├── .gitignore
├── README.md
├── Snakefile
├── bin
    ├── filter_sites.py
    ├── group_pileup.py
    ├── join_pileup.py
    └── select_sites.py
├── config.yaml
├── data
    ├── test1_R1.fq.gz
    ├── test1_R2.fq.gz
    ├── test2_R1.fq.gz
    ├── test2_R2.fq.gz
    ├── test3_R1.fq.gz
    └── test3_R2.fq.gz
└── docs
    └── flow.svg


/.gitignore:
--------------------------------------------------------------------------------
1 | .snakemake/
2 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.11046885.svg)](https://doi.org/10.5281/zenodo.11046885)
 2 | 
 3 | # m<sup>5</sup>C-UBSseq
 4 | 
 5 | ## Changelog
 6 | 
 7 | - 4/23/2024: rewrite code using polars
 8 | 
 9 | ## workflow
10 | 
11 | [![](./docs/flow.svg)](https://github.com/y9c/m5C-UBSseq)
12 | 
13 | ## Citation
14 | 
15 | - cite this software
16 | 
17 |   ```BibTex
18 |   @software{chang_y_2024_11046885,
19 |       author    = {Chang Y},
20 |       title     = {y9c/m5C-UBSseq: V0.1},
21 |       publisher = {Zenodo},
22 |       version   = {v0.1},
23 |       doi       = {10.5281/zenodo.11046885},
24 |       url       = {https://doi.org/10.5281/zenodo.11046885}
25 |   }
26 |   ```
27 | 
28 | - cite the method
29 | 
30 |   ```BibTex
31 |   @article{dai_ultrafast_2024,
32 |       title = {Ultrafast bisulfite sequencing detection of 5-methylcytosine in {DNA} and {RNA}},
33 |       url = {https://www.nature.com/articles/s41587-023-02034-w},
34 |       doi = {10.1038/s41587-023-02034-w},
35 |       author = {Dai, Qing and Ye, Chang and Irkliyenko, Iryna and Wang, Yiding and Sun, Hui-Lung and Gao, Yun and Liu, Yushuai and Beadell, Alana and Perea, José and Goel, Ajay and He, Chuan},
36 |       date = {2024-01-02},
37 |   }
38 |   ```
39 | 
40 | &nbsp;
41 | 
42 | <p align="center">
43 | <img
44 |   src="https://raw.githubusercontent.com/y9c/y9c/master/resource/footer_line.svg?sanitize=true"
45 | />
46 | </p>
47 | <p align="center">
48 | Copyright &copy; 2021-present
49 | <a href="https://github.com/y9c" target="_blank">Chang Y</a>
50 | </p>
51 | <p align="center">
52 | 


