (int i=0; i<nwin; i++) {
 75 |     tEnd[i]=(i)*block_size+block_size-1;
 76 |   }
 77 |   tEnd[nwin-1]=nsites-1; // nsites is 1 based
 78 |  
 79 |   // if you dont start from beginning
 80 |   if (firstbase>0) {
 81 |     for (int i=0; i<nwin; i++) {
 82 |       tEnd[i]=tEnd[i]+firstbase-1;
 83 |     }
 84 |   }
 85 | 
 86 |   end.data=tEnd;
 87 |   return end;
 88 | }
 89 | 
 90 | // get the filesize of a file
 91 | size_t fsize(const char* fname){
 92 |   struct stat st ;
 93 |   stat(fname,&st);
 94 |   return st.st_size;
 95 | }
 96 | 
 97 | // find out if a file exists
 98 | int fexists(const char* str) {
 99 |   struct stat buffer ;
100 |   return (stat(str, &buffer )==0 );
101 | }
102 | 
103 | // to append names
104 | char *append(const char* a,const char *b){
105 |   char *c =(char *) malloc((strlen(a)+strlen(b)+1)*sizeof(char));
106 |   strcpy(c,a);
107 |   strncat(c,b,strlen(b));
108 |   return c;
109 | }
110 | 
111 | // a nice wrapper for getting files
112 | FILE *getFILE(const char* fname,const char* mode) {
113 |   FILE *fp;
114 |   int writeFile = 0;
115 |   for(size_t i=0;i<strlen(mode);i++)
116 |     if(mode[i]=='w')
117 |       writeFile = 1;
118 | 
119 |   if(writeFile && fexists(fname)){
120 |     fprintf(stderr,"\t-> File exists: %s exiting...\n",fname);
121 |     exit(0);
122 |   }
123 |   
124 |   if(strcmp(fname, "-") == 0){
125 |     if(writeFile)
126 |       fp = stdout;
127 |     else
128 |       fp = stdin;
129 |   } else {
130 |     if(NULL==(fp=fopen(fname,mode))){
131 |       fprintf(stderr,"\t->Error opening FILE handle for file:%s exiting\n",fname);
132 |       exit(0);
133 |     }
134 |   }
135 | 
136 |   if(isatty(fileno(fp))) {
137 |     fprintf(stderr, "Your stdin/stdout is not a pipe, this might not be what you want!\n");
138 |     exit(0);
139 |   }
140 |   
141 |   return fp;
142 | }
143 | 
144 | // read a file of prior into an array
145 | array<double> readArray(const char *fname, int nInd) {
146 |   FILE *fp = getFILE(fname,"r");
147 |   size_t filesize =fsize(fname);
148 |   if(filesize==0){
149 |     fprintf(stderr,"file:%s looks empty\n",fname);
150 |     exit(0);
151 |   }
152 |   int len = 2*nInd+1;
153 |   char *buf = new char[filesize];
154 |   double *tmp = new double[len];
155 |   fread(buf,sizeof(char),filesize,fp);
156 |   tmp[0] = atof(strtok(buf,"\t \n"));
157 |   for(int i=1;i<(len);i++)
158 |       tmp[i] = atof(strtok(NULL,"\t \n"));
159 |   fclose(fp);
160 |   delete [] buf;
161 |   array<double> ret;
162 |   ret.x = len;
163 |   ret.data = tmp;
164 |   return ret;
165 | }
166 | 
167 | // read 2d sfs
168 | matrix<double> readPrior12(const char *fname, int nrow, int ncol) {
169 |   FILE *fp = getFILE(fname,"r");
170 |   size_t filesize =fsize(fname);
171 |   if(filesize==0){
172 |     fprintf(stderr,"file:%s looks empty\n",fname);
173 |     exit(0);
174 |   }
175 |   double *tmp = new double[nrow*ncol];
176 |   char *buf = new char[filesize];
177 |   fread(buf,sizeof(char),filesize,fp);
178 |   tmp[0] = atof(strtok(buf,"\t \n"));
179 |   for(int i=1;i<(nrow*ncol);i++)
180 |     tmp[i] = atof(strtok(NULL,"\t \n"));
181 |   fclose(fp);
182 |   delete [] buf;
183 |   array<double> allvalues;
184 |   allvalues.x = nrow*ncol;
185 |   allvalues.data = tmp;
186 |   int index=0;
187 |   double **data = new double*[nrow];
188 |   for(int i=0;i<nrow;i++){
189 |     double *tmp2 = new double[ncol];
190 |     for(int k=0;k<ncol;k++) {
191 |       tmp2[k]=allvalues.data[index];
192 |       index=index+1;
193 |     }
194 |     data[i]= tmp2;
195 |   }
196 |   matrix<double> ret;
197 |   ret.x=nrow;
198 |   ret.y=ncol;
199 |   ret.data=data;
200 |   delete [] allvalues.data;
201 |   return ret;
202 | }
203 | 
204 | 
205 | // read a file of posterior probabilities into a matrix but only for a specific subsets of positions (0-based notation)
206 | matrix<double> readFileSub(char *fname, int nInd, int start, int end) {
207 |   FILE *fp = getFILE(fname,"r");
208 |   size_t filesize =fsize(fname);
209 |   int n_categ = 2*nInd+1;
210 | 
211 |   if( strcmp(fname,"-")!=0 ) {
212 |     if( filesize % (n_categ*sizeof(float)) != 2*sizeof(float) ) {
213 |       fprintf(stderr,"\n\t-> Possible error reading SFS, binary file might be broken...\n");
214 |       exit(-1);
215 |     }
216 |   }
217 | 
218 |   int nsites = end-start+1;
219 |   double **data = new double*[nsites];
220 |   float float_tmp = 0;
221 | 
222 |   // Locate data to read
223 |   fseek(fp, (2+n_categ*start)*sizeof(float), SEEK_SET);
224 | 
225 |   // Read data
226 |   for(int i=0; i<nsites; i++) {
227 |     double *tmp = new double[n_categ];
228 |     for(int c=0; c<n_categ; c++){
229 |       fread(&float_tmp, sizeof(float), 1, fp);
