├── Code ├── SIMC │ ├── Qlpl.m │ ├── SIMC.m │ ├── index2spa.m │ ├── sideobjectCalc.m │ ├── sidesvd2Threshold.m │ ├── xumm.c │ ├── xumm.mexa64 │ ├── xumm.mexw32 │ └── xumm.mexw64 ├── SIMCLDA_demo.m ├── gKernel.m └── pca_energy.m ├── Datasets ├── Dataset1 │ ├── disSim_Jaccard.mat │ ├── disease_Name.txt │ ├── interMatrix.mat │ ├── lncRNA_Name.txt │ └── lncSim.mat ├── Dataset2 │ ├── disSim_Jaccard.mat │ ├── disease_Name.txt │ ├── interMatrix.mat │ ├── lncRNA_Name.txt │ └── lncSim.mat └── Datseet3 │ ├── disSim_Jaccard.mat │ ├── disease_Name.txt │ ├── interMatrix.mat │ ├── lncRNA_Name.txt │ └── lncSim.mat └── README.md /Code/SIMC/Qlpl.m: -------------------------------------------------------------------------------- 1 | function retVal=Qlpl(B,Z,L,qlpl1,qlpl2) 2 | %Qlpl compute approximation of Z_n+1 3 | 4 | retVal=qlpl1+L/2*(norm((B-Z),'fro'))^2; 5 | retVal=retVal+trace((B-Z)'*qlpl2); 6 | 7 | end -------------------------------------------------------------------------------- /Code/SIMC/SIMC.m: -------------------------------------------------------------------------------- 1 | function [M_recover]=SIMC(M_Omega,Omega_linear,A,B) 2 | %ProSVM implements the algorithm Maxide proposed in [1] 3 | % Syntax 4 | % [M_recover,]=Maxide(M_Omega,Omega_linear,A,B,lambda,max_iter) 5 | % Description 6 | % Maxide takes, 7 | % M_Omega - n\times m, the target matrix with only observed 8 | % entries when the unobserved entries are 0 . 9 | % Omega_linear - A vector recording the observed positions 10 | % in the target matrix. If the (i,j)th entry is 11 | % observed, a value (j-1)*n+i is recorded in Omega_linear. 12 | % A - the side information matrix where left singular 13 | % vectores lie in. 14 | % B - the side information matrix where right singular 15 | % vectores lie in. 16 | % lambda - the regularization parameter 17 | % max_iter - maximum number of iterations 18 | % and returns, 19 | % M_recover - the recoverd matrix 20 | % telapsed - the training time measures in seconds 21 | %[1] Miao Xu, Rong Jin and Zhi-Hua Zhou. Speed up matrix completion with 22 | %side information: application to multi-label learning. In: NIPS'13. 23 | 24 | % initialization 25 | lambda=1; 26 | max_iter=1000; 27 | r_a=size(A,2); 28 | r_b=size(B,2); 29 | L=1; % parameter s 30 | gamma=2; 31 | Z0=zeros(r_a,r_b); 32 | Z=Z0; 33 | alpha0=1; 34 | alpha=1; 35 | i=0; 36 | convergence=zeros(max_iter,1); 37 | 38 | M_Omega_linear=full(M_Omega(Omega_linear))'; 39 | [n,m]=size(M_Omega); 40 | [row,column]=index2spa(Omega_linear,n); 41 | 42 | svdt3=A'*M_Omega*B; 43 | AZ0BOmega=xumm(A*Z0,B',row,column); 44 | AZBOmega=AZ0BOmega; 45 | 46 | while iQlpl(Z,Y,L,qlpl1,qlpl2) 64 | L=L*gamma; 65 | Z=sidesvd2Threshold(Y,svdt2,svdt3,L,lambda); % SVT to sovle approximation of Z 66 | AZBOmega=xumm(A*Z,B',row,column); 67 | DiffL2=norm(AZBOmega-M_Omega_linear,'fro')^2/2; 68 | end 69 | 70 | alpha0=alpha; 71 | alpha=(sqrt(alpha^4+4*alpha^2)-alpha^2)/2; 72 | convergence(i,1)=sideobjectCalc(Z,lambda,DiffL2); 73 | if i>1 74 | if abs(convergence(i,1)-convergence(i-1,1))<(1e-5)*convergence(i,1) 75 | break; 76 | end 77 | end 78 | end 79 | M_recover=A*Z*B'; 80 | 81 | 82 | -------------------------------------------------------------------------------- /Code/SIMC/index2spa.m: -------------------------------------------------------------------------------- 1 | function [row,column]=index2spa(Omega_linear,n) % 2 | %index2spa compute column and row of the postive sample 3 | % Usage: [row,column]=index2spa(Omega_linear,n) 4 | % Inputs: 5 | % Omega_linear: indices of positive samples 6 | % n: the number of row 7 | % 8 | % Outputs: 9 | % row: the number of row 10 | % column: the number of column 11 | 12 | 13 | if size(Omega_linear,1)==1 14 | Omega_linear=Omega_linear'; 15 | end 16 | 17 | row=mod(Omega_linear,n); 18 | row(find(row==0))=n; 19 | column=((Omega_linear-row)/n)'; 20 | column=column+1; 21 | row=row'; -------------------------------------------------------------------------------- /Code/SIMC/sideobjectCalc.m: -------------------------------------------------------------------------------- 1 | function retValue=sideobjectCalc(B,lambda,DiffL2) 2 | %sideobjectCalc calculate the minimum value of the obejective function 3 | 4 | s=svd(B); 5 | retValue=lambda*sum(s); 6 | retValue=retValue+DiffL2; 7 | 8 | end -------------------------------------------------------------------------------- /Code/SIMC/sidesvd2Threshold.m: -------------------------------------------------------------------------------- 1 | function retVal=sidesvd2Threshold(svdt1,svdt2,svdt3,L,lambda) 2 | %sidesvd2Threshold soft-threshold