--------------------------------------------------------------------------------
/Snakefile:
--------------------------------------------------------------------------------
  1 | from snakemake.utils import min_version
  2 | from collections import defaultdict
  3 | from pathlib import Path
  4 | 
  5 | min_version("8.0")
  6 | 
  7 | 
  8 | configfile: Path(workflow.basedir) / "config.yaml"
  9 | 
 10 | 
 11 | workdir: "workspace"
 12 | 
 13 | 
 14 | BIN = config["path"]
 15 | REF = config["reference"]
 16 | 
 17 | CUSTOMIZED_GENES = [os.path.expanduser(i) for i in config.get("customized_genes", [])]
 18 | WITH_UMI = config.get("library", "") in ["INLINE", "TAKARAV3"]
 19 | MARKDUP = config.get("markdup", False)
 20 | 
 21 | 
 22 | SAMPLE2DATA = defaultdict(dict)
 23 | SAMPLE2LIB = defaultdict(dict)
 24 | GROUP2SAMPLE = defaultdict(list)
 25 | for s, v in config["samples"].items():
 26 |     if v.get("treated", True):
 27 |         # set default group as sample name, if not specified
 28 |         GROUP2SAMPLE[v.get("group", s)].append(s)
 29 |     SAMPLE2LIB[s] = v.get("library", config.get("library", ""))
 30 |     for i, v2 in enumerate(v.get("data", []), 1):
 31 |         r = f"run{i}"
 32 |         SAMPLE2DATA[s][r] = {k3: os.path.expanduser(v3) for k3, v3 in v2.items()}
 33 | 
 34 | 
 35 | INTERNALDIR = Path("internal_files")
 36 | TEMPDIR = Path(".tmp")
 37 | 
 38 | if os.environ.get("TMPDIR") is None:
 39 |     os.environ["TMPDIR"] = str(TEMPDIR)
 40 | 
 41 | 
 42 | envvars:
 43 |     "TMPDIR",
 44 | 
 45 | 
 46 | rule all:
 47 |     input:
 48 |         expand("report_reads/mapped/{sample}.tsv", sample=SAMPLE2DATA.keys()),
 49 |         [
 50 |             (
 51 |                 INTERNALDIR / f"discarded_reads/{sample}_{rn}_R1.unmapped.fq.gz"
 52 |                 if len(v) == 1
 53 |                 else [
 54 |                     INTERNALDIR / f"discarded_reads/{sample}_{rn}_R1.unmapped.fq.gz",
 55 |                     INTERNALDIR / f"discarded_reads/{sample}_{rn}_R2.unmapped.fq.gz",
 56 |                 ]
 57 |             )
 58 |             for sample, v in SAMPLE2DATA.items()
 59 |             for rn, v2 in v.items()
 60 |         ],
 61 |         expand(
 62 |             "detected_sites/filtered/{sample}.{ref}.tsv",
 63 |             sample=SAMPLE2DATA.keys(),
 64 |             ref=["genes", "genome"],
 65 |         ),
 66 | 
 67 | 
 68 | rule cutadapt_SE:
 69 |     input:
 70 |         lambda wildcards: SAMPLE2DATA[wildcards.sample][wildcards.rn].get("R1", "/"),
 71 |     output:
 72 |         fastq_cut=temp(TEMPDIR / "cut_adapter_SE/{sample}_{rn}_R1.fq.gz"),
 73 |         fastq_tooshort=INTERNALDIR / "discarded_reads/{sample}_{rn}_R1.tooshort.fq.gz",
 74 |         fastq_untrimmed=INTERNALDIR / "discarded_reads/{sample}_{rn}_R1.untrimmed.fq.gz",
 75 |         report="report_reads/trimming/{sample}_{rn}.json",
 76 |     params:
 77 |         library=lambda wildcards: SAMPLE2LIB[wildcards.sample],
 78 |     threads: 20
 79 |     shell:
 80 |         """
 81 |         cutseq -t {threads} -A {params.library} -m 20 --trim-polyA --ensure-inline-barcode --auto-rc -o {output.fastq_cut} -s {output.fastq_tooshort} -u {output.fastq_untrimmed} --json-file {output.report} {input} 
 82 |         """
 83 | 
 84 | 
 85 | rule cutadapt_PE:
 86 |     input:
 87 |         lambda wildcards: SAMPLE2DATA[wildcards.sample][wildcards.rn].get("R1", "/"),
 88 |         lambda wildcards: SAMPLE2DATA[wildcards.sample][wildcards.rn].get("R2", "/"),
 89 |     output:
 90 |         fastq_cut=[
 91 |             temp(TEMPDIR / "cut_adapter_PE/{sample}_{rn}_R1.fq.gz"),
 92 |             temp(TEMPDIR / "cut_adapter_PE/{sample}_{rn}_R2.fq.gz"),
 93 |         ],
 94 |         fastq_tooshort=[
 95 |             INTERNALDIR / "discarded_reads/{sample}_{rn}_R1.tooshort.fq.gz",
 96 |             INTERNALDIR / "discarded_reads/{sample}_{rn}_R2.tooshort.fq.gz",
 97 |         ],
 98 |         fastq_untrimmed=[
 99 |             INTERNALDIR / "discarded_reads/{sample}_{rn}_R1.untrimmed.fq.gz",
100 |             INTERNALDIR / "discarded_reads/{sample}_{rn}_R2.untrimmed.fq.gz",
101 |         ],
102 |         report="report_reads/trimming/{sample}_{rn}.report",
103 |     params:
104 |         library=lambda wildcards: SAMPLE2LIB[wildcards.sample],
105 |     threads: 20
106 |     shell:
107 |         """
108 |         cutseq -t {threads} -A {params.library} -m 20 --trim-polyA --ensure-inline-barcode --auto-rc -o {output.fastq_cut} -s {output.fastq_tooshort} -u {output.fastq_untrimmed} --json-file {output.report} {input} 
109 |         """
110 | 
111 | 
112 | rule prepare_genes_index:
113 |     input:
114 |         CUSTOMIZED_GENES,
115 |     output:
116 |         fa="prepared_genes/genes.fa",
117 |         index="prepared_genes/genes.3n.CT.1.ht2",
118 |     params:
119 |         index="prepared_genes/genes",
120 |     threads: 12
121 |     shell:
122 |         """
123 |         cat {input} >{output.fa}
124 |         rm -f `dirname {output.index}`/`basename {output.index} ".CT.1.ht2"`.*.ht2
125 |         ~/tools/hisat2/hisat-3n-build -p 12 --base-change C,T {output.fa} {params.index}
126 |         """
127 | 
128 | 
129 | rule build_gene_index:
130 |     input:
131 |         fa="prepared_genes/genes.fa",
132 |     output:
133 |         fai="prepared_genes/genes.fa.fai",
134 |     shell:
135 |         """
136 |         samtools faidx {output.fa}
137 |         """
138 | 
139 | 
140 | rule generate_saf_gene:
141 |     input:
142 |         fai="prepared_genes/genes.fa.fai",
143 |     output:
144 |         saf="prepared_genes/genes.saf",
145 |     shell:
146 |         """
147 |         awk 'BEGIN{{OFS="\\t"}}{{print $1,$1,0,$2,"+"}}' {input} > {output}
148 |         """
149 | 
150 | 
151 | # Mapping (SE mapping mode)
152 | 
153 | 
154 | rule hisat2_3n_mapping_contamination_SE:
155 |     input:
156 |         TEMPDIR / "cut_adapter_SE/{sample}_{rn}_R1.fq.gz",
157 |     output:
158 |         mapped=temp(TEMPDIR / "mapping_unsorted_SE/{sample}_{rn}.contamination.bam"),
159 |         unmapped=temp(TEMPDIR / "mapping_discarded_SE/{sample}_{rn}.contamination.bam"),
160 |         summary="report_reads/mapping/{sample}_{rn}.contamination.summary",
161 |     params:
162 |         index=REF["contamination"]["hisat3n"],
163 |     threads: 24
164 |     shell:
165 |         """
166 |         {BIN[hisat3n]} --index {params.index} -p {threads} --summary-file {output.summary} --new-summary -q -U {input[0]} --directional-mapping --base-change C,T --mp 8,2 --no-spliced-alignment | \
167 |             {BIN[samtools]} view -@ {threads} -e '!flag.unmap' -O BAM -U {output.unmapped} -o {output.mapped}
168 |         """
169 | 
170 | 
171 | rule hisat2_3n_mapping_genes_SE:
172 |     input:
173 |         TEMPDIR / "unmapped_internal_SE/{sample}_{rn}_R1.contamination.fq.gz",
174 |         "prepared_genes/genes.3n.CT.1.ht2" if CUSTOMIZED_GENES else [],
175 |     output:
176 |         mapped=temp(TEMPDIR / "mapping_unsorted_SE/{sample}_{rn}.genes.bam"),
177 |         unmapped=temp(TEMPDIR / "mapping_discarded_SE/{sample}_{rn}.genes.bam"),
178 |         summary="report_reads/mapping/{sample}_{rn}.genes.summary",
179 |     params:
180 |         index=(
181 |             REF["genes"]["hisat3n"] if not CUSTOMIZED_GENES else "prepared_genes/genes"
182 |         ),
183 |     threads: 24
184 |     shell:
185 |         """
186 |         {BIN[hisat3n]} --index {params.index} -p {threads} --summary-file {output.summary} --new-summary -q -U {input[0]} --directional-mapping --all --norc --base-change C,T --mp 8,2 --no-spliced-alignment | \
187 |             {BIN[samtools]} view -@ {threads} -e '!flag.unmap' -O BAM -U {output.unmapped} -o {output.mapped}
188 |         """
189 | 
190 | 
191 | rule hisat2_3n_mapping_genome_SE:
192 |     input:
193 |         TEMPDIR / "unmapped_internal_SE/{sample}_{rn}_R1.genes.fq.gz",
194 |     output:
195 |         mapped=temp(TEMPDIR / "mapping_unsorted_SE/{sample}_{rn}.genome.bam"),
196 |         unmapped=temp(TEMPDIR / "mapping_discarded_SE/{sample}_{rn}.genome.bam"),
197 |         summary="report_reads/mapping/{sample}_{rn}.genome.summary",
198 |     params:
199 |         index=REF["genome"]["hisat3n"],
200 |     threads: 24
201 |     shell:
202 |         """
203 |         {BIN[hisat3n]} --index {params.index} -p {threads} --summary-file {output.summary} --new-summary -q -U {input[0]} --directional-mapping --base-change C,T --pen-noncansplice 20 --mp 4,1 | \
204 |             {BIN[samtools]} view -@ {threads} -e '!flag.unmap' -O BAM -U {output.unmapped} -o {output.mapped}
205 |         """
206 | 
207 | 
208 | rule extract_unmap_bam_internal_SE:
209 |     input:
210 |         TEMPDIR / "mapping_discarded_SE/{sample}_{rn}.{reftype}.bam",
211 |     output:
212 |         temp(TEMPDIR / "unmapped_internal_SE/{sample}_{rn}_R1.{reftype}.fq.gz"),
213 |     threads: 4
214 |     shell:
215 |         """
216 |         {BIN[samtools]} fastq -@ {threads} -0 {output} {input}
217 |         """
218 | 
219 | 
220 | # Mapping (PE mapping mode)
221 | 
222 | 
223 | rule hisat2_3n_mapping_contamination_PE:
224 |     input:
225 |         TEMPDIR / "cut_adapter_PE/{sample}_{rn}_R1.fq.gz",
226 |         TEMPDIR / "cut_adapter_PE/{sample}_{rn}_R2.fq.gz",
227 |     output:
228 |         mapped=temp(TEMPDIR / "mapping_unsorted_PE/{sample}_{rn}.contamination.bam"),
229 |         unmapped=temp(TEMPDIR / "mapping_discarded_PE/{sample}_{rn}.contamination.bam"),
230 |         summary="report_reads/mapping/{sample}_{rn}.contamination.summary",
231 |     params:
232 |         index=REF["contamination"]["hisat3n"],
233 |     threads: 24
234 |     shell:
235 |         """
236 |         {BIN[hisat3n]} --index {params.index} -p {threads} --summary-file {output.summary} --new-summary -q -1 {input[0]} -2 {input[1]} --directional-mapping --base-change C,T --mp 8,2 --no-spliced-alignment | \
237 |             {BIN[samtools]} view -@ {threads} -e 'flag.proper_pair && !flag.unmap && !flag.munmap' -O BAM -U {output.unmapped} -o {output.mapped}
238 |         """
239 | 
240 | 
241 | rule hisat2_3n_mapping_genes_PE:
242 |     input:
243 |         TEMPDIR / "unmapped_internal_PE/{sample}_{rn}_R1.contamination.fq.gz",
244 |         TEMPDIR / "unmapped_internal_PE/{sample}_{rn}_R2.contamination.fq.gz",
245 |         "prepared_genes/genes.3n.CT.1.ht2" if CUSTOMIZED_GENES else [],
246 |     output:
247 |         mapped=temp(TEMPDIR / "mapping_unsorted_PE/{sample}_{rn}.genes.bam"),
248 |         unmapped=temp(TEMPDIR / "mapping_discarded_PE/{sample}_{rn}.genes.bam"),
249 |         summary="report_reads/mapping/{sample}_{rn}.genes.summary",
250 |     params:
251 |         index=(
252 |             REF["genes"]["hisat3n"] if not CUSTOMIZED_GENES else "prepared_genes/genes"
253 |         ),
254 |     threads: 24
255 |     shell:
256 |         """
257 |         {BIN[hisat3n]} --index {params.index} -p {threads} --summary-file {output.summary} --new-summary -q -1 {input[0]} -2 {input[1]} --directional-mapping --all --norc --base-change C,T --mp 8,2 --no-spliced-alignment | \
258 |             {BIN[samtools]} view -@ {threads} -e 'flag.proper_pair && !flag.unmap && !flag.munmap' -O BAM -U {output.unmapped} -o {output.mapped}
259 |         """
260 | 
261 | 
262 | rule hisat2_3n_mapping_genome_PE:
263 |     input:
264 |         TEMPDIR / "unmapped_internal_PE/{sample}_{rn}_R1.genes.fq.gz",
265 |         TEMPDIR / "unmapped_internal_PE/{sample}_{rn}_R2.genes.fq.gz",
266 |     output:
267 |         mapped=temp(TEMPDIR / "mapping_unsorted_PE/{sample}_{rn}.genome.bam"),