230 |       tmp[c] = (double) float_tmp;
231 |     }
232 |     data[i] = tmp;
233 |   }
234 | 
235 |   fclose(fp);
236 |   matrix<double> ret;
237 |   ret.x = nsites;
238 |   ret.y = n_categ;
239 |   ret.data = data;
240 |   return ret;
241 | }
242 | 
243 | // read genotype posterior probabilities from angsd (-dogeno 64), but only for a specific subsets of positions (0-based notation)
244 | matrix<double> readEstiSub(char *fname, int nInd, int start, int end) {
245 |   FILE *fp = getFILE(fname,"rb");
246 |   size_t filesize =fsize(fname);
247 |   if( strcmp(fname,"-")!=0 && (filesize %(sizeof(double)*3*nInd)) ) {
248 |     fprintf(stderr,"\n\t-> Possible error read GENO, binary file might be broken...\n");
249 |     exit(-1);
250 |   }
251 |   int nsites = end-start+1;
252 |   double **data = new double*[nsites];
253 |   fseek(fp, sizeof(double)*(3*nInd)*start, SEEK_SET);
254 |   for(int i=0; i<nsites; i++) {
255 |     double *tmp = new double[3*nInd];
256 |     fread(tmp,sizeof(double),3*nInd,fp);
257 |     data[i]= tmp;
258 |   }
259 |   fclose(fp);
260 |   matrix<double> ret;
261 |   ret.x = nsites;
262 |   ret.y = 3*nInd;
263 |   ret.data = data;
264 |   return ret;
265 | }
266 | 
267 | // read genotype quality (boolean), analysis only on sites to be kept (1) and discard the rest (0)
268 | array<int> readGenoQuality(const char *fname, int nsites) {
269 |   // nsites is how many sites you want
270 |   FILE *fp = getFILE(fname,"r");
271 |   size_t filesize =fsize(fname);
272 |   if( strcmp(fname,"-")!=0 && filesize==0){
273 |     fprintf(stderr,"file:%s looks empty\n",fname);
274 |     exit(0);
275 |   }
276 |   int *tmp = new int[nsites];
277 |   char *buf = new char[filesize];
278 |   fread(buf,sizeof(char),filesize,fp);
279 |   tmp[0] = atoi(strtok(buf,"\t \n"));
280 |   for(int i=1;i<(nsites);i++)
281 |     tmp[i] = atoi(strtok(NULL,"\t \n"));
282 |   fclose(fp);
283 |   array<int> allvalues;
284 |   allvalues.x = nsites;
285 |   allvalues.data = tmp;
286 |   return allvalues;
287 | }
288 | 
289 | // return max value position of a row from a matrix of geno likes or post probs for a specific individual
290 | int maxposarr(matrix<double> &m, int row, int start, int end) {
291 |   double val = m.data[row][start];
292 | 
293 |   for (int i = start; i < end; i++) {
294 |     if (m.data[row][i] > val) {
295 |       start = i;
296 |       val = m.data[row][i];
297 |     }
298 |   }
299 | 
300 |   return start;
301 | }
302 | 
303 | // normalize SFS and exp it if log
304 | void normSFS(matrix<double> &sfs, bool islog) {
305 |   int nsites = sfs.x;
306 |   int ncol = sfs.y;
307 |   double somma = 0.0;
308 |   for (int j=0; j<nsites; j++) {
309 |     // get the sum of values (do exp if they are in log scale)
310 |     somma = 0;
311 |     for(int i=0; i<ncol; i++) {
312 |       if (islog) {
313 |         somma = somma + exp(sfs.data[j][i]);
314 |         } else {
315 |         somma = somma + sfs.data[j][i];
316 |       }
317 |     }
318 |     // divide each value for the sum
319 |     for(int i=0; i<ncol; i++) {
320 |       if (islog) {
321 |         sfs.data[j][i] = exp(sfs.data[j][i]) / somma;
322 |       } else {
323 |         sfs.data[j][i] = sfs.data[j][i] / somma;
324 |       }
325 |     }
326 |    }
327 | }
328 | 
329 | 
330 | // get probability of being variable from posterior probabilities of sample allele frequencies
331 | void getPvar(matrix<double> &sfs, array<double> pvar) {
332 |   for (int i=0; i<sfs.x; i++)
333 |     pvar.data[i]=1-sfs.data[i][0]-sfs.data[i][2*(sfs.y-1)];
334 | }
335 | 
336 | // write an array of doubles into a file
337 | void writearray(array<double> &m,FILE *fp) {
338 |   for(int i=0;i<m.x;i++)
339 |     fprintf(fp,"%f\t",m.data[i]);
340 |   fprintf(fp,"\n");
341 | }
342 | 
343 | // write an array of ints into a file
344 | void writearrayInt(array<int> &m,FILE *fp) {
345 |   for(int i=0;i<m.x;i++)
346 |     fprintf(fp,"%d\t",m.data[i]);
347 |   fprintf(fp,"\n");
348 | }
349 | 
350 | // write a matrix of doubles into a file
351 | void writematrix(matrix<double> &m,FILE *fp) {
352 |   for(int i=0;i<m.x;i++){
353 |     for(int j=0;j<m.y;j++)
354 |       fprintf(fp,"%f\t",m.data[i][j]);
355 |     fprintf(fp,"\n");
356 |   }
357 | }
358 | 
359 | // write a matrix of ints into a file
360 | void writematrixInt(matrix<int> &m,FILE *fp) {
361 |   for(int i=0;i<m.x;i++){
362 |     for(int j=0;j<m.y;j++)
363 |       fprintf(fp,"%d\t",m.data[i][j]);
364 |     fprintf(fp,"\n");
365 |   }
366 | }
367 | 
368 | // add prior
369 | void addPrior(matrix<double> &sfs, array<double> prior) {
370 |   int nsites = sfs.x;
371 |   int ncol = sfs.y;
372 |   for (int j=0; j<nsites; j++) {