shrink svd (SVT) calculate approximation 3 | % value of Z 4 | % 5 | 6 | A=svdt1-svdt2/L+svdt3/L; 7 | k=rank(A); 8 | [L_svd,S_svd,T_svd] = svds(A,k); 9 | S_svd=diag(max(0,diag(S_svd)-lambda/L)); 10 | retVal=L_svd*S_svd*T_svd'; 11 | 12 | end -------------------------------------------------------------------------------- /Code/SIMC/xumm.c: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bioinfomaticsCSU/SIMCLDA/0559d19a7d42004a1a928d80660bee9a2f0ae256/Code/SIMC/xumm.c -------------------------------------------------------------------------------- /Code/SIMC/xumm.mexa64: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bioinfomaticsCSU/SIMCLDA/0559d19a7d42004a1a928d80660bee9a2f0ae256/Code/SIMC/xumm.mexa64 -------------------------------------------------------------------------------- /Code/SIMC/xumm.mexw32: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bioinfomaticsCSU/SIMCLDA/0559d19a7d42004a1a928d80660bee9a2f0ae256/Code/SIMC/xumm.mexw32 -------------------------------------------------------------------------------- /Code/SIMC/xumm.mexw64: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bioinfomaticsCSU/SIMCLDA/0559d19a7d42004a1a928d80660bee9a2f0ae256/Code/SIMC/xumm.mexw64 -------------------------------------------------------------------------------- /Code/SIMCLDA_demo.m: -------------------------------------------------------------------------------- 1 | % SIMCLDA: Prediction of lncRNA-disease associations based on inductive matrix completion 2 | % 3 | %% 4 | % interMatrix.mat: an n*m association matrix between lncRNAs and diseases, n is 5 | %the number of lncRNAs, and m is the number of diseases 6 | % lncSim.mat: an n*n sequence similarity matrix of lncRNAs 7 | % disSim_Jaccard.mat: an m*m similarity matrix of disease 8 | 9 | %% configuration 10 | addpath('SIMC'); 11 | 12 | %% load data 13 | LD=importdata('../Datasets/Dataset1/interMatrix.mat'); 14 | lncSim=importdata('../Datasets/Dataset1/lncSim.mat'); 15 | dissim=importdata('../Datasets/Dataset1/disSim_Jaccard.mat'); 16 | 17 | %% complete interaction information for a new lncRNA 18 | for i=1:nl 19 | if length(find(LD(i,:)))==0 20 | rowVec=lncSim(i,:); 21 | rowVec(i)=0; 22 | simNeighbors=find(rowVec>=mean(mean(lncSim))); 23 | if length(simNeighbors) 24 | new_row=zeros(1,nd); 25 | for l=1:length(simNeighbors) 26 | new_row=new_row+LD(simNeighbors(l),:); 27 | end 28 | new_row=new_row/length(simNeighbors); 29 | LD(i,:)=new_row; 30 | end 31 | end 32 | end 33 | 34 | %% computing Gaussian interaction profile kernel of lncRNAs 35 | [LL,~]=gKernel(nl,nd,LD); 36 | [nl,nd]=size(LD); 37 | 38 | %% extract feature vectors of lncRNAs and diseases 39 | lnc_feature=pca_energy(LL,0.8); 40 | dis_feature=pca_energy(dissim,0.6); 41 | 42 | %% using inductive matrix completion to complete the association matrix of lncRNA-disease 43 | Omega=find(LD==1); 44 | M_recover=SIMC(LD,Omega,lnc_feature,dis_feature); 45 | 46 | -------------------------------------------------------------------------------- /Code/gKernel.m: -------------------------------------------------------------------------------- 1 | function [result_lnc,result_dis]=gKernel(nl,nd,inter_lncdis) 2 | %gKernel compute Gaussian interaction profile kernel 3 | % Usage: [result_lnc,result_dis]=gKernel(nl,nd,inter_lncdis) 4 | % Inputs: 5 | % nl: the number of lncRNAs 6 | % nd: the number of diseases 7 | % inter_lncdis: an nl*nd association matrix between lncRNAs and diseases 8 | % 9 | % Outputs: 10 | % result_lnc: Gaussian interaction profile kernel of lncRNAs 11 | % result_dis: Gaussian interaction profile kernel of diseases 12 | 13 | 14 | for i=1:nl 15 | sl(i)=norm(inter_lncdis(i,:))^2; 16 | end 17 | gamal=nl/sum(sl')*1; 18 | for i=1:nl 19 | for j=1:nl 20 | pkl(i,j)=exp(-gamal*(norm(inter_lncdis(i,:)-inter_lncdis(j,:)))^2); 21 | end 22 | end 23 | for i=1:nd 24 | sd(i)=norm(inter_lncdis(:,i))^2; 25 | end 26 | gamad=nd/sum(sd')*1; 27 | for i=1:nd 28 | for j=1:nd 29 | pkd(i,j)=exp(-gamad*(norm(inter_lncdis(:,i)-inter_lncdis(:,j)))^2); 30 | end 31 | end 32 | result_lnc=pkl; 33 | result_dis=pkd; 34 | end 35 | 36 | 37 | -------------------------------------------------------------------------------- /Code/pca_energy.m: -------------------------------------------------------------------------------- 1 | function [feature_vecs]=pca_energy(simMat,para) 2 | %pca_energy extracting primary feature vectors based on energy strategy 3 | % Usage: [feature_vecs]=pca_energy(simMat,para) 4 | % Inputs: 5 | % simMat: kernel of lncRNAs or diseases 6 | % para: percent of energy for extracting primary feature vectors 7 | % 8 | % Outputs: 9 | % feature_vecs: primary feature vectors of lncRNAs or diseases 10 | 11 | pca_rank=0; 12 | singular_mat=svd(simMat); 13 | for i=1:rank(simMat) 14 | if sum(singular_mat(1:i))>para*sum(svd(simMat)) 15 | pca_rank=i; 16 | break; 17 | end 18 | end 19 | [U_,S,V]=svds(simMat,pca_rank); 20 | feature_vecs=V; 21 | end -------------------------------------------------------------------------------- /Datasets/Dataset1/disSim_Jaccard.