268 |         unmapped=temp(TEMPDIR / "mapping_discarded_PE/{sample}_{rn}.genome.bam"),
269 |         summary="report_reads/mapping/{sample}_{rn}.genome.summary",
270 |     params:
271 |         index=REF["genome"]["hisat3n"],
272 |     threads: 24
273 |     shell:
274 |         """
275 |         {BIN[hisat3n]} --index {params.index} -p {threads} --summary-file {output.summary} --new-summary -q -1 {input[0]} -2 {input[1]} --directional-mapping --base-change C,T --pen-noncansplice 20 --mp 4,1 | \
276 |             {BIN[samtools]} view -@ {threads} -e 'flag.proper_pair && !flag.unmap && !flag.munmap' -O BAM -U {output.unmapped} -o {output.mapped}
277 |         """
278 | 
279 | 
280 | rule extract_unmap_bam_internal_PE:
281 |     input:
282 |         TEMPDIR / "mapping_discarded_PE/{sample}_{rn}.{reftype}.bam",
283 |     output:
284 |         r1=temp(TEMPDIR / "unmapped_internal_PE/{sample}_{rn}_R1.{reftype}.fq.gz"),
285 |         r2=temp(TEMPDIR / "unmapped_internal_PE/{sample}_{rn}_R2.{reftype}.fq.gz"),
286 |     threads: 4
287 |     shell:
288 |         """
289 |         {BIN[samtools]} fastq -@ {threads} -1 {output.r1} -2 {output.r2} -0 /dev/null -s /dev/null -n {input}
290 |         """
291 | 
292 | 
293 | ruleorder: extract_unmap_bam_final_PE > extract_unmap_bam_final_SE
294 | 
295 | 
296 | rule extract_unmap_bam_final_SE:
297 |     input:
298 |         r1=TEMPDIR / "unmapped_internal_SE/{sample}_{rn}_R1.genome.fq.gz",
299 |     output:
300 |         r1=INTERNALDIR / "discarded_reads/{sample}_{rn}_R1.unmapped.fq.gz",
301 |     threads: 4
302 |     shell:
303 |         """
304 |         mv {input.r1} {output.r1}
305 |         """
306 | 
307 | 
308 | rule extract_unmap_bam_final_PE:
309 |     input:
310 |         r1=TEMPDIR / "unmapped_internal_PE/{sample}_{rn}_R1.genome.fq.gz",
311 |         r2=TEMPDIR / "unmapped_internal_PE/{sample}_{rn}_R2.genome.fq.gz",
312 |     output:
313 |         r1=INTERNALDIR / "discarded_reads/{sample}_{rn}_R1.unmapped.fq.gz",
314 |         r2=INTERNALDIR / "discarded_reads/{sample}_{rn}_R2.unmapped.fq.gz",
315 |     threads: 4
316 |     shell:
317 |         """
318 |         mv {input.r1} {output.r1}
319 |         mv {input.r2} {output.r2}
320 |         """
321 | 
322 | 
323 | rule hisat2_3n_sort:
324 |     input:
325 |         lambda wildcards: TEMPDIR
326 |         / (
327 |             "mapping_unsorted_SE/{sample}_{rn}.{ref}.bam"
328 |             if len(SAMPLE2DATA[wildcards.sample][wildcards.rn]) == 1
329 |             else "mapping_unsorted_PE/{sample}_{rn}.{ref}.bam"
330 |         ),
331 |     output:
332 |         INTERNALDIR / "run_sorted/{sample}_{rn}.{ref}.bam",
333 |     threads: 16
334 |     shell:
335 |         """
336 |         {BIN[samtools]} sort -@ {threads} --write-index -m 3G -O BAM -o {output} {input}
337 |         """
338 | 
339 | 
340 | # combine mapping results (multi run)
341 | 
342 | 
343 | rule combine_runs:
344 |     input:
345 |         lambda wildcards: [
346 |             INTERNALDIR / f"run_sorted/{wildcards.sample}_{r}.{wildcards.ref}.bam"
347 |             for r in SAMPLE2DATA[wildcards.sample]
348 |         ],
349 |     output:
350 |         temp(TEMPDIR / "combined_mapping/{sample}.{ref}.bam"),
351 |     params:
352 |         path_samtools=config["path"]["samtools"],
353 |     threads: 8
354 |     shell:
355 |         "{params.path_samtools} merge -@ {threads} -o {output} {input}"
356 | 
357 | 
358 | rule stat_mapping_number:
359 |     input:
360 |         bam=lambda wildcards: [
361 |             TEMPDIR / f"combined_mapping/{wildcards.sample}.{ref}.bam"
362 |             for ref in ["contamination", "genes", "genome"]
363 |         ],
364 |     output:
365 |         tsv="report_reads/mapped/{sample}.tsv",
366 |     params:
367 |         refs=["contamination", "genes", "genome"],
368 |     threads: 4
369 |     shell:
370 |         """
371 |         paste <(echo {params.refs} |  tr " " "\\n") <(echo {input.bam} |  tr " " "\\n") | while read ref file; do
372 |             {BIN[samtools]} view -@ {threads} -F 3980 -c $file | awk -v ref="$ref" '{{FS="\\t";OFS="\\t"}}NR==1{{print ref,$1}}' >> {output}
373 |         done
374 |         """
375 | 
376 | 
377 | rule dedup_mapping:
378 |     input:
379 |         bam=TEMPDIR / "combined_mapping/{sample}.{ref}.bam",
380 |     output:
381 |         bam=INTERNALDIR / "aligned_bam/{sample}.{ref}.bam",
382 |         txt="report_reads/dedup/{sample}.{ref}.log",
383 |     params:
384 |         tmp=os.environ["TMPDIR"],
385 |     threads: 20
386 |     run:
387 |         if WITH_UMI:
388 |             shell(
389 |                 """
390 |             /software/java-15.0.2-el8-x86_64/bin/java -server -Xms8G -Xmx40G -Xss100M -Djava.io.tmpdir={params.tmp} -jar {BIN[umicollapse]} bam \
391 |                 -t 2 -T {threads} --data naive --merge avgqual --two-pass -i {input.bam} -o {output.bam} >{output.txt}
392 |             """
393 |             )
394 |         elif MARKDUP:
395 |             shell(
396 |                 """
397 |                 ~/tools/jdk8u322-b06-jre/bin/java -Xmx36G -jar ~/tools/gatk-4.2.5.0/gatk-package-4.2.5.0-local.jar MarkDuplicates \
398 |                     -I {input} -O {output.bam} -M {output.txt} --DUPLICATE_SCORING_STRATEGY SUM_OF_BASE_QUALITIES --REMOVE_DUPLICATES true --VALIDATION_STRINGENCY SILENT --TMP_DIR {params.tmp}
399 |             """
400 |             )
401 |         else:
402 |             shell(
403 |                 """
404 |                 cp {input.bam} {output.bam}
405 |                 touch {output.txt}
406 |             """
407 |             )
408 | 
409 | 
410 | rule dedup_index:
411 |     input:
412 |         bam=INTERNALDIR / "aligned_bam/{sample}.{ref}.bam",
413 |     output:
414 |         bai=INTERNALDIR / "aligned_bam/{sample}.{ref}.bam.bai",
415 |     threads: 6
416 |     shell:
417 |         """
418 |         {BIN[samtools]} index -@ {threads} {input}
419 |         """
420 | 
421 | 
422 | # call mutation
423 | 
424 | 
425 | rule hisat2_3n_calling_unfiltered_unique:
426 |     input:
427 |         INTERNALDIR / "aligned_bam/{sample}.{ref}.bam",
428 |     output:
429 |         temp(TEMPDIR / "unfiltered_unique/{sample}.{ref}.tsv.gz"),
430 |     params:
431 |         fa=lambda wildcards: (
432 |             REF[wildcards.ref]["fa"]
433 |             if wildcards.ref != "genes" or not CUSTOMIZED_GENES
434 |             else "prepared_genes/genes.fa"
435 |         ),
436 |     threads: 16
437 |     shell:
438 |         """
439 |         {BIN[samtools]} view -e "rlen<100000" -h {input} | {BIN[hisat3ntable]} -p {threads} -u --alignments - --ref {params.fa} --output-name /dev/stdout --base-change C,T | cut -f 1,2,3,5,7 | bgzip -@ {threads} -c > {output}
440 |         """
441 | 
442 | 
443 | rule hisat2_3n_calling_unfiltered_multi:
444 |     input:
445 |         INTERNALDIR / "aligned_bam/{sample}.{ref}.bam",
446 |     output:
447 |         temp(TEMPDIR / "unfiltered_multi/{sample}.{ref}.tsv.gz"),
448 |     params:
449 |         fa=lambda wildcards: (
450 |             REF[wildcards.ref]["fa"]
451 |             if wildcards.ref != "genes" or not CUSTOMIZED_GENES
452 |             else "prepared_genes/genes.fa"
453 |         ),
454 |     threads: 16
455 |     shell:
456 |         """
457 |         {BIN[samtools]} view -e "rlen<100000" -h {input} | {BIN[hisat3ntable]} -p {threads} -m --alignments - --ref {params.fa} --output-name /dev/stdout --base-change C,T | cut -f 1,2,3,5,7 | bgzip -@ {threads} -c > {output}
458 |         """
459 | 
460 | 
461 | rule hisat2_3n_filtering:
462 |     input:
463 |         INTERNALDIR / "aligned_bam/{sample}.{ref}.bam",
464 |     output:
465 |         temp(TEMPDIR / "hisat_converted/{sample}.{ref}.bam"),
466 |     threads: 4
467 |     shell:
468 |         """
469 |         {BIN[samtools]} view -@ {threads} -e "[XM] * 20 <= (qlen-sclen) && [Zf] <= 3 && 3 * [Zf] <= [Zf] + [Yf]" {input} -O BAM -o {output}
470 |         """
471 | 
472 | 
473 | rule hisat2_3n_calling_filtered_unqiue:
474 |     input:
475 |         TEMPDIR / "hisat_converted/{sample}.{ref}.bam",
476 |     output:
477 |         temp(TEMPDIR / "filtered_unique/{sample}.{ref}.tsv.gz"),
478 |     params:
479 |         fa=lambda wildcards: (
480 |             REF[wildcards.ref]["fa"]
481 |             if wildcards.ref != "genes" or not CUSTOMIZED_GENES
482 |             else "prepared_genes/genes.fa"
483 |         ),
484 |     threads: 16
485 |     shell:
486 |         """
487 |         {BIN[samtools]} view -e "rlen<100000" -h {input} | {BIN[hisat3ntable]} -p {threads} -u --alignments - --ref {params.fa} --output-name /dev/stdout --base-change C,T | cut -f 1,2,3,5,7 | bgzip -@ {threads} -c > {output}
488 |         """
489 | 
490 | 
491 | rule hisat2_3n_calling_filtered_multi:
492 |     input:
493 |         TEMPDIR / "hisat_converted/{sample}.{ref}.bam",
494 |     output:
495 |         temp(TEMPDIR / "filtered_multi/{sample}.{ref}.tsv.gz"),
496 |     params:
497 |         fa=lambda wildcards: (
498 |             REF[wildcards.ref]["fa"]
499 |             if wildcards.ref != "genes" or not CUSTOMIZED_GENES
500 |             else "prepared_genes/genes.fa"
501 |         ),
502 |     threads: 16
503 |     shell:
504 |         """
505 |         {BIN[samtools]} view -e "rlen<100000" -h {input} | {BIN[hisat3ntable]} -p {threads} -m --alignments - --ref {params.fa} --output-name /dev/stdout --base-change C,T | cut -f 1,2,3,5,7 | bgzip -@ {threads} -c > {output}
506 |         """
507 | 
508 | 
509 | rule join_pileup:
510 |     input:
511 |         lambda wildcards: [
512 |             TEMPDIR / f"{t}/{wildcards.sample}.{wildcards.ref}.tsv.gz"
513 |             for t in [
514 |                 "unfiltered_unique",
515 |                 "unfiltered_multi",
516 |                 "filtered_unique",
517 |                 "filtered_multi",
518 |             ]
519 |         ],
520 |     output:
521 |         INTERNALDIR / "count_sites/{sample}.{ref}.arrow",
522 |     threads: 6
523 |     shell:
524 |         """
525 |         {BIN[join_pileup.py]} -i {input} -o {output}
526 |         """
527 | 
528 | 
529 | rule group_pileup:
530 |     input:
531 |         lambda wildcards: [
532 |             INTERNALDIR / f"count_sites/{sample}.{wildcards.ref}.arrow"
533 |             for sample in GROUP2SAMPLE[wildcards.group]
534 |         ],
535 |     output:
536 |         INTERNALDIR / "group_sites/{group}.{ref}.arrow",
537 |     threads: 6
538 |     shell:
539 |         """
540 |         {BIN[group_pileup.py]} -i {input} -o {output}
541 |         """
542 | 
543 | 
544 | rule combined_select_sites:
545 |     input:
546 |         expand(
547 |             INTERNALDIR / "group_sites/{group}.{{ref}}.arrow",
548 |             group=GROUP2SAMPLE.keys(),
549 |         ),
550 |     output:
551 |         "detected_sites/prefilter/{ref}.tsv",
552 |     shell:
553 |         """
554 |         {BIN[select_sites.py]} -i {input} -o {output}
555 |         """
556 | 
557 | 
558 | rule stat_sample_background:
559 |     input:
560 |         site=INTERNALDIR / "count_sites/{sample}.{ref}.arrow",
561 |         mask="detected_sites/prefilter/{ref}.tsv",
562 |     output:
563 |         background="detected_sites/background/{sample}.{ref}.tsv",
564 |         filtered="detected_sites/filtered/{sample}.{ref}.tsv",
565 |     threads: 2
566 |     shell:
567 |         """
568 |         {BIN[filter_sites.py]} -i {input.site} -m {input.mask} -b {output.background} -o {output.filtered}
569 |         """
570 | 