373 |     for(int i=0; i<ncol; i++) {
374 |         sfs.data[j][i] = sfs.data[j][i]*prior.data[i];
375 |     }
376 |   }
377 | }
378 | 


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
  1 | GNU GENERAL PUBLIC LICENSE
  2 |                        Version 3, 29 June 2007
  3 | 
  4 |  Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
  5 |  Everyone is permitted to copy and distribute verbatim copies
  6 |  of this license document, but changing it is not allowed.
  7 | 
  8 |                             Preamble
  9 | 
 10 |   The GNU General Public License is a free, copyleft license for
 11 | software and other kinds of works.
 12 | 
 13 |   The licenses for most software and other practical works are designed
 14 | to take away your freedom to share and change the works.  By contrast,
 15 | the GNU General Public License is intended to guarantee your freedom to
 16 | share and change all versions of a program--to make sure it remains free
 17 | software for all its users.  We, the Free Software Foundation, use the
 18 | GNU General Public License for most of our software; it applies also to
 19 | any other work released this way by its authors.  You can apply it to
 20 | your programs, too.
 21 | 
 22 |   When we speak of free software, we are referring to freedom, not
 23 | price.  Our General Public Licenses are designed to make sure that you
 24 | have the freedom to distribute copies of free software (and charge for
 25 | them if you wish), that you receive source code or can get it if you
 26 | want it, that you can change the software or use pieces of it in new
 27 | free programs, and that you know you can do these things.
 28 | 
 29 |   To protect your rights, we need to prevent others from denying you
 30 | these rights or asking you to surrender the rights.  Therefore, you have
 31 | certain responsibilities if you distribute copies of the software, or if
 32 | you modify it: responsibilities to respect the freedom of others.
 33 | 
 34 |   For example, if you distribute copies of such a program, whether
 35 | gratis or for a fee, you must pass on to the recipients the same
 36 | freedoms that you received.  You must make sure that they, too, receive
 37 | or can get the source code.  And you must show them these terms so they
 38 | know their rights.
 39 | 
 40 |   Developers that use the GNU GPL protect your rights with two steps:
 41 | (1) assert copyright on the software, and (2) offer you this License
 42 | giving you legal permission to copy, distribute and/or modify it.
 43 | 
 44 |   For the developers' and authors' protection, the GPL clearly explains
 45 | that there is no warranty for this free software.  For both users' and
 46 | authors' sake, the GPL requires that modified versions be marked as
 47 | changed, so that their problems will not be attributed erroneously to
 48 | authors of previous versions.
 49 | 
 50 |   Some devices are designed to deny users access to install or run
 51 | modified versions of the software inside them, although the manufacturer
 52 | can do so.  This is fundamentally incompatible with the aim of
 53 | protecting users' freedom to change the software.  The systematic
 54 | pattern of such abuse occurs in the area of products for individuals to
 55 | use, which is precisely where it is most unacceptable.  Therefore, we
 56 | have designed this version of the GPL to prohibit the practice for those
 57 | products.  If such problems arise substantially in other domains, we
 58 | stand ready to extend this provision to those domains in future versions
 59 | of the GPL, as needed to protect the freedom of users.
 60 | 
 61 |   Finally, every program is threatened constantly by software patents.
 62 | States should not allow patents to restrict development and use of
 63 | software on general-purpose computers, but in those that do, we wish to
 64 | avoid the special danger that patents applied to a free program could
 65 | make it effectively proprietary.  To prevent this, the GPL assures that
 66 | patents cannot be used to render the program non-free.
 67 | 
 68 |   The precise terms and conditions for copying, distribution and
 69 | modification follow.
 70 | 
 71 |                        TERMS AND CONDITIONS
 72 | 
 73 |   0. Definitions.
 74 | 
 75 |   "This License" refers to version 3 of the GNU General Public License.
 76 | 
 77 |   "Copyright" also means copyright-like laws that apply to other kinds of
 78 | works, such as semiconductor masks.
 79 | 
 80 |   "The Program" refers to any copyrightable work licensed under this
 81 | License.  Each licensee is addressed as "you".  "Licensees" and
 82 | "recipients" may be individuals or organizations.
