Bioinformatics and Systems Medicine Laboratory

We listed some previous and ongoing projects. Please contact us if you need more information or support.

DrVAEN: Drug response prediction through deep Variational Autoencoder model followed by Elastic Net.

INSCT: Integrating millions of single cells using batch-aware triplet neural networks.

Deep4mC: A deep learning method for systematic assessment and computational prediction of DNA N4-methylcytosine sites.

DeepFun: A tissue and cell type specific deep learning sequence-based model to decipher noncoding variant effects.

DrivAER: Identification of driving transcriptional programs in single-cell RNA sequencing data.

TSEA-DB: A trait-tissue association map for human complex traits and diseases.

VISDB: A knowledgebase containing the most comprehensive DNA virus integration sites and also the integration sites for several typical RNA retrovirus.

CleftGeneDB: The cleft gene annotation database aiming to provide a resource or reference for the midfacial development and the related disease studies for mouse and human.

MotifPredictor: With miRNA-TF, miRNA-gene, TF-miRNA, and TF-gene interactions as input, this C package can identify specific motifs (miRNA-TF-gene feed-forward and feedback loops) from networks.

ANCO-GeneDB: annotations and comprehensive analysis of candidate genes for alcohol, nicotine, cocaine and opioid dependence

deTS: An R package to identify the most relevant tissues for candidate genes or for gene expression profiles.

CNet: A JAVA package that detects groups of genomic signatures that are associated with clinical and phenotypical outcomes.

TissGDB: Tissue-specific Gene annotation DataBase in cancer for better understanding tissue-specificity and identifying targetable alterations of tissue-specific genes.

scRNASeqDB: A database for gene expression profiling in human single cell by RNA-seq.

SZGR: Schizophrenia Gene Resource provides a comprehensive online resource for schizophrenia genetics studies.>

mutLBSgeneDB: A Database of Genes with Mutated Ligand Binding Sitese. A comprehensive database for cataloging mutated ligand binding site genes for better understanding of mutated ligand binding sites and identifying potential druggable ligand binding sites in cancerous cells.

ccmGDB: Cancer Cell Metabolism Gene Database. A comprehensive database for cataloging cancer cell metabolism genes for better understanding of mutational landscapes of all metabolism genes and identifying potential druggable cancer cell metabolism targets in cancerous cells.

TSGene 2.0: Tumor Suppressor Gene Database version 2.0 A comprehensive database for tumor suppressor genes in multiple model organisms and their related biological information (tumor types, gene expression, mutations, pathways, protein-protein interactions, and non-coding genes, etc). Major updates include: added and curated hundreads more TSGenes (1022 coding and 192 non-coding genes now), added pan-cancer gene expression, somatic mutation, miRNA data, added many pre-computed results (e.g. differential expression, mutation hotspots, networks, loss of function), data visulization, among others.

EW_dmGWAS Edge-weighted dense module search for genome-wide association studies and gene expression profiles. This is an upgraded algorithm of our previous dmGWAS to boost GWAS signals in a node- and edge-weighted protein-protein interaction network. In EW_dmGWAS, we utilize condition-specific gene expression profiles for edge weights. Tool is available by clicking here.

CCG: The Catalogue of Cancer Genes database is an integrated Interactome of Cancer Genes.

DESnowball: method to identify downstream target genes that are affected by a recurrent driver mutation.

VirusFinder: software to detect viruses and their integration sites in host genomes through next generation sequencing data.

CNVannotator: A comprehensive annotation server for copy number variation (CNV) in humans.

TSGene: Tumor Suppressor Gene Database: A comprehensive database for tumor suppressor genes in multiple model organisms and their related biological information (tumor types, gene expression, mutations, pathways, protein-protein interactions, and non-coding genes, etc).

DT tool (Drug-target extraction tool in Python) : source code, examples, and documents can be downloaded here.

glad (gene length bias detection in GWAS datasets): source