--------------------------------------------------------------------------------
/bin/filter_sites.py:
--------------------------------------------------------------------------------
 1 | #!/usr/bin/env python
 2 | # -*- coding: utf-8 -*-
 3 | #
 4 | # Copyright © 2021 Ye Chang yech1990@gmail.com
 5 | # Distributed under terms of the MIT license.
 6 | #
 7 | # Created: 2021-10-06 01:53
 8 | 
 9 | 
10 | import argparse
11 | 
12 | import polars as pl
13 | from scipy.stats import binomtest
14 | 
15 | arg_parser = argparse.ArgumentParser()
16 | arg_parser.add_argument("-i", "--input-file", help="Input site file")
17 | arg_parser.add_argument("-m", "--mask-file", help="mask file")
18 | arg_parser.add_argument("-b", "--background-file", help="background file")
19 | arg_parser.add_argument("-o", "--output-file", help="output file")
20 | 
21 | 
22 | args = arg_parser.parse_args()
23 | 
24 | df_site = (
25 |     pl.read_ipc(args.input_file)
26 |     .with_columns(
27 |         u=pl.col("unconvertedBaseCount_filtered_uniq"),
28 |         d=pl.col("convertedBaseCount_filtered_uniq")
29 |         + pl.col("unconvertedBaseCount_filtered_uniq"),
30 |     )
31 |     .with_columns(ur=pl.col("u") / pl.col("d"))
32 | )
33 | 
34 | df_pre = pl.read_csv(
35 |     args.mask_file,
36 |     separator="\t",
37 |     has_header=False,
38 |     new_columns=["ref", "pos", "strand"],
39 |     dtypes={"ref": pl.Utf8, "pos": pl.Int64, "strand": pl.Utf8},
40 | )
41 | 
42 | bg_ratio = (
43 |     df_site.join(df_pre, on=["ref", "pos", "strand"], how="anti")
44 |     .get_column("ur")
45 |     .drop_nans()
46 |     .mean()
47 | )
48 | with open(args.background_file, "w") as f:
49 |     f.write(f"{bg_ratio}\n")
50 | 
51 | 
52 | def testp(successes, trials, p):
53 |     if successes == 0 or trials == 0:
54 |         return 1.0
55 |     return binomtest(successes, trials, p, alternative="greater").pvalue
56 | 
57 | 
58 | df_filter = (
59 |     df_pre.join(df_site, on=["ref", "pos", "strand"], how="left")
60 |     .with_columns(pl.col("u").fill_null(strategy="zero"))
61 |     .with_columns(pl.col("d").fill_null(strategy="zero"))
62 |     .select(["ref", "pos", "strand", "u", "d", "ur"])
63 |     .with_columns(
64 |         pval=pl.struct(["u", "d"]).map_elements(
65 |             lambda x: testp(x["u"], x["d"], bg_ratio)
66 |         )
67 |     )
68 |     .with_columns(
69 |         passed=(pl.col("pval") < 0.001)
70 |         & (pl.col("u") >= 2)
71 |         & (pl.col("d") >= 10)
72 |         & (pl.col("ur") > 0.02)
73 |     )
74 | )
75 | 
76 | 
77 | df_filter.write_csv(args.output_file, separator="\t", include_header=True)
78 | 