 83 | 
 84 |   To "modify" a work means to copy from or adapt all or part of the work
 85 | in a fashion requiring copyright permission, other than the making of an
 86 | exact copy.  The resulting work is called a "modified version" of the
 87 | earlier work or a work "based on" the earlier work.
 88 | 
 89 |   A "covered work" means either the unmodified Program or a work based
 90 | on the Program.
 91 | 
 92 |   To "propagate" a work means to do anything with it that, without
 93 | permission, would make you directly or secondarily liable for
 94 | infringement under applicable copyright law, except executing it on a
 95 | computer or modifying a private copy.  Propagation includes copying,
 96 | distribution (with or without modification), making available to the
 97 | public, and in some countries other activities as well.
 98 | 
 99 |   To "convey" a work means any kind of propagation that enables other
100 | parties to make or receive copies.  Mere interaction with a user through
101 | a computer network, with no transfer of a copy, is not conveying.
102 | 
103 |   An interactive user interface displays "Appropriate Legal Notices"
104 | to the extent that it includes a convenient and prominently visible
105 | feature that (1) displays an appropriate copyright notice, and (2)
106 | tells the user that there is no warranty for the work (except to the
107 | extent that warranties are provided), that licensees may convey the
108 | work under this License, and how to view a copy of this License.  If
109 | the interface presents a list of user commands or options, such as a
110 | menu, a prominent item in the list meets this criterion.
111 | 
112 |   1. Source Code.
113 | 
114 |   The "source code" for a work means the preferred form of the work
115 | for making modifications to it.  "Object code" means any non-source
116 | form of a work.
117 | 
118 |   A "Standard Interface" means an interface that either is an official
119 | standard defined by a recognized standards body, or, in the case of
120 | interfaces specified for a particular programming language, one that
121 | is widely used among developers working in that language.
122 | 
123 |   The "System Libraries" of an executable work include anything, other
124 | than the work as a whole, that (a) is included in the normal form of
125 | packaging a Major Component, but which is not part of that Major
126 | Component, and (b) serves only to enable use of the work with that
127 | Major Component, or to implement a Standard Interface for which an
128 | implementation is available to the public in source code form.  A
129 | "Major Component", in this context, means a major essential component
130 | (kernel, window system, and so on) of the specific operating system
131 | (if any) on which the executable work runs, or a compiler used to
132 | produce the work, or an object code interpreter used to run it.
133 | 
134 |   The "Corresponding Source" for a work in object code form means all
135 | the source code needed to generate, install, and (for an executable
136 | work) run the object code and to modify the work, including scripts to
137 | control those activities.  However, it does not include the work's
138 | System Libraries, or general-purpose tools or generally available free
139 | programs which are used unmodified in performing those activities but
140 | which are not part of the work.  For example, Corresponding Source
141 | includes interface definition files associated with source files for
142 | the work, and the source code for shared libraries and dynamically
143 | linked subprograms that the work is specifically designed to require,
144 | such as by intimate data communication or control flow between those
145 | subprograms and other parts of the work.
146 | 
147 |   The Corresponding Source need not include anything that users
148 | can regenerate automatically from other parts of the Corresponding
149 | Source.
150 | 
151 |   The Corresponding Source for a work in source code form is that
152 | same work.
153 | 
154 |   2. Basic Permissions.
155 | 
156 |   All rights granted under this License are granted for the term of
157 | copyright on the Program, and are irrevocable provided the stated
158 | conditions are met.  This License explicitly affirms your unlimited
159 | permission to run the unmodified Program.  The output from running a
160 | covered work is covered by this License only if the output, given its
161 | content, constitutes a covered work.  This License acknowledges your
162 | rights of fair use or other equivalent, as provided by copyright law.
163 | 
164 |   You may make, run and propagate covered works that you do not
165 | convey, without conditions so long as your license otherwise remains
166 | in force.  You may convey covered works to others for the sole purpose
167 | of having them make modifications exclusively for you, or provide you
168 | with facilities for running those works, provided that you comply with
169 | the terms of this License in conveying all material for which you do
170 | not control copyright.  Those thus making or running the covered works
171 | for you must do so exclusively on your behalf, under your direction
172 | and control, on terms that prohibit them from making any copies of
173 | your copyrighted material outside their relationship with you.
174 | 
175 |   Conveying under any other circumstances is permitted solely under
176 | the conditions stated below.  Sublicensing is not allowed; section 10
177 | makes it unnecessary.
178 | 
179 |   3. Protecting Users' Legal Rights From Anti-Circumvention Law.
180 | 
181 |   No covered work shall be deemed part of an effective technological
182 | measure under any applicable law fulfilling obligations under article
183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or
184 | similar laws prohibiting or restricting circumvention of such
185 | measures.
186 | 
187 |   When you convey a covered work, you waive any legal power to forbid
188 | circumvention of technological measures to the extent such circumvention
189 | is effected by exercising rights under this License with respect to
190 | the covered work, and you disclaim any intention to limit operation or
191 | modification of the work as a means of enforcing, against the work's
192 | users, your or third parties' legal rights to forbid circumvention of
193 | technological measures.
194 | 
195 |   4. Conveying Verbatim Copies.
196 | 
197 |   You may convey verbatim copies of the Program's source code as you
198 | receive it, in any medium, provided that you conspicuously and
199 | appropriately publish on each copy an appropriate copyright notice;
200 | keep intact all notices stating that this License and any
201 | non-permissive terms added in accord with section 7 apply to the code;
202 | keep intact all notices of the absence of any warranty; and give all
203 | recipients a copy of this License along with the Program.