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bioinfomaticsCSU/SIMCLDA/0559d19a7d42004a1a928d80660bee9a2f0ae256/Datasets/Dataset1/disSim_Jaccard.mat -------------------------------------------------------------------------------- /Datasets/Dataset1/disease_Name.txt: -------------------------------------------------------------------------------- 1 | AIDS 2 | abdominal aortic aneurysm 3 | acute lymphoblastic leukemia 4 | acute myeloid leukemia 5 | adolescent idiopathic scoliosis 6 | adrenocortical carcinomas 7 | affective disorders 8 | aging 9 | alcoholic liver disease 10 | Alzheimer's disease 11 | Angelman syndrome 12 | aortic aneurysm 13 | atherosclerosis 14 | Autism spectrum disorder 15 | autoimmune disease 16 | autoimmune thyroid disease 17 | basal cell carcinoma 18 | Beckwith-Wiedemann syndrome 19 | biparental complete hydatidiform moles 20 | bipolar disorder 21 | bladder cancer 22 | blepharophimosis syndrome 23 | breast cancer 24 | Burkitt's lymphomas 25 | cancer 26 | cardiac hypertrophy 27 | cardiomyopathy 28 | cardiovascular disease 29 | cat eye syndrome 30 | cervical cancer 31 | chronic lymphocytic leukemia 32 | chronic myeloid leukemia 33 | chronic myeloproliferative disorders 34 | chronic nonalcoholic liver disease 35 | cleft lip 36 | colon cancer 37 | colorectal cancer 38 | Congenital hyperinsulinism 39 | coronary artery disease 40 | coronary disease 41 | coronary heart disease 42 | depression 43 | dermatomyositis 44 | Diabetes 45 | diabetic nephropathy 46 | DiGeorge syndrome 47 | dilated cardiomyopathy 48 | Down's syndrome 49 | drug abuse 50 | ductal carcinoma 51 | dyskeratosis congenita 52 | embryonal carcinoma 53 | endometrial cancer 54 | Endometrial stromal sarcoma 55 | endometriosis 56 | esophagus cancer 57 | familial and sporadic intracranial aneurysms 58 | fragile X syndrome 59 | frontotemporal lobar degeneration 60 | gastric cancer 61 | gastrointestinal stromal tumors 62 | germ cell tumor 63 | gestational choriocarcinoma 64 | gestational trophoblastic diseases 65 | Glaucoma 66 | glioblastoma 67 | glioma 68 | growth restriction 69 | HCV 70 | hematopoiesis 71 | hepatic colorectal metastasis 72 | hepatocellular carcinoma 73 | heroin abuse 74 | Hodgkin's lymphoma 75 | Huntington's disease 76 | hyperhomocysteinemia 77 | infertility 78 | intracranial aneurysm 79 | kidney cancer 80 | Klinefelter's syndrome 81 | Leishmania 82 | leukemia 83 | liver cancer 84 | liver injury 85 | lung adenocarcinoma 86 | lung cancer 87 | lymphocytic leukemia 88 | lymphoma 89 | Medulloblastoma 90 | melanoma 91 | melasma 92 | Meningioma 93 | Mullerian aplasia 94 | multiple sclerosis 95 | myelodysplastic syndrome 96 | myeloma 97 | myeloproliferative polycythaemia vera 98 | myocardial infarction 99 | myopia 100 | myotonic dystrophy type 1 101 | narcolepsy 102 | nasopharyngeal carcinoma 103 | neural system tumors syndrome 104 | neural tube defects 105 | neuroblastoma 106 | Neurofibromatosis type 1 107 | nonfunctioning pituitary adenomas 108 | non-small cell lung cancer 109 | obesity 110 | osteosarcoma 111 | ovarian cancer 112 | pancreatic cancer 113 | Pancreatic ductal adenocarcinoma 114 | pancreaticobiliary maljunction 115 | panic disorder 116 | papillary thyroid carcinoma 117 | Parkinson's disease 118 | parotid cancer 119 | periodontitis 120 | peripheral artery disease 121 | pheochromocytoma 122 | photoperiod-sensitive male sterility 123 | Pituitary adenoma 124 | polymyositis 125 | Prader-Willi syndrome 126 | pre-eclampsia 127 | prostate cancer 128 | pseudohypoparathyroidism type Ib 129 | psoriasis 130 | renal cancer 131 | renal disease 132 | rhabdomyosarcoma 133 | schizoaffective disorder 134 | Schizophrenia 135 | Silver-Russell syndrome 136 | spinocerebellar ataxia type 7 137 | spinocerebellar ataxia type 8 138 | Split Hand/Split Foot malformation disorder 139 | squamous carcinoma 140 | Stroke 141 | syndromic developmental defect 142 | testicular cancer 143 | tongue cancer 144 | transient neonatal Diabetes mellitus 145 | trophoblastic tumor 146 | type 1 Diabetes 147 | type 2 Diabetes 148 | velocardiofacial syndrome 149 | West Syndrome 150 | Wilms' tumor -------------------------------------------------------------------------------- /Datasets/Dataset1/interMatrix.