--------------------------------------------------------------------------------
/bin/group_pileup.py:
--------------------------------------------------------------------------------
  1 | #!/usr/bin/env python
  2 | # -*- coding: utf-8 -*-
  3 | #
  4 | # Copyright © 2024 Ye Chang yech1990@gmail.com
  5 | # Distributed under terms of the GNU license.
  6 | #
  7 | # Created: 2024-02-09 13:41
  8 | 
  9 | 
 10 | import polars as pl
 11 | 
 12 | 
 13 | def import_df(file_name, suffix):
 14 |     count_cols = [
 15 |         "convertedBaseCount_unfiltered_uniq",
 16 |         "unconvertedBaseCount_unfiltered_uniq",
 17 |         "convertedBaseCount_unfiltered_multi",
 18 |         "unconvertedBaseCount_unfiltered_multi",
 19 |         "convertedBaseCount_filtered_uniq",
 20 |         "unconvertedBaseCount_filtered_uniq",
 21 |         "convertedBaseCount_filtered_multi",
 22 |         "unconvertedBaseCount_filtered_multi",
 23 |     ]
 24 |     df = pl.read_ipc(file_name).rename({col: col + "_" + suffix for col in count_cols})
 25 |     return df
 26 | 
 27 | 
 28 | def combine_files(*files):
 29 |     samples = [f.split("/")[-1].rsplit(".", 2)[0] for f in files]
 30 |     f = files[0]
 31 |     s = samples[0]
 32 |     df_com = import_df(f, s)
 33 |     for f, s in zip(files[1:], samples[1:]):
 34 |         df = import_df(f, s)
 35 |         df_com = df_com.join(df, on=["ref", "pos", "strand"], how="outer_coalesce")
 36 | 
 37 |     df_com = (
 38 |         df_com.with_columns(
 39 |             u=pl.sum_horizontal(
 40 |                 f"unconvertedBaseCount_filtered_uniq_{s}" for s in samples
 41 |             ),
 42 |             d=pl.sum_horizontal(
 43 |                 f"{t}_filtered_uniq_{s}"
 44 |                 for s in samples
 45 |                 for t in ["convertedBaseCount", "unconvertedBaseCount"]
 46 |             ),
 47 |             _t=pl.sum_horizontal(
 48 |                 f"{t1}_unfiltered_{t2}_{s}"
 49 |                 for s in samples
 50 |                 for t1 in ["convertedBaseCount", "unconvertedBaseCount"]
 51 |                 for t2 in ["uniq", "multi"]
 52 |             ),
 53 |         )
 54 |         .with_columns(
 55 |             # ur: unconverted ratio
 56 |             ur=pl.col("u") / pl.col("d"),
 57 |             # mr: multiple mapping ratio
 58 |             mr=pl.sum_horizontal(
 59 |                 f"{t}_unfiltered_multi_{s}"
 60 |                 for s in samples
 61 |                 for t in ["convertedBaseCount", "unconvertedBaseCount"]
 62 |             )
 63 |             / pl.col("_t"),
 64 |             # cr: cluster ratio
 65 |             cr=1
 66 |             - pl.sum_horizontal(
 67 |                 f"{t1}_filtered_{t2}_{s}"
 68 |                 for s in samples
 69 |                 for t1 in ["convertedBaseCount", "unconvertedBaseCount"]
 70 |                 for t2 in ["uniq", "multi"]
 71 |             )
 72 |             / pl.col("_t"),
 73 |         )
 74 |         .with_columns(
 75 |             [
 76 |                 pl.col(f"unconvertedBaseCount_filtered_uniq_{s}").alias(f"u_{s}")
 77 |                 for s in samples
 78 |             ]
 79 |             + [
 80 |                 (
 81 |                     pl.col(f"unconvertedBaseCount_filtered_uniq_{s}")
 82 |                     + pl.col(f"convertedBaseCount_filtered_uniq_{s}")
 83 |                 ).alias(f"d_{s}")
 84 |                 for s in samples
 85 |             ]
 86 |         )
 87 |         .select(
 88 |             ["ref", "pos", "strand", "u", "d", "ur", "mr", "cr"]
 89 |             + [f"{t}_{s}" for s in samples for t in ["u", "d"]]
 90 |         )
 91 |         .fill_null(0)
 92 |     )
 93 | 
 94 |     return df_com
 95 | 
 96 | 
 97 | if __name__ == "__main__":
 98 |     import argparse
 99 | 
100 |     arg_parser = argparse.ArgumentParser()
101 |     arg_parser.add_argument(
102 |         "-i",
103 |         "--input-files",
104 |         nargs="+",
105 |         required=True,
106 |         help="Multiple input files to be combined",
107 |     )
108 |     arg_parser.add_argument("-o", "--output-file", help="output file")
109 |     args = arg_parser.parse_args()
110 | 
111 |     # Write the combined DataFrame to a CSV file
112 |     combine_files(*args.input_files).write_ipc(args.output_file, compression="lz4")
113 | 