204 | 
205 |   You may charge any price or no price for each copy that you convey,
206 | and you may offer support or warranty protection for a fee.
207 | 
208 |   5. Conveying Modified Source Versions.
209 | 
210 |   You may convey a work based on the Program, or the modifications to
211 | produce it from the Program, in the form of source code under the
212 | terms of section 4, provided that you also meet all of these conditions:
213 | 
214 |     a) The work must carry prominent notices stating that you modified
215 |     it, and giving a relevant date.
216 | 
217 |     b) The work must carry prominent notices stating that it is
218 |     released under this License and any conditions added under section
219 |     7.  This requirement modifies the requirement in section 4 to
220 |     "keep intact all notices".
221 | 
222 |     c) You must license the entire work, as a whole, under this
223 |     License to anyone who comes into possession of a copy.  This
224 |     License will therefore apply, along with any applicable section 7
225 |     additional terms, to the whole of the work, and all its parts,
226 |     regardless of how they are packaged.  This License gives no
227 |     permission to license the work in any other way, but it does not
228 |     invalidate such permission if you have separately received it.
229 | 
230 |     d) If the work has interactive user interfaces, each must display
231 |     Appropriate Legal Notices; however, if the Program has interactive
232 |     interfaces that do not display Appropriate Legal Notices, your
233 |     work need not make them do so.
234 | 
235 |   A compilation of a covered work with other separate and independent
236 | works, which are not by their nature extensions of the covered work,
237 | and which are not combined with it such as to form a larger program,
238 | in or on a volume of a storage or distribution medium, is called an
239 | "aggregate" if the compilation and its resulting copyright are not
240 | used to limit the access or legal rights of the compilation's users
241 | beyond what the individual works permit.  Inclusion of a covered work
242 | in an aggregate does not cause this License to apply to the other
243 | parts of the aggregate.
244 | 
245 |   6. Conveying Non-Source Forms.
246 | 
247 |   You may convey a covered work in object code form under the terms
248 | of sections 4 and 5, provided that you also convey the
249 | machine-readable Corresponding Source under the terms of this License,
250 | in one of these ways:
251 | 
252 |     a) Convey the object code in, or embodied in, a physical product
253 |     (including a physical distribution medium), accompanied by the
254 |     Corresponding Source fixed on a durable physical medium
255 |     customarily used for software interchange.
256 | 
257 |     b) Convey the object code in, or embodied in, a physical product
258 |     (including a physical distribution medium), accompanied by a
259 |     written offer, valid for at least three years and valid for as
260 |     long as you offer spare parts or customer support for that product
261 |     model, to give anyone who possesses the object code either (1) a
262 |     copy of the Corresponding Source for all the software in the
263 |     product that is covered by this License, on a durable physical
264 |     medium customarily used for software interchange, for a price no
265 |     more than your reasonable cost of physically performing this
266 |     conveying of source, or (2) access to copy the
267 |     Corresponding Source from a network server at no charge.
268 | 
269 |     c) Convey individual copies of the object code with a copy of the
270 |     written offer to provide the Corresponding Source.  This
271 |     alternative is allowed only occasionally and noncommercially, and
272 |     only if you received the object code with such an offer, in accord
273 |     with subsection 6b.
274 | 
275 |     d) Convey the object code by offering access from a designated
276 |     place (gratis or for a charge), and offer equivalent access to the
277 |     Corresponding Source in the same way through the same place at no
278 |     further charge.  You need not require recipients to copy the
279 |     Corresponding Source along with the object code.  If the place to
280 |     copy the object code is a network server, the Corresponding Source
281 |     may be on a different server (operated by you or a third party)
282 |     that supports equivalent copying facilities, provided you maintain
283 |     clear directions next to the object code saying where to find the
284 |     Corresponding Source.  Regardless of what server hosts the
285 |     Corresponding Source, you remain obligated to ensure that it is
286 |     available for as long as needed to satisfy these requirements.
287 | 
288 |     e) Convey the object code using peer-to-peer transmission, provided
289 |     you inform other peers where the object code and Corresponding
290 |     Source of the work are being offered to the general public at no
291 |     charge under subsection 6d.
292 | 
293 |   A separable portion of the object code, whose source code is excluded
294 | from the Corresponding Source as a System Library, need not be
295 | included in conveying the object code work.
296 | 
297 |   A "User Product" is either (1) a "consumer product", which means any
298 | tangible personal property which is normally used for personal, family,
299 | or household purposes, or (2) anything designed or sold for incorporation
300 | into a dwelling.  In determining whether a product is a consumer product,
301 | doubtful cases shall be resolved in favor of coverage.  For a particular
302 | product received by a particular user, "normally used" refers to a
303 | typical or common use of that class of product, regardless of the status
304 | of the particular user or of the way in which the particular user
305 | actually uses, or expects or is expected to use, the product.  A product
306 | is a consumer product regardless of whether the product has substantial
307 | commercial, industrial or non-consumer uses, unless such uses represent
308 | the only significant mode of use of the product.
309 | 
310 |   "Installation Information" for a User Product means any methods,
311 | procedures, authorization keys, or other information required to install
312 | and execute modified versions of a covered work in that User Product from
313 | a modified version of its Corresponding Source.  The information must
314 | suffice to ensure that the continued functioning of the modified object
315 | code is in no case prevented or interfered with solely because
316 | modification has been made.