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bioinfomaticsCSU/SIMCLDA/0559d19a7d42004a1a928d80660bee9a2f0ae256/Datasets/Dataset1/interMatrix.mat -------------------------------------------------------------------------------- /Datasets/Dataset1/lncRNA_Name.txt: -------------------------------------------------------------------------------- 1 | 7SK 2 | 7SL 3 | AIR 4 | AK023948 5 | anti-NOS2A 6 | ASFMR1 7 | ATP6V1G2-DDX39B 8 | ATXN8OS 9 | BACE1-AS 10 | BC040587 11 | BCAR4 12 | BCYRN1 13 | BDNF-AS1 14 | BOK-AS1 15 | BPESC1 16 | BX118339 17 | C15orf2 18 | C1QTNF9B-AS1 19 | CASC2 20 | CBR3-AS1 21 | CDKN2B-AS1 22 | CECR3 23 | CECR9 24 | CHL1-AS2 25 | CRNDE 26 | DAOA-AS1 27 | DAPK1 28 | DGCR5 29 | DISC2 30 | DLEU1 31 | DLEU2 32 | DLG2AS 33 | DLX6-AS1 34 | DMPK 35 | DNM3OS 36 | DSCAM-AS1 37 | EPB41L4A-AS1 38 | ESRG 39 | GAS5 40 | GDNFOS 41 | GNAS-AS1 42 | H19 43 | HAR1A 44 | HAR1B 45 | HCP5 46 | HIF1A-AS1 47 | HLA-AS1 48 | HOTAIR 49 | HTTAS 50 | HULC 51 | HYMAI 52 | IFNG-AS1 53 | IGF2-AS 54 | IPW 55 | KCNQ1DN 56 | KCNQ1OT1 57 | LDMAR 58 | LINC00032 59 | LINC00162 60 | LINC00271 61 | LINC00312 62 | LSINCT5 63 | MALAT1 64 | MAP3K14 65 | MEG3 66 | MESTIT1 67 | MIAT 68 | MIR100HG 69 | MIR155HG 70 | MIR17HG 71 | MIR31HG 72 | MKRN3-AS1 73 | MYCNOS 74 | NAMA 75 | NDM29 76 | NEAT1 77 | NRON 78 | PCA3 79 | PCAT1 80 | PCGEM1 81 | PDZRN3-AS1 82 | PINC 83 | PINK1-AS 84 | PISRT1 85 | PPP3CB 86 | PRINS 87 | PSORS1C3 88 | PVT1 89 | RMST 90 | RRP1B 91 | SCAANT1 92 | SNHG11 93 | SNHG3 94 | SNHG4 95 | SNHG5 96 | SOX2-OT 97 | SPRY4-IT1 98 | SRA1 99 | TCL6 100 | TDRG1 101 | TERC 102 | TRAF3IP2-AS1 103 | TUG1 104 | TUSC7 105 | UBE3A-AS1 106 | UCA1 107 | WRAP53 108 | WT1-AS 109 | XIST 110 | Yiya 111 | ZFAT-AS1 112 | ZNFX1-AS1 -------------------------------------------------------------------------------- /Datasets/Dataset1/lncSim.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bioinfomaticsCSU/SIMCLDA/0559d19a7d42004a1a928d80660bee9a2f0ae256/Datasets/Dataset1/lncSim.mat -------------------------------------------------------------------------------- /Datasets/Dataset2/disSim_Jaccard.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bioinfomaticsCSU/SIMCLDA/0559d19a7d42004a1a928d80660bee9a2f0ae256/Datasets/Dataset2/disSim_Jaccard.mat -------------------------------------------------------------------------------- /Datasets/Dataset2/disease_Name.txt: -------------------------------------------------------------------------------- 1 | AIDS 2 | abdominal aortic aneurysm 3 | acute lymphoblastic leukemia 4 | acute myeloid leukemia 5 | adolescent idiopathic scoliosis 6 | adrenocortical carcinomas 7 | affective disorders 8 | aging 9 | alcoholic liver disease 10 | Alzheimer's disease 11 | Angelman syndrome 12 | aortic aneurysm 13 | atherosclerosis 14 | Autism spectrum disorder 15 | autoimmune disease 16 | barrett's Esophagus 17 | basal cell carcinoma 18 | Beckwith-Wiedemann syndrome 19 | biparental complete hydatidiform moles 20 | bipolar disorder 21 | bladder cancer 22 | Bladder urothelial carcinoma 23 | blepharophimosis syndrome 24 | bone diseases 25 | brachydactyly 26 | breast cancer 27 | Burkitt's lymphomas 28 | cancer 29 | cardiac hypertrophy 30 | cardiomyopathy 31 | cardiovascular disease 32 | cat eye syndrome 33 | cervical cancer 34 | choriocarcinoma 35 | chronic lymphocytic leukemia 36 | chronic myeloid leukemia 37 | chronic myeloproliferative disorders 38 | chronic nonalcoholic liver disease 39 | cleft lip 40 | colon cancer 41 | colorectal cancer 42 | Congenital hyperinsulinism 43 | coronary artery disease 44 | depression 45 | dermatomyositis 46 | Diabetes 47 | diabetic nephropathy 48 | DiGeorge syndrome 49 | dilated cardiomyopathy 50 | Down's syndrome 51 | drug abuse 52 | Duchenne muscular dystrophy 53 | dyskeratosis congenita 54 | embryonal carcinoma 55 | endometrial cancer 56 | Endometrial stromal sarcoma 57 | endometriosis 58 | enterovirus 71 infection 59 | enterovirus 72 infection 60 | enterovirus 73 infection 61 | enterovirus 74 infection 62 | esophagus cancer 63 | extravillous trophoblast 64 | Facioscapulohumeral muscular dystrophy 65 | familial and sporadic intracranial aneurysms 66 | fragile X syndrome 67 | frontotemporal lobar degeneration 68 | gastric cancer 69 | gastrointestinal stromal tumor 70 | germ cell tumor 71 | gestational choriocarcinoma 72 | gestational trophoblastic diseases 73 | Glaucoma 74 | glioblastoma 75 | glioma 76 | glucose metabolism disorder 77 | growth restriction 78 | HCV 79 | Heart Failure 80 | hematopoiesis 81 | hepatic colorectal metastasis 82 | hepatocellular carcinoma 83 | heroin abuse 84 | Hodgkin's lymphoma 85 | Human Dilated Cardiomyopathy 86 | Huntington's disease 87 | hyperhomocysteinemia 88 | infertility 89 | intracranial aneurysm 90 | Kaposi's sarcoma 91 | kidney cancer 92 | Leishmania 93 | leukemia 94 | lipid metabolism disorder 95 | liver cancer 96 | liver injury 97 | lung cancer 98 | lymphocytic leukemia 99 | lymphoma 100 | Major depression 101 | Medulloblastoma 102 | melanoma 103 | melasma 104 | Meningioma 105 | Mullerian aplasia 106 | multiple sclerosis 107 | myelodysplastic syndrome 108 | myeloma 109 | myeloproliferative polycythaemia vera 110 | myocardial infarction 111 | myopia 112 | myotonic dystrophy type 1 113 | narcolepsy 114 | nasopharyngeal carcinoma 115 | neural system tumors syndrome 116 | neural tube defects 117 | neuroblastoma 118 | Neurofibromatosis type 1 119 | nonfunctioning pituitary adenomas 120 | non-small cell lung cancer 121 | obesity 122 | osteosarcoma 123 | ovarian cancer 124 | pancreas cancer 125 | Pancreatic ductal adenocarcinoma 126 | pancreaticobiliary maljunction 127 | panic disorder 128 | papillary thyroid carcinoma 129 | Parkinson's disease 130 | parotid cancer 131 | periodontitis 132 | peripheral artery disease 133 | pheochromocytoma 134 | photoperiod-sensitive male sterility 135 | Pituitary adenoma 136 | Plexiform neurofibroma 137 | polymyositis 138 | Prader-Willi syndrome 139 | pre-eclampsia 140 | prostate 141 | prostate cancer 142 | pseudohypoparathyroidism type Ib 143 | psoriasis 144 | renal cancer 145 | renal disease 146 | rhabdomyosarcoma 147 | schizoaffective disorder 148 | Schizophrenia 149 | Silver-Russell syndrome 150 | small cell lung cancer 151 | spinocerebellar ataxia type 7 152 | spinocerebellar ataxia type 8 153 | Split Hand/Split Foot malformation disorder 154 | squamous carcinoma 155 | squamous-cell lung carcinomas 156 | Stroke 157 | syndromic developmental defect 158 | systemic lupus erythematosus 159 | testicular cancer 160 | tongue cancer 161 | transient neonatal Diabetes mellitus 162 | trophoblastic tumor 163 | tumor 164 | type 1 Diabetes 165 | type 2 Diabetes 166 | uterus cancer 167 | velocardiofacial syndrome 168 | West Syndrome 169 | Wilms' tumor -------------------------------------------------------------------------------- /Datasets/Dataset2/interMatrix.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bioinfomaticsCSU/SIMCLDA/0559d19a7d42004a1a928d80660bee9a2f0ae256/Datasets/Dataset2/interMatrix.mat -------------------------------------------------------------------------------- /Datasets/Dataset2/lncRNA_Name.txt: -------------------------------------------------------------------------------- 1 | 7SK 2 | 7SL 3 | AC002511.1 4 | AFAP1-AS1 5 | AIR 6 | AK023948 7 | AP000688.29 8 | ASFMR1 9 | ATP6V1G2-DDX39B 10 | ATXN8OS 11 | BACE1-AS 12 | BANCR 13 | BC040587 14 | BCAR4 15 | BCYRN1 16 | BDNF-AS1 17 | BOK-AS1 18 | BPESC1 19 | BX118339 20 | C15orf2 21 | C1QTNF9B-AS1 22 | CASC2 23 | CBR3-AS1 24 | CCAT1 25 | CCDC26 26 | CCND1 27 | CDKN2B-AS1 28 | CECR3 29 | CECR9 30 | CHL1-AS2 31 | CRNDE 32 | DANCR 33 | DAOA-AS1 34 | DAPK1 35 | DBE-T 36 | DGCR5 37 | DISC2 38 | DLEU1 39 | DLEU2 40 | DLG2AS 41 | DLX6-AS1 42 | DMPK 43 | DNM3OS 44 | DSCAM-AS1 45 | EPB41L4A-AS1 46 | ESRG 47 | FADS1 48 | Fendrr 49 | GAS5 50 | GDNFOS 51 | GNAS-AS1 52 | H19 53 | HAR1A 54 | HAR1B 55 | HCP5 56 | HELLPAR 57 | HIF1A-AS1 58 | HI-LNC25 59 | HLA-AS1 60 | HOTAIR 61 | HTTAS 62 | HULC 63 | HYMAI 64 | IFNG-AS1 65 | IGF2-AS 66 | IPW 67 | KCNQ1DN 68 | KCNQ1OT1 69 | KUCG1 70 | LDMAR 71 | LINC00032 72 | LINC00162 73 | LINC00271 74 | LINC00312 75 | LincRNA-p21 76 | LSINCT5 77 | MALAT1 78 | MAP3K14 79 | MEG3 80 | MESTIT1 81 | MIAT 82 | MIR100HG 83 | MIR155HG 84 | MIR17HG 85 | MIR31HG 86 | MKRN3-AS1 87 | MYCNOS 88 | NAMA 89 | NDM29 90 | NEAT1 91 | NPPA-AS1 92 | NPTN-IT1 93 | NRON 94 | PAN 95 | PANDAR 96 | PCA3 97 | PCAT1 98 | PCGEM1 99 | PCNCR1 100 | PDZRN3-AS1 101 | PINC 102 | PINK1-AS 103 | PISRT1 104 | PPP3CB 105 | PRINS 106 | PSORS1C3 107 | PTENpg1 108 | PTHLH 109 | PVT1 110 | RMST 111 | RP4-620F22.3 112 | RP5-843L14.1 113 | RRP1B 114 | SCAANT1 115 | SNHG11 116 | SNHG3 117 | SNHG4 118 | SNHG5 119 | SOX2-OT 120 | SPRY4-IT1 121 | SRA1 122 | TCL6 123 | TDRG1 124 | TERC 125 | TRAF3IP2-AS1 126 | T-UCRs 127 | TUG1 128 | TUSC7 129 | UBE3A-AS1 130 | UCA1 131 | WRAP53 -------------------------------------------------------------------------------- /Datasets/Dataset2/lncSim.