--------------------------------------------------------------------------------
/bin/join_pileup.py:
--------------------------------------------------------------------------------
 1 | #!/usr/bin/env python
 2 | # -*- coding: utf-8 -*-
 3 | #
 4 | # Copyright © 2024 Ye Chang yech1990@gmail.com
 5 | # Distributed under terms of the GNU license.
 6 | #
 7 | # Created: 2024-02-09 13:41
 8 | 
 9 | 
10 | import polars as pl
11 | 
12 | 
13 | def import_df(file_name, suffix):
14 |     df = pl.read_csv(
15 |         file_name,
16 |         separator="\t",
17 |         columns=["ref", "pos", "strand", "convertedBaseCount", "unconvertedBaseCount"],
18 |         dtypes={
19 |             "ref": pl.Utf8,
20 |             "pos": pl.Int64,
21 |             "strand": pl.Utf8,
22 |             "convertedBaseCount": pl.Int64,
23 |             "unconvertedBaseCount": pl.Int64,
24 |         },
25 |     )
26 |     df = df.rename(
27 |         {
28 |             "convertedBaseCount": "convertedBaseCount_" + suffix,
29 |             "unconvertedBaseCount": "unconvertedBaseCount_" + suffix,
30 |         }
31 |     )
32 |     return df
33 | 
34 | 
35 | def combine_files(*files):
36 |     suffixes = [
37 |         "unfiltered_uniq",
38 |         "unfiltered_multi",
39 |         "filtered_uniq",
40 |         "filtered_multi",
41 |     ]
42 |     f = files[0]
43 |     s = suffixes[0]
44 |     df_com = import_df(f, s)
45 |     for f, s in zip(files[1:], suffixes[1:]):
46 |         df = import_df(f, s)
47 |         df_com = df_com.join(df, on=["ref", "pos", "strand"], how="outer_coalesce")
48 |     return df_com.fill_null(0)
49 | 
50 | 
51 | if __name__ == "__main__":
52 |     import argparse
53 | 
54 |     arg_parser = argparse.ArgumentParser()
55 |     arg_parser.add_argument(
56 |         "-i",
57 |         "--input-files",
58 |         nargs=4,
59 |         required=True,
60 |         help="4 input files: unfiltered_uniq, unfiltered_multi, filtered_uniq, filtered_multi",
61 |     )
62 |     arg_parser.add_argument("-o", "--output-file", help="output file")
63 |     args = arg_parser.parse_args()
64 | 
65 |     # Write the combined DataFrame to a CSV file
66 |     combine_files(*args.input_files).write_ipc(args.output_file, compression="lz4")
67 | 