317 | 
318 |   If you convey an object code work under this section in, or with, or
319 | specifically for use in, a User Product, and the conveying occurs as
320 | part of a transaction in which the right of possession and use of the
321 | User Product is transferred to the recipient in perpetuity or for a
322 | fixed term (regardless of how the transaction is characterized), the
323 | Corresponding Source conveyed under this section must be accompanied
324 | by the Installation Information.  But this requirement does not apply
325 | if neither you nor any third party retains the ability to install
326 | modified object code on the User Product (for example, the work has
327 | been installed in ROM).
328 | 
329 |   The requirement to provide Installation Information does not include a
330 | requirement to continue to provide support service, warranty, or updates
331 | for a work that has been modified or installed by the recipient, or for
332 | the User Product in which it has been modified or installed.  Access to a
333 | network may be denied when the modification itself materially and
334 | adversely affects the operation of the network or violates the rules and
335 | protocols for communication across the network.
336 | 
337 |   Corresponding Source conveyed, and Installation Information provided,
338 | in accord with this section must be in a format that is publicly
339 | documented (and with an implementation available to the public in
340 | source code form), and must require no special password or key for
341 | unpacking, reading or copying.
342 | 
343 |   7. Additional Terms.
344 | 
345 |   "Additional permissions" are terms that supplement the terms of this
346 | License by making exceptions from one or more of its conditions.
347 | Additional permissions that are applicable to the entire Program shall
348 | be treated as though they were included in this License, to the extent
349 | that they are valid under applicable law.  If additional permissions
350 | apply only to part of the Program, that part may be used separately
351 | under those permissions, but the entire Program remains governed by
352 | this License without regard to the additional permissions.
353 | 
354 |   When you convey a copy of a covered work, you may at your option
355 | remove any additional permissions from that copy, or from any part of
356 | it.  (Additional permissions may be written to require their own
357 | removal in certain cases when you modify the work.)  You may place
358 | additional permissions on material, added by you to a covered work,
359 | for which you have or can give appropriate copyright permission.
360 | 
361 |   Notwithstanding any other provision of this License, for material you
362 | add to a covered work, you may (if authorized by the copyright holders of
363 | that material) supplement the terms of this License with terms:
364 | 
365 |     a) Disclaiming warranty or limiting liability differently from the
366 |     terms of sections 15 and 16 of this License; or
367 | 
368 |     b) Requiring preservation of specified reasonable legal notices or
369 |     author attributions in that material or in the Appropriate Legal
370 |     Notices displayed by works containing it; or
371 | 
372 |     c) Prohibiting misrepresentation of the origin of that material, or
373 |     requiring that modified versions of such material be marked in
374 |     reasonable ways as different from the original version; or
375 | 
376 |     d) Limiting the use for publicity purposes of names of licensors or
377 |     authors of the material; or
378 | 
379 |     e) Declining to grant rights under trademark law for use of some
380 |     trade names, trademarks, or service marks; or
381 | 
382 |     f) Requiring indemnification of licensors and authors of that
383 |     material by anyone who conveys the material (or modified versions of
384 |     it) with contractual assumptions of liability to the recipient, for
385 |     any liability that these contractual assumptions directly impose on
386 |     those licensors and authors.
387 | 
388 |   All other non-permissive additional terms are considered "further
389 | restrictions" within the meaning of section 10.  If the Program as you
390 | received it, or any part of it, contains a notice stating that it is
391 | governed by this License along with a term that is a further
392 | restriction, you may remove that term.  If a license document contains
393 | a further restriction but permits relicensing or conveying under this
394 | License, you may add to a covered work material governed by the terms
395 | of that license document, provided that the further restriction does
396 | not survive such relicensing or conveying.
397 | 
398 |   If you add terms to a covered work in accord with this section, you
399 | must place, in the relevant source files, a statement of the
400 | additional terms that apply to those files, or a notice indicating
401 | where to find the applicable terms.
402 | 
403 |   Additional terms, permissive or non-permissive, may be stated in the
404 | form of a separately written license, or stated as exceptions;
405 | the above requirements apply either way.
406 | 
407 |   8. Termination.
408 | 
409 |   You may not propagate or modify a covered work except as expressly
410 | provided under this License.  Any attempt otherwise to propagate or
411 | modify it is void, and will automatically terminate your rights under
412 | this License (including any patent licenses granted under the third
413 | paragraph of section 11).
414 | 
415 |   However, if you cease all violation of this License, then your
416 | license from a particular copyright holder is reinstated (a)
417 | provisionally, unless and until the copyright holder explicitly and
418 | finally terminates your license, and (b) permanently, if the copyright
419 | holder fails to notify you of the violation by some reasonable means
420 | prior to 60 days after the cessation.
421 | 
422 |   Moreover, your license from a particular copyright holder is
423 | reinstated permanently if the copyright holder notifies you of the
424 | violation by some reasonable means, this is the first time you have
425 | received notice of violation of this License (for any work) from that
426 | copyright holder, and you cure the violation prior to 30 days after
427 | your receipt of the notice.
428 | 
429 |   Termination of your rights under this section does not terminate the
430 | licenses of parties who have received copies or rights from you under
431 | this License.  If your rights have been terminated and not permanently
432 | reinstated, you do not qualify to receive new licenses for the same
433 | material under section 10.