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bioinfomaticsCSU/SIMCLDA/0559d19a7d42004a1a928d80660bee9a2f0ae256/Datasets/Dataset2/lncSim.mat -------------------------------------------------------------------------------- /Datasets/Datseet3/disSim_Jaccard.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bioinfomaticsCSU/SIMCLDA/0559d19a7d42004a1a928d80660bee9a2f0ae256/Datasets/Datseet3/disSim_Jaccard.mat -------------------------------------------------------------------------------- /Datasets/Datseet3/disease_Name.txt: -------------------------------------------------------------------------------- 1 | abdominal aortic aneurysm 2 | acute lymphoblastic leukemia 3 | acute myeloid leukemia 4 | acute myocardial infarction 5 | adenocarcinoma 6 | adolescent idiopathic scoliosis 7 | adrenocortical carcinomas 8 | affective disorders 9 | aging 10 | AIDS 11 | alcoholic liver disease 12 | Alzheimer's disease 13 | amyotrophic lateral sclerosis 14 | Angelman syndrome 15 | aortic aneurysm 16 | atherosclerosis 17 | Autism spectrum disorder 18 | autoimmune disease 19 | barrett's Esophagus 20 | basal cell carcinoma 21 | B-cell neoplasms 22 | Beckwith-Wiedemann syndrome 23 | biparental complete hydatidiform moles 24 | bipolar disorder 25 | bladder cancer 26 | blepharophimosis syndrome 27 | bone diseases 28 | brachydactyly 29 | breast cancer 30 | Burkitt's lymphomas 31 | cancer 32 | carcinoma 33 | carcinoma of the urinary bladder 34 | cardiac hypertrophy 35 | cardiomyopathy 36 | cardiovascular and renal disease 37 | cardiovascular disease 38 | Cartilage Hair Hypoplaisia 39 | cat eye syndrome 40 | cervical cancer 41 | choriocarcinoma 42 | chronic lymphocytic leukemia 43 | chronic myeloid leukemia 44 | chronic myeloproliferative disorders 45 | chronic nonalcoholic liver disease 46 | cleft lip 47 | colon cancer 48 | colorectal cancer 49 | Congenital hyperinsulinism 50 | coronary artery disease 51 | coronary disease 52 | coronary heart disease 53 | Crohn's disease 54 | decreased myogenesis 55 | depression 56 | dermatomyositis 57 | Diabetes 58 | Diabetes mellitus 59 | diabetic nephropathy 60 | Diffuse cerebral hypomyelination with cerebellar atrophy and hypoplasia of the corpus callosum 61 | DiGeorge syndrome 62 | dilated cardiomyopathy 63 | Down's syndrome 64 | drug abuse 65 | Duchenne muscular dystrophy 66 | ductal carcinoma 67 | dyskeratosis congenita 68 | embryonal carcinoma 69 | endometrial cancer 70 | endometriosis 71 | enterovirus 71 infection 72 | enterovirus 72 infection 73 | enterovirus 73 infection 74 | enterovirus 74 infection 75 | epithelial ovarian cancer 76 | esophageal adenocarcinoma 77 | Esophageal squamous cell carcinoma 78 | esophagus cancer 79 | extravillous trophoblast 80 | Facioscapulohumeral muscular dystrophy 81 | familial and sporadic intracranial aneurysms 82 | female cancers 83 | fragile X syndrome 84 | Fragile X-associated tremor and ataxia syndrome 85 | frontotemporal lobar degeneration 86 | gallbladder cancer 87 | gastric cancer 88 | gastrointestinal cancer 89 | germ cell tumor 90 | gestational choriocarcinoma 91 | gestational trophoblastic diseases 92 | Glaucoma 93 | glioblastoma 94 | glioma 95 | glucose metabolism disorder 96 | growth restriction 97 | H. pylori-related diseases 98 | HCV 99 | Head and neck squamous carcinoma 100 | Heart Failure 101 | hematopoiesis 102 | hematopoietic malignancies 103 | hepatic colorectal metastasis 104 | hepatocellular carcinoma 105 | hereditary cutaneous malignant melanoma 106 | Hereditary Hemorrhagic Telangiectasia 107 | heroin abuse 108 | Hirschsprung's disease 109 | Hodgkin's lymphoma 110 | Human Dilated Cardiomyopathy 111 | Huntington's disease 112 | hyperhomocysteinemia 113 | Inclusion body myositis 114 | infertility 115 | Intellectual and developmental disability 116 | intracranial aneurysm 117 | Intrauterine Growth Restriction 118 | ischemia/reperfusion 119 | ischemic stroke 120 | Kaposi's sarcoma 121 | Kawasaki disease 122 | kidney cancer 123 | Klinefelter's syndrome 124 | laryngeal squamous carcinoma 125 | Leishmania 126 | leukemia 127 | lipid metabolism disorder 128 | liver cancer 129 | liver injury 130 | low-grade gliomas 131 | lung adenocarcinoma 132 | lung cancer 133 | lung squamous carcinoma 134 | lymphocytic leukemia 135 | lymphoma 136 | Macular degeneration 137 | Major depression 138 | Medulloblastoma 139 | melanoma 140 | membranous nephropathy 141 | Meningioma 142 | Mullerian aplasia 143 | multiple myeloma 144 | multiple sclerosis 145 | myelodysplastic syndrome 146 | myeloma 147 | myeloproliferative polycythaemia vera 148 | myocardial infarction 149 | myopia 150 | myotonic dystrophy type 1 151 | narcolepsy 152 | nasopharyngeal carcinoma 153 | neural system tumors