--------------------------------------------------------------------------------
/bin/select_sites.py:
--------------------------------------------------------------------------------
 1 | #!/usr/bin/env python
 2 | # -*- coding: utf-8 -*-
 3 | #
 4 | # Copyright © 2021 Ye Chang yech1990@gmail.com
 5 | # Distributed under terms of the MIT license.
 6 | #
 7 | # Created: 2021-10-06 01:53
 8 | 
 9 | """pre-filter sites.
10 | 
11 | - V3: select sites with both unique and multi mapped reads.
12 |       change pandas into polars to speed up.
13 | - V4: read combined file directly.
14 | """
15 | 
16 | import argparse
17 | import sys
18 | 
19 | import polars as pl
20 | 
21 | arg_parser = argparse.ArgumentParser()
22 | arg_parser.add_argument(
23 |     "-i",
24 |     "--input-files",
25 |     nargs="+",
26 |     required=True,
27 |     help="Multiple input files to be combined",
28 | )
29 | arg_parser.add_argument("-o", "--output-file", help="output file")
30 | 
31 | args = arg_parser.parse_args()
32 | 
33 | TOTAL_DEPTH = 20
34 | TOTAL_SUPPORT = 3
35 | AVERAGE_UNC_RATIO = 0.02
36 | AVERAGE_CLU_RATIO = 0.5
37 | AVERAGE_MUL_RATIO = 0.2
38 | 
39 | 
40 | dfs = []
41 | for f in args.input_files:
42 |     df = (
43 |         pl.read_ipc(f)
44 |         .filter(
45 |             (pl.col("d") >= TOTAL_DEPTH)
46 |             & (pl.col("u") >= TOTAL_SUPPORT)
47 |             & (pl.col("ur") >= AVERAGE_UNC_RATIO)
48 |             & (pl.col("cr") < AVERAGE_CLU_RATIO)
49 |             & (pl.col("mr") < AVERAGE_MUL_RATIO)
50 |         )
51 |         .select(["ref", "pos", "strand"])
52 |     )
53 |     print(f"Read data for {f}...", file=sys.stderr)
54 |     dfs.append(df)
55 | 
56 | pl.concat(dfs, how="vertical").unique(maintain_order=True).write_csv(
57 |     args.output_file, separator="\t", include_header=False
58 | )
59 | 


--------------------------------------------------------------------------------
/config.yaml:
--------------------------------------------------------------------------------
 1 | # tools and scripts
 2 | path:
 3 |   samtools: /path/to/samtools
 4 |   hisat3n: /path/to/hisat-3n
 5 |   hisat3ntable: /path/to/hisat-3n-table
 6 |   join_pileup.py: ../bin/join_pileup.py
 7 |   group_pileup.py: ../bin/group_pileup.py
 8 |   select_sites.py: ../bin/select_sites.py
 9 |   filter_sites.py: ../bin/filter_sites.py
10 | 
11 | # global config
12 | #
13 | # prepare genes index
14 | # premap to rRNA, tRNA and other small RNA
15 | # If study virus, then also premap to virus genome
16 | # customized_genes:
17 | #   - a.fa
18 | #   - b.fa
19 | # library: INLINE
20 | # makedup: false
21 | 
22 | # reference genome and index
23 | reference:
24 |   contamination:
25 |     fa: ~/reference/genome/contamination/contamination.fa
26 |     hisat3n: ~/reference/index/hisat3n/contamination/contamination
27 |   genes:
28 |     fa: ~/reference/genome/Homo_sapiens.GRCh38.sncRNA.fa
29 |     hisat3n: ~/reference/index/hisat3n/Homo_sapiens.GRCh38.sncRNA/Homo_sapiens.GRCh38.sncRNA
30 |   genome:
31 |     fa: ~/reference/genome/Homo_sapiens.GRCh38.genome.fa
32 |     hisat3n: ~/reference/index/hisat3n/Homo_sapiens.GRCh38.genome/Homo_sapiens.GRCh38.genome
33 | 
34 | # Sample name should be indentical and listed in the 2nd level of the yaml file
35 | # Each sample will be analysis seperately, but
36 | # samples sharing the same group id will be regared as biological replicates and combined in the comparing step
37 | samples:
38 |   CONTROL-rep1:
39 |     data:
40 |       - R1: ../data/test1_R1.fq.gz
41 |         R2: ../data/test1_R2.fq.gz
42 |     group: CONTROL
43 |   DRUG-rep1:
44 |     data:
45 |       - R1: ../data/test2_R1.fq.gz
46 |     group: DRUG
47 |   DRUG-rep2:
48 |     data:
49 |       - R1: ../data/test3_R1.fq.gz
50 |         R2: ../data/test3_R2.fq.gz
51 |     group: DRUG
52 | 


--------------------------------------------------------------------------------
/data/test1_R1.fq.gz:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/y9c/m5C-UBSseq/9f5e719edba39ac0ae0b74ec126ec7f8fe6de2bf/data/test1_R1.fq.gz


--------------------------------------------------------------------------------
/data/test1_R2.fq.gz:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/y9c/m5C-UBSseq/9f5e719edba39ac0ae0b74ec126ec7f8fe6de2bf/data/test1_R2.fq.gz


--------------------------------------------------------------------------------
/data/test2_R1.fq.gz:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/y9c/m5C-UBSseq/9f5e719edba39ac0ae0b74ec126ec7f8fe6de2bf/data/test2_R1.fq.gz


--------------------------------------------------------------------------------
/data/test2_R2.fq.gz:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/y9c/m5C-UBSseq/9f5e719edba39ac0ae0b74ec126ec7f8fe6de2bf/data/test2_R2.fq.gz


--------------------------------------------------------------------------------
/data/test3_R1.fq.gz:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/y9c/m5C-UBSseq/9f5e719edba39ac0ae0b74ec126ec7f8fe6de2bf/data/test3_R1.fq.gz


--------------------------------------------------------------------------------
/data/test3_R2.fq.gz:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/y9c/m5C-UBSseq/9f5e719edba39ac0ae0b74ec126ec7f8fe6de2bf/data/test3_R2.fq.gz