434 | 
435 |   9. Acceptance Not Required for Having Copies.
436 | 
437 |   You are not required to accept this License in order to receive or
438 | run a copy of the Program.  Ancillary propagation of a covered work
439 | occurring solely as a consequence of using peer-to-peer transmission
440 | to receive a copy likewise does not require acceptance.  However,
441 | nothing other than this License grants you permission to propagate or
442 | modify any covered work.  These actions infringe copyright if you do
443 | not accept this License.  Therefore, by modifying or propagating a
444 | covered work, you indicate your acceptance of this License to do so.
445 | 
446 |   10. Automatic Licensing of Downstream Recipients.
447 | 
448 |   Each time you convey a covered work, the recipient automatically
449 | receives a license from the original licensors, to run, modify and
450 | propagate that work, subject to this License.  You are not responsible
451 | for enforcing compliance by third parties with this License.
452 | 
453 |   An "entity transaction" is a transaction transferring control of an
454 | organization, or substantially all assets of one, or subdividing an
455 | organization, or merging organizations.  If propagation of a covered
456 | work results from an entity transaction, each party to that
457 | transaction who receives a copy of the work also receives whatever
458 | licenses to the work the party's predecessor in interest had or could
459 | give under the previous paragraph, plus a right to possession of the
460 | Corresponding Source of the work from the predecessor in interest, if
461 | the predecessor has it or can get it with reasonable efforts.
462 | 
463 |   You may not impose any further restrictions on the exercise of the
464 | rights granted or affirmed under this License.  For example, you may
465 | not impose a license fee, royalty, or other charge for exercise of
466 | rights granted under this License, and you may not initiate litigation
467 | (including a cross-claim or counterclaim in a lawsuit) alleging that
468 | any patent claim is infringed by making, using, selling, offering for
469 | sale, or importing the Program or any portion of it.
470 | 
471 |   11. Patents.
472 | 
473 |   A "contributor" is a copyright holder who authorizes use under this
474 | License of the Program or a work on which the Program is based.  The
475 | work thus licensed is called the contributor's "contributor version".
476 | 
477 |   A contributor's "essential patent claims" are all patent claims
478 | owned or controlled by the contributor, whether already acquired or
479 | hereafter acquired, that would be infringed by some manner, permitted
480 | by this License, of making, using, or selling its contributor version,
481 | but do not include claims that would be infringed only as a
482 | consequence of further modification of the contributor version.  For
483 | purposes of this definition, "control" includes the right to grant
484 | patent sublicenses in a manner consistent with the requirements of
485 | this License.
486 | 
487 |   Each contributor grants you a non-exclusive, worldwide, royalty-free
488 | patent license under the contributor's essential patent claims, to
489 | make, use, sell, offer for sale, import and otherwise run, modify and
490 | propagate the contents of its contributor version.
491 | 
492 |   In the following three paragraphs, a "patent license" is any express
493 | agreement or commitment, however denominated, not to enforce a patent
494 | (such as an express permission to practice a patent or covenant not to
495 | sue for patent infringement).  To "grant" such a patent license to a
496 | party means to make such an agreement or commitment not to enforce a
497 | patent against the party.
498 | 
499 |   If you convey a covered work, knowingly relying on a patent license,
500 | and the Corresponding Source of the work is not available for anyone
501 | to copy, free of charge and under the terms of this License, through a
502 | publicly available network server or other readily accessible means,
503 | then you must either (1) cause the Corresponding Source to be so
504 | available, or (2) arrange to deprive yourself of the benefit of the
505 | patent license for this particular work, or (3) arrange, in a manner
506 | consistent with the requirements of this License, to extend the patent
507 | license to downstream recipients.  "Knowingly relying" means you have
508 | actual knowledge that, but for the patent license, your conveying the
509 | covered work in a country, or your recipient's use of the covered work
510 | in a country, would infringe one or more identifiable patents in that
511 | country that you have reason to believe are valid.
512 | 
513 |   If, pursuant to or in connection with a single transaction or
514 | arrangement, you convey, or propagate by procuring conveyance of, a
515 | covered work, and grant a patent license to some of the parties
516 | receiving the covered work authorizing them to use, propagate, modify
517 | or convey a specific copy of the covered work, then the patent license
518 | you grant is automatically extended to all recipients of the covered
519 | work and works based on it.
520 | 
521 |   A patent license is "discriminatory" if it does not include within
522 | the scope of its coverage, prohibits the exercise of, or is
523 | conditioned on the non-exercise of one or more of the rights that are
524 | specifically granted under this License.  You may not convey a covered
525 | work if you are a party to an arrangement with a third party that is
526 | in the business of distributing software, under which you make payment
527 | to the third party based on the extent of your activity of conveying
528 | the work, and under which the third party grants, to any of the
529 | parties who would receive the covered work from you, a discriminatory
530 | patent license (a) in connection with copies of the covered work
531 | conveyed by you (or copies made from those copies), or (b) primarily
532 | for and in connection with specific products or compilations that
533 | contain the covered work, unless you entered into that arrangement,
534 | or that patent license was granted, prior to 28 March 2007.
535 | 
536 |   Nothing in this License shall be construed as excluding or limiting
537 | any implied license or other defenses to infringement that may
538 | otherwise be available to you under applicable patent law.
539 | 
540 |   12. No Surrender of Others' Freedom.