syndrome 154 | neural tube defects 155 | neuroblastoma 156 | Neurodevelopmental syndromes associated with the SOX2 locus 157 | Neurofibromatosis type 1 158 | neuropathic pain 159 | Nonalcoholic fatty liver disease 160 | nonfunctioning pituitary adenomas 161 | non-small cell lung cancer 162 | obesity 163 | Opitz-Kaveggia syndrome 164 | oral squamous carcinoma 165 | osteosarcoma 166 | ovarian cancer 167 | p53-associated pathological states 168 | pancreas cancer 169 | Pancreatic ductal adenocarcinoma 170 | pancreaticobiliary maljunction 171 | panic disorder 172 | papillary thyroid carcinoma 173 | Parkinson's disease 174 | parotid cancer 175 | periodontitis 176 | peripheral artery disease 177 | pheochromocytoma 178 | photoperiod-sensitive male sterility 179 | Pituitary adenoma 180 | Plexiform neurofibroma 181 | Polycystic Ovary Syndrome 182 | polymyositis 183 | postmenopausal osteoporosis 184 | Prader-Willi syndrome 185 | pre-eclampsia 186 | Progressive encephalopathy with severe infantile anorexia 187 | prostate 188 | prostate cancer 189 | pseudohypoparathyroidism type Ib 190 | psoriasis 191 | psychiatric disease 192 | renal carcinoma 193 | renal cell carcinoma 194 | renal clear cell carcinoma 195 | renal inflammation 196 | rhabdomyosarcoma 197 | rheumatoid arthritis 198 | Schizophrenia 199 | Silver-Russell syndrome 200 | skin melanoma 201 | small cell lung cancer 202 | spinocerebellar ataxia type 7 203 | spinocerebellar ataxia type 8 204 | Split Hand/Split Foot malformation disorder 205 | squamous carcinoma 206 | squamous-cell lung carcinomas 207 | stomach adenocarcinoma 208 | Stroke 209 | syndromic developmental defect 210 | systemic lupus erythematosus 211 | TDP-43-associated pathological states 212 | testicular cancer 213 | TLS-associated pathological states 214 | tongue cancer 215 | tongue squamous carcinomas 216 | transient neonatal Diabetes mellitus 217 | triple-negative breast cancer 218 | trophoblastic tumor 219 | tumor 220 | type 1 Diabetes 221 | type 2 Diabetes 222 | uterus cancer 223 | velocardiofacial syndrome 224 | Ventricular septal defects 225 | West Syndrome 226 | Wilms' tumor -------------------------------------------------------------------------------- /Datasets/Datseet3/interMatrix.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bioinfomaticsCSU/SIMCLDA/0559d19a7d42004a1a928d80660bee9a2f0ae256/Datasets/Datseet3/interMatrix.mat -------------------------------------------------------------------------------- /Datasets/Datseet3/lncRNA_Name.txt: -------------------------------------------------------------------------------- 1 | 116HG 2 | 1B FGF-AS 3 | 51A 4 | 7SK 5 | 7SL 6 | AB074278 7 | AC002511.1 8 | AC006050.3-003 9 | ACTA2-AS1 10 | ADAMTS9-AS2 11 | AF086415 12 | AFAP1-AS1 13 | AIR 14 | AK023948 15 | AK056098 16 | AK095147 17 | AK294004 18 | Alg2 19 | Alu 20 | anti-NOS2A 21 | AP000688.29 22 | AP5M1 23 | Arid2-IR 24 | Asb3 25 | ASFMR1 26 | ATP6V1G2-DDX39B 27 | ATXN8OS 28 | BACE1-AS 29 | BANCR 30 | BC040587 31 | BCAR4 32 | BCYRN1 33 | BDNF-AS1 34 | BLACAT1 35 | BOK-AS1 36 | BPESC1 37 | BX118339 38 | C15orf2 39 | C1QTNF9B-AS1 40 | CASC2 41 | CBR3-AS1 42 | CCAT1 43 | CCAT2 44 | CCDC26 45 | CCND1 46 | CDKN2B-AS1 47 | CECR3 48 | CECR9 49 | Chac2 50 | CHL1-AS2 51 | CHRF 52 | CRNDE 53 | CTBP1-AS 54 | D4Z4 55 | DANCR 56 | DAOA-AS1 57 | DAPK1 58 | DBE-T 59 | DGCR5 60 | DISC2 61 | DLEU1 62 | DLEU2 63 | DLG2AS 64 | DLX6-AS1 65 | DMPK 66 | DNM3OS 67 | DQ786243 68 | DRAIC 69 | DSCAM-AS1 70 | ENSG00000135253.9 71 | ENSG00000147753.5 72 | ENSG00000196096.3 73 | ENSG00000197251.3 74 | ENSG00000203325.3 75 | ENSG00000206129.3 76 | ENSG00000215231.3 77 | ENSG00000215374.4 78 | ENSG00000215808.2 79 | ENSG00000226496.1 80 | ENSG00000229563.1 81 | ENSG00000230133.1 82 | ENSG00000230544.1 83 | ENSG00000231133.1 84 | ENSG00000231185.2 85 | ENSG00000232021.2 86 | ENSG00000232046.1 87 | ENSG00000232956.3 88 | ENSG00000233154.1 89 | ENSG00000233251.3 90 | ENSG00000235285.1 91 | ENSG00000237036.3 92 | ENSG00000237548.1 93 | ENSG00000240453.1 94 | ENSG00000241269.1 95 | ENSG00000245910.3 96 | ENSG00000248176.1 97 | ENSG00000249364.1 98 | ENSG00000249772.1 99 | ENSG00000250195.1 100 | ENSG00000250608.1 101 | ENSG00000254154.3 102 | ENSG00000255471.1 103 | ENSG00000256218.1 104 | ENSG00000259150.1 105 | ENSG00000259334.1 106 | ENSG00000259484.1 107 | ENSG00000259758.1 108 | ENSG00000263753.1 109 | ENSG00000264772.1 110 | ENSG00000266952.1 111 | ENST00000480739 112 | ENST00000513542 113 | EPB41L4A-AS1 114 | ESCCAL-1 115 | ESCCAL-5 116 | ESRG 117 | FADS1 118 | Fendrr 119 | FGF10-AS1 120 | FMR5 121 | FMR6 122 | GAPLINC 