--------------------------------------------------------------------------------
/docs/flow.svg:
--------------------------------------------------------------------------------
  1 | <?xml version="1.0" encoding="utf-8"?>
  2 | <!-- Generator: Adobe Illustrator 27.2.0, SVG Export Plug-In . SVG Version: 6.00 Build 0)  -->
  3 | <svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
  4 | 	 viewBox="0 0 1353 980" style="enable-background:new 0 0 1353 980;" xml:space="preserve">
  5 | <style type="text/css">
  6 | 	.st0{fill:none;stroke:#567BD8;stroke-width:3;}
  7 | 	.st1{fill:#777777;}
  8 | 	.st2{font-family:'TimesNewRomanPSMT';}
  9 | 	.st3{font-size:18px;}
 10 | 	.st4{opacity:0.21;fill:#CC9900;stroke:#FFFFFF;stroke-width:3;}
 11 | 	.st5{fill:none;stroke:#C0C0C0;stroke-width:3;}
 12 | 	.st6{fill:#C0C0C0;stroke:#C0C0C0;stroke-width:3;}
 13 | 	.st7{fill:none;stroke:#99FF33;stroke-width:3;}
 14 | 	.st8{fill:none;stroke:#33CCFF;stroke-width:3;}
 15 | </style>
 16 | <path class="st0" d="M596.5,940h-30c-6,0-12,6-12,12v12c0,6,6,12,12,12h30c6,0,12-6,12-12v-12C608.5,946,602.5,940,596.5,940"/>
 17 | <text transform="matrix(1 0 0 1 557.7539 963.633)" class="st1 st2 st3">results</text>
 18 | <path class="st4" d="M490,652H337c-6,0-12,6-12,12v12c0,6,6,12,12,12H490c6,0,12-6,12-12v-12C502,658,496,652,490,652"/>
 19 | <text transform="matrix(1 0 0 1 333.0148 675.4)" class="st1 st2 st3">stat_mapping_number</text>
 20 | <path class="st5" d="M417.8,688c10.5,41.5,40.8,145.6,94.7,216c9.2,12,21.5,22.7,33.3,31.5"/>
 21 | <polygon class="st6" points="548.1,932.8 554.2,941.4 544,938.5 "/>
 22 | <path class="st4" d="M733.5,364h-94c-6,0-12,6-12,12v12c0,6,6,12,12,12h94c6,0,12-6,12-12v-12C745.5,370,739.5,364,733.5,364"/>
 23 | <text transform="matrix(1 0 0 1 635.5109 387.4)" class="st1 st2 st3">combine_runs</text>
 24 | <path class="st5" d="M627.2,392.2c-89.9,19.1-258,69.3-330.7,187.8c-8.4,13.6-8.6,22.5,0,36c8.7,13.6,21.8,23.8,36,31.5"/>
 25 | <polygon class="st6" points="334.1,644.3 341.6,651.9 331.1,650.6 "/>
 26 | <path class="st4" d="M747.5,436h-108c-6,0-12,6-12,12v12c0,6,6,12,12,12h108c6,0,12-6,12-12v-12C759.5,442,753.5,436,747.5,436"/>
 27 | <text transform="matrix(1 0 0 1 635.5104 459.4)" class="st1 st2 st3">dedup_mapping</text>
 28 | <path class="st5" d="M688.3,400.2c0.7,7.7,1.6,16.9,2.5,25.4"/>
 29 | <polygon class="st6" points="694.2,425.3 691.7,435.6 687.3,426 "/>
 30 | <path class="st4" d="M735.5,292h-98c-6,0-12,6-12,12v12c0,6,6,12,12,12h98c6,0,12-6,12-12v-12C747.5,298,741.5,292,735.5,292"/>
 31 | <text transform="matrix(1 0 0 1 633.5026 315.4)" class="st1 st2 st3">hisat2_3n_sort</text>
 32 | <path class="st5" d="M686.5,328.2c0,7.7,0,16.9,0,25.4"/>
 33 | <polygon class="st6" points="690,353.6 686.5,363.6 683,353.6 "/>
 34 | <path class="st7" d="M603.5,76H327.5c-6,0-12,6-12,12v12c0,6,6,12,12,12h275.9c6,0,12-6,12-12V88C615.5,82,609.5,76,603.5,76"/>
 35 | <text transform="matrix(1 0 0 1 323.5177 99.4)" class="st1 st2 st3">hisat2_3n_mapping_contamination_PE</text>
 36 | <path class="st5" d="M516.4,112.1c22.4,9.1,48.5,21.3,70.1,35.9c38,25.7,50.4,32.6,74,72c11.5,19.1,18.1,43.5,21.8,62.1"/>
 37 | <polygon class="st6" points="685.7,281.5 684.1,292 678.9,282.8 "/>
 38 | <path class="st7" d="M565.9,148H333.1c-6,0-12,6-12,12v12c0,6,6,12,12,12h232.9c6,0,12-6,12-12v-12C577.9,154,571.9,148,565.9,148"
 39 | 	/>
 40 | <text transform="matrix(1 0 0 1 329.0378 171.4)" class="st1 st2 st3">extract_unmap_bam_internal_PE</text>
 41 | <path class="st5" d="M461.5,112.2c-1.7,7.7-3.7,16.9-5.6,25.4"/>
 42 | <polygon class="st6" points="459.2,138.6 453.6,147.6 452.3,137.1 "/>
 43 | <path class="st7" d="M507,4h-83c-6,0-12,6-12,12v12c0,6,6,12,12,12h83c6,0,12-6,12-12V16C519,10,513,4,507,4"/>
 44 | <text transform="matrix(1 0 0 1 420.0128 27.4)" class="st1 st2 st3">cutadapt_PE</text>
 45 | <path class="st5" d="M465.5,40.2c0,7.7,0,16.9,0,25.4"/>
 46 | <polygon class="st6" points="469,65.6 465.5,75.6 462,65.6 "/>
 47 | <path class="st7" d="M639.5,220H425.5c-6,0-12,6-12,12v12c0,6,6,12,12,12h213.9c6,0,12-6,12-12v-12C651.5,226,645.5,220,639.5,220"
 48 | 	/>
 49 | <text transform="matrix(1 0 0 1 421.5123 243.4)" class="st1 st2 st3">hisat2_3n_mapping_genes_PE</text>
 50 | <path class="st5" d="M571.4,256.2c20.4,9.5,45.6,21.3,67.2,31.4"/>
 51 | <polygon class="st6" points="640.3,284.6 647.9,292 637.4,290.9 "/>
 52 | <path class="st5" d="M517.5,219.8c-9.4-8.9-21.6-19.7-33.2-29.3"/>
 53 | <polygon class="st6" points="481.9,193.2 476.4,184.2 486.4,187.8 "/>
 54 | <path class="st5" d="M464.5,184.2c9.4,8.9,21.6,19.7,33.2,29.3"/>
 55 | <polygon class="st6" points="500.1,210.8 505.6,219.8 495.6,216.2 "/>
 56 | <path class="st7" d="M383.5,220H153.5c-6,0-12,6-12,12v12c0,6,6,12,12,12h229.9c6,0,12-6,12-12v-12C395.5,226,389.5,220,383.5,220"
 57 | 	/>
 58 | <text transform="matrix(1 0 0 1 149.5143 243.4)" class="st1 st2 st3">hisat2_3n_mapping_genome_PE</text>
 59 | <path class="st5" d="M397.9,184.2c-25.4,9.7-55.7,21.7-80.7,32"/>
 60 | <polygon class="st6" points="318.5,219.4 307.9,220 315.8,212.9 "/>
 61 | <path class="st7" d="M226.9,292H16.1c-6,0-12,6-12,12v12c0,6,6,12,12,12h210.9c6,0,12-6,12-12v-12C238.9,298,232.9,292,226.9,292"/>
 62 | <text transform="matrix(1 0 0 1 12.0328 315.4)" class="st1 st2 st3">extract_unmap_bam_final_PE</text>
 63 | <path class="st5" d="M321,172.6c-76.1,6.7-162.5,20.2-188.5,47.4c-15.4,16.1-17.1,41.9-15.6,61.8"/>
 64 | <polygon class="st6" points="120.4,281.5 118,291.8 113.4,282.3 "/>
 65 | <path class="st5" d="M373.2,256c75.6,13,175.6,30.2,242.1,41.7"/>
 66 | <polygon class="st6" points="616,294.3 625.2,299.4 614.8,301.2 "/>
 67 | <path class="st5" d="M319.8,220c25.3-9.7,55.7-21.7,80.7-32"/>
 68 | <polygon class="st6" points="399.2,184.7 409.8,184.2 401.9,191.2 "/>
 69 | <path class="st8" d="M929.5,76H653.5c-6,0-12,6-12,12v12c0,6,6,12,12,12h275.9c6,0,12-6,12-12V88C941.5,82,935.5,76,929.5,76"/>
 70 | <text transform="matrix(1 0 0 1 649.5177 99.4)" class="st1 st2 st3">hisat2_3n_mapping_contamination_SE</text>
 71 | <path class="st5" d="M782.7,112c-18.4,37.9-61.2,125.9-83,170.7"/>
 72 | <polygon class="st6" points="702.8,284.4 695.3,291.9 696.5,281.3 "/>
 73 | <path class="st8" d="M1116.9,148H884.1c-6,0-12,6-12,12v12c0,6,6,12,12,12h232.9c6,0,12-6,12-12v-12
 74 | 	C1128.9,154,1122.9,148,1116.9,148"/>
 75 | <text transform="matrix(1 0 0 1 880.0377 171.4)" class="st1 st2 st3">extract_unmap_bam_internal_SE</text>
 76 | <path class="st5" d="M844,112.1c28.7,9.9,64.4,22.2,94.5,32.6"/>
 77 | <polygon class="st6" points="939.7,141.4 948,147.9 937.4,148 "/>
 78 | <path class="st8" d="M833,4h-83c-6,0-12,6-12,12v12c0,6,6,12,12,12h83c6,0,12-6,12-12V16C845,10,839,4,833,4"/>
 79 | <text transform="matrix(1 0 0 1 746.0128 27.4)" class="st1 st2 st3">cutadapt_SE</text>
 80 | <path class="st5" d="M791.5,40.2c0,7.7,0,16.9,0,25.4"/>
 81 | <polygon class="st6" points="795,65.6 791.5,75.6 788,65.6 "/>
 82 | <path class="st8" d="M971.5,220H757.5c-6,0-12,6-12,12v12c0,6,6,12,12,12h213.9c6,0,12-6,12-12v-12C983.5,226,977.5,220,971.5,220"
 83 | 	/>
 84 | <text transform="matrix(1 0 0 1 753.5123 243.4)" class="st1 st2 st3">hisat2_3n_mapping_genes_SE</text>
 85 | <path class="st5" d="M819.6,256.2c-24,9.7-53.8,21.7-79,32"/>
 86 | <polygon class="st6" points="741.7,291.5 731.1,292 739.1,285 "/>
 87 | <path class="st5" d="M904.8,219.8c18.5-9.3,40.2-20.7,58.3-30.6"/>
 88 | <polygon class="st6" points="961.7,185.9 972.1,184.2 965.1,192.1 "/>
 89 | <path class="st5" d="M960.2,184.2c-18.5,9.3-40.2,20.7-58.3,30.6"/>
 90 | <polygon class="st6" points="903.3,218.1 892.9,219.8 899.9,211.9 "/>
 91 | <path class="st8" d="M1243.5,220h-229.9c-6,0-12,6-12,12v12c0,6,6,12,12,12h229.9c6,0,12-6,12-12v-12
 92 | 	C1255.5,226,1249.5,220,1243.5,220"/>
 93 | <text transform="matrix(1 0 0 1 1009.5143 243.4)" class="st1 st2 st3">hisat2_3n_mapping_genome_SE</text>
 94 | <path class="st5" d="M1026.8,184.2c15.8,9.4,36.1,20.9,54.6,30.9"/>
 95 | <polygon class="st6" points="1083.1,212 1090.3,219.8 1079.8,218.2 "/>
 96 | <path class="st8" d="M1336.9,364h-210.9c-6,0-12,6-12,12v12c0,6,6,12,12,12h210.9c6,0,12-6,12-12v-12
 97 | 	C1348.9,370,1342.9,364,1336.9,364"/>
 98 | <text transform="matrix(1 0 0 1 1122.0328 387.4)" class="st1 st2 st3">extract_unmap_bam_final_SE</text>
 99 | <path class="st5" d="M1129.1,177c58,7.9,117.6,21.1,135.4,43c31.7,38.9,4.7,100.2-15.6,135.2"/>
100 | <polygon class="st6" points="1251.8,357.2 1243.7,363.9 1245.8,353.6 "/>
101 | <path class="st5" d="M1017.8,256c-81.5,13.3-190,30.9-260.2,42.4"/>
102 | <polygon class="st6" points="757.9,301.9 747.5,300.1 756.8,295 "/>
103 | <path class="st5" d="M1102.2,219.8c-15.8-9.4-36.1-20.9-54.6-30.9"/>
104 | <polygon class="st6" points="1045.9,192 1038.8,184.2 1049.2,185.8 "/>
105 | <path class="st5" d="M146.2,328.2c30.5,24.8,78.3,72.2,78.3,125.8c0,0,0,0,0,360c0,68.5,228.6,119.6,319.9,137.3"/>
106 | <polygon class="st6" points="545.2,947.8 554.4,953.1 543.9,954.7 "/>
107 | <path class="st5" d="M1227.1,400.1c-6.2,27.2-16.6,80.2-16.6,125.9c0,0,0,0,0,288c0,122.2-456.5,140.7-591.7,143.5"/>
108 | <polygon class="st6" points="618.6,961 608.5,957.7 618.5,954 "/>
109 | <path class="st4" d="M704,868H533c-6,0-12,6-12,12v12c0,6,6,12,12,12H704c6,0,12-6,12-12v-12C716,874,710,868,704,868"/>
110 | <text transform="matrix(1 0 0 1 529.0236 891.4)" class="st1 st2 st3">stat_sample_background</text>
111 | <path class="st5" d="M609.2,904.2c-4.1,8-9,17.5-13.5,26.3"/>
112 | <polygon class="st6" points="598.6,932.3 591,939.6 592.4,929.1 "/>
113 | <path class="st4" d="M772.5,652h-74c-6,0-12,6-12,12v12c0,6,6,12,12,12h74c6,0,12-6,12-12v-12C784.5,658,778.5,652,772.5,652"/>
114 | <text transform="matrix(1 0 0 1 694.504 675.4)" class="st1 st2 st3">join_pileup</text>
115 | <path class="st5" d="M708.4,688.2c-12.7,9.5-27.3,22.1-37.9,35.8c-30.7,40.1-43.6,98.9-48.8,133.5"/>
116 | <polygon class="st6" points="625.1,858.4 620.3,867.9 618.2,857.5 "/>
117 | <path class="st4" d="M779.5,724h-88c-6,0-12,6-12,12v12c0,6,6,12,12,12h88c6,0,12-6,12-12v-12C791.5,730,785.5,724,779.5,724"/>
118 | <text transform="matrix(1 0 0 1 687.5079 747.4)" class="st1 st2 st3">group_pileup</text>
119 | <path class="st5" d="M735.5,688.2c0,7.7,0,16.9,0,25.4"/>
120 | <polygon class="st6" points="739,713.6 735.5,723.6 732,713.6 "/>
121 | <path class="st4" d="M573.9,580H317.1c-6,0-12,6-12,12v12c0,6,6,12,12,12h256.9c6,0,12-6,12-12v-12C585.9,586,579.9,580,573.9,580"
122 | 	/>
123 | <text transform="matrix(1 0 0 1 313.0319 603.4)" class="st1 st2 st3">hisat2_3n_calling_unfiltered_unique</text>
124 | <path class="st5" d="M518.3,616.1c48.9,12.1,112.6,27.9,158.3,39.3"/>
125 | <polygon class="st6" points="677.5,652 686.4,657.8 675.8,658.8 "/>
126 | <path class="st5" d="M662.3,472.1c-44.8,26-127.5,74-176.8,102.7"/>
127 | <polygon class="st6" points="487.1,577.9 476.7,579.9 483.6,571.8 "/>
128 | <path class="st4" d="M1133.5,508H887.5c-6,0-12,6-12,12v12c0,6,6,12,12,12h245.9c6,0,12-6,12-12v-12
129 | 	C1145.5,514,1139.5,508,1133.5,508"/>
130 | <text transform="matrix(1 0 0 1 883.525 531.4)" class="st1 st2 st3">hisat2_3n_calling_unfiltered_multi</text>
131 | <path class="st5" d="M759.6,469c46.9,10.6,110.3,25.1,161.7,36.7"/>
132 | <polygon class="st6" points="922.1,502.3 931.1,508 920.5,509.2 "/>
133 | <path class="st4" d="M800,508H671c-6,0-12,6-12,12v12c0,6,6,12,12,12h129c6,0,12-6,12-12v-12C812,514,806,508,800,508"/>
134 | <text transform="matrix(1 0 0 1 667.0118 531.4)" class="st1 st2 st3">hisat2_3n_filtering</text>
135 | <path class="st5" d="M704.1,472.2c4.7,8,10.3,17.7,15.5,26.5"/>
136 | <polygon class="st6" points="722.7,497.2 724.8,507.6 716.7,500.7 "/>
137 | <path class="st5" d="M1098.8,544.1c18.4,8,35.5,19.4,46.7,35.9c9,13.2,10.5,24,0,36c-22.8,26-242.7,43.4-350.7,50.5"/>
138 | <polygon class="st6" points="794.9,670 784.7,667.1 794.5,663 "/>
139 | <path class="st4" d="M854.9,580H616.1c-6,0-12,6-12,12v12c0,6,6,12,12,12h238.9c6,0,12-6,12-12v-12C866.9,586,860.9,580,854.9,580"
140 | 	/>
141 | <text transform="matrix(1 0 0 1 612.0319 603.4)" class="st1 st2 st3">hisat2_3n_calling_filtered_unqiue</text>
142 | <path class="st5" d="M735.5,616.2c0,7.7,0,16.9,0,25.4"/>
143 | <polygon class="st6" points="739,641.6 735.5,651.6 732,641.6 "/>
144 | <path class="st5" d="M735.5,544.2c0,7.7,0,16.9,0,25.4"/>
145 | <polygon class="st6" points="739,569.6 735.5,579.6 732,569.6 "/>
146 | <path class="st4" d="M1124.5,580H896.5c-6,0-12,6-12,12v12c0,6,6,12,12,12h227.9c6,0,12-6,12-12v-12
147 | 	C1136.5,586,1130.5,580,1124.5,580"/>
148 | <text transform="matrix(1 0 0 1 892.525 603.4)" class="st1 st2 st3">hisat2_3n_calling_filtered_multi</text>
149 | <path class="st5" d="M804.5,544.1c38.7,10.1,87,22.8,127.1,33.3"/>
150 | <polygon class="st6" points="932.6,574 941.4,579.9 930.9,580.8 "/>
151 | <path class="st5" d="M941.5,616.1c-45.3,11.9-103.9,27.2-147.1,38.5"/>
152 | <polygon class="st6" points="795.2,658 784.6,657.1 793.4,651.2 "/>
153 | <path class="st4" d="M812.5,796H658.5c-6,0-12,6-12,12v12c0,6,6,12,12,12h153.9c6,0,12-6,12-12v-12C824.5,802,818.5,796,812.5,796"
154 | 	/>
155 | <text transform="matrix(1 0 0 1 654.5226 819.4)" class="st1 st2 st3">combined_select_sites</text>
156 | <path class="st5" d="M706,832.2c-15,9.2-33.3,20.5-49.3,30.4"/>
157 | <polygon class="st6" points="658.4,865.6 648,867.8 654.7,859.6 "/>
158 | <path class="st5" d="M735.5,760.2c0,7.7,0,16.9,0,25.4"/>
159 | <polygon class="st6" points="739,785.6 735.5,795.6 732,785.6 "/>
160 | </svg>
161 | 


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