541 | 
542 |   If conditions are imposed on you (whether by court order, agreement or
543 | otherwise) that contradict the conditions of this License, they do not
544 | excuse you from the conditions of this License.  If you cannot convey a
545 | covered work so as to satisfy simultaneously your obligations under this
546 | License and any other pertinent obligations, then as a consequence you may
547 | not convey it at all.  For example, if you agree to terms that obligate you
548 | to collect a royalty for further conveying from those to whom you convey
549 | the Program, the only way you could satisfy both those terms and this
550 | License would be to refrain entirely from conveying the Program.
551 | 
552 |   13. Use with the GNU Affero General Public License.
553 | 
554 |   Notwithstanding any other provision of this License, you have
555 | permission to link or combine any covered work with a work licensed
556 | under version 3 of the GNU Affero General Public License into a single
557 | combined work, and to convey the resulting work.  The terms of this
558 | License will continue to apply to the part which is the covered work,
559 | but the special requirements of the GNU Affero General Public License,
560 | section 13, concerning interaction through a network will apply to the
561 | combination as such.
562 | 
563 |   14. Revised Versions of this License.
564 | 
565 |   The Free Software Foundation may publish revised and/or new versions of
566 | the GNU General Public License from time to time.  Such new versions will
567 | be similar in spirit to the present version, but may differ in detail to
568 | address new problems or concerns.
569 | 
570 |   Each version is given a distinguishing version number.  If the
571 | Program specifies that a certain numbered version of the GNU General
572 | Public License "or any later version" applies to it, you have the
573 | option of following the terms and conditions either of that numbered
574 | version or of any later version published by the Free Software
575 | Foundation.  If the Program does not specify a version number of the
576 | GNU General Public License, you may choose any version ever published
577 | by the Free Software Foundation.
578 | 
579 |   If the Program specifies that a proxy can decide which future
580 | versions of the GNU General Public License can be used, that proxy's
581 | public statement of acceptance of a version permanently authorizes you
582 | to choose that version for the Program.
583 | 
584 |   Later license versions may give you additional or different
585 | permissions.  However, no additional obligations are imposed on any
586 | author or copyright holder as a result of your choosing to follow a
587 | later version.
588 | 
589 |   15. Disclaimer of Warranty.
590 | 
591 |   THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
592 | APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
596 | PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
597 | IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
599 | 
600 |   16. Limitation of Liability.
601 | 
602 |   IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
610 | SUCH DAMAGES.
611 | 
612 |   17. Interpretation of Sections 15 and 16.
613 | 
614 |   If the disclaimer of warranty and limitation of liability provided
615 | above cannot be given local legal effect according to their terms,
616 | reviewing courts shall apply local law that most closely approximates
617 | an absolute waiver of all civil liability in connection with the
618 | Program, unless a warranty or assumption of liability accompanies a
619 | copy of the Program in return for a fee.
620 | 
621 |                      END OF TERMS AND CONDITIONS
622 | 
623 |             How to Apply These Terms to Your New Programs
624 | 
625 |   If you develop a new program, and you want it to be of the greatest
626 | possible use to the public, the best way to achieve this is to make it
627 | free software which everyone can redistribute and change under these terms.
628 | 
629 |   To do so, attach the following notices to the program.  It is safest
630 | to attach them to the start of each source file to most effectively
631 | state the exclusion of warranty; and each file should have at least
632 | the "copyright" line and a pointer to where the full notice is found.
633 | 
634 |     {one line to give the program's name and a brief idea of what it does.}
635 |     Copyright (C) {year}  {name of author}
636 | 
637 |     This program is free software: you can redistribute it and/or modify
638 |     it under the terms of the GNU General Public License as published by
639 |     the Free Software Foundation, either version 3 of the License, or
640 |     (at your option) any later version.
641 | 
642 |     This program is distributed in the hope that it will be useful,
643 |     but WITHOUT ANY WARRANTY; without even the implied warranty of
644 |     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
645 |     GNU General Public License for more details.
646 | 
647 |     You should have received a copy of the GNU General Public License
648 |     along with this program.  If not, see <http://www.gnu.org/licenses/>.
649 | 
650 | Also add information on how to contact you by electronic and paper mail.
651 | 
652 |   If the program does terminal interaction, make it output a short
653 | notice like this when it starts in an interactive mode:
654 | 
655 |     {project}  Copyright (C) {year}  {fullname}
656 |     This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
657 |     This is free software, and you are welcome to redistribute it
658 |     under certain conditions; type `show c' for details.
659 | 
660 | The hypothetical commands `show w' and `show c' should show the appropriate
661 | parts of the General Public License.  Of course, your program's commands
662 | might be different; for a GUI interface, you would use an "about box".
663 | 
664 |   You should also get your employer (if you work as a programmer) or school,
665 | if any, to sign a "copyright disclaimer" for the program, if necessary.
666 | For more information on this, and how to apply and follow the GNU GPL, see
667 | <http://www.gnu.org/licenses/>.
668 | 
669 |   The GNU General Public License does not permit incorporating your program
670 | into proprietary programs.  If your program is a subroutine library, you
671 | may consider it more useful to permit linking proprietary applications with
672 | the library.  If this is what you want to do, use the GNU Lesser General
673 | Public License instead of this License.  But first, please read
674 | <http://www.gnu.org/philosophy/why-not-lgpl.html>.
675 | 


--------------------------------------------------------------------------------