123 | GAS5 124 | GDNFOS 125 | GHET1 126 | GNAS-AS1 127 | H19 128 | HA117 129 | HAR1A 130 | HAR1B 131 | HCP5 132 | HEIH 133 | HELLPAR 134 | HIF1A-AS1 135 | HIF1A-AS2 136 | HI-LNC25 137 | HLA-AS1 138 | HNF1A-AS1 139 | HOST2 140 | HOTAIR 141 | HOTTIP 142 | HTTAS 143 | HULC 144 | HYMAI 145 | IFNG-AS1 146 | IGF2-AS 147 | IPW 148 | Kcna2-AS 149 | KCNQ1DN 150 | KCNQ1OT1 151 | KRASP1 152 | KUCG1 153 | LALR 154 | LDMAR 155 | LINC00032 156 | LINC00162 157 | LINC00271 158 | LINC00299 159 | LINC00312 160 | Linc00963 161 | LINC01133 162 | LINC01262 163 | LINCMD1 164 | linc-POU3F3 165 | LincRNA-p21 166 | lincRNA-RoR 167 | LIPCAR 168 | lnc-AL355149.1-1 169 | lnc-C22orf32-1 170 | lnc-KCTD6-3 171 | lnc-LCE5A-1 172 | lncRNA-ATB 173 | LncRNA-LALR1 174 | lncRNA-MVIH 175 | lnc-SCA7 176 | lnc-ZNF674-1 177 | LOC389023 178 | Loc554202 179 | LOC728228 180 | LOC728606 181 | LSINCT5 182 | MALAT1 183 | MALAT2 184 | MAP3K14 185 | MEG3 186 | MESTIT1 187 | MIAT 188 | MINA 189 | MIR100HG 190 | MIR155HG 191 | MIR17HG 192 | miR-21 193 | MIR31HG 194 | MIR7-3HG 195 | MKRN3-AS1 196 | MRAK052686 197 | MYCNOS 198 | NAMA 199 | NBAT1 200 | NDM29 201 | NEAT1 202 | NPPA-AS1 203 | NPTN-IT1 204 | NRON 205 | PAN 206 | PANDAR 207 | PCA3 208 | PCAT1 209 | PCAT29 210 | PCGEM1 211 | PCNA-AS1 212 | PCNCR1 213 | PDZRN3-AS1 214 | Pex11b 215 | PINC 216 | PINK1-AS 217 | PISRT1 218 | PPP3CB 219 | PRINS 220 | PRNCR1 221 | PSORS1C3 222 | PTCSC3 223 | PTENpg1 224 | PTHLH 225 | PVT1 226 | REST/CoREST-regulated lncRNAs 227 | RMST 228 | RNA polymerase III-dependent lncRNAs 229 | RNA-a 230 | RNase MRP 231 | RP1-179N16.3 232 | RP4-620F22.3 233 | RP5-833A20.1 234 | RP5-843L14.1 235 | RRP1B 236 | RUNXOR 237 | SCAANT1 238 | Scarb2 239 | SCHLAP1 240 | Sema3g 241 | SLC7A2-IT1A/B 242 | SNHG11 243 | SNHG16 244 | SNHG3 245 | SNHG4 246 | SNHG5 247 | SOX2-OT 248 | Sox4 249 | Sp5 250 | SPRY4-IT1 251 | SRA1 252 | Srsf9 253 | SUMO1P3 254 | TARID 255 | TC0100223 256 | TC0101441 257 | TC0101686 258 | TCL6 259 | TDRG1 260 | TERC 261 | THRIL 262 | TINCR 263 | TRAF3IP2-AS1 264 | Trpm3 265 | T-UCRs 266 | TUG1 267 | TUSC7 268 | TUSC8 269 | U1 spliceosomal lncRNA 270 | UBE3A-AS1 271 | UCA1 272 | UCHL1-AS 273 | WNT4 274 | WRAP53 275 | WT1-AS 276 | XIST 277 | XLOC_000620 278 | XLOC_004122 279 | XLOC_004562 280 | XLOC_005912 281 | XLOC_014388 282 | Yiya 283 | ZFAT-AS1 284 | Zim3 285 | ZNFX1-AS1 -------------------------------------------------------------------------------- /Datasets/Datseet3/lncSim.mat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bioinfomaticsCSU/SIMCLDA/0559d19a7d42004a1a928d80660bee9a2f0ae256/Datasets/Datseet3/lncSim.mat -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | License 2 | ========= 3 | Copyright (C) 2017 Jianxin Wang(jxwang@mail.csu.edu.cn),Chengqian Lu(chengqlu@csu.edu.cn) 4 | 5 | This program is free software; you can redistribute it and/or 6 | modify it under the terms of the GNU General Public License 7 | as published by the Free Software Foundation; either version 3 8 | of the License, or (at your option) any later version. 9 | 10 | This program is distributed in the hope that it will be useful, 11 | but WITHOUT ANY WARRANTY; without even the implied warranty of 12 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 13 | GNU General Public License for more details. 14 | 15 | You should have received a copy of the GNU General Public License 16 | along with this program; if not, see . 17 | 18 | Jianxin Wang(jxwang@mail.csu.edu.cn),Chengqian Lu(chengqlu@csu.edu.cn) 19 | School of Information Science and Engineering 20 | Central South University 21 | ChangSha 22 | CHINA, 410083 23 | 24 | Type: Package 25 | Title: Prediction of lncRNA-disease associations based on inductive matrix completion 26 | ================= 27 | Description: This package implements the SIMCLDA algorithm with inductive matrix completion framework, predicting lncRNA-disease 28 | associations. 29 | 30 | Files: 31 | 1.Dataset 32 | 33 | 1) lncSim.mat and disSim_Jaccard.mat store lncRNA similarity matrix and disease similarity matrix, respectively; 34 | 35 | 2) interMatrix.mat stores known lncRNA-disease association information; 36 | 37 | 3) lncRNA_Name.txt and diseases_Name.txt store lncRNA ids and disease ids, respectively; 38 | 39 | 2.Code 40 | 1) gKernel.m: function computing Gaussian interaction profile kernel; 41 | 42 | 2) pca_energy.m: function extracting feature vectors via PCA; 43 | 44 | 3) SIMC.m : function completing matrix; 45 | 46 | 4) SIMCLDA: predict potential lncRNA-disease associations; 47 | --------------------------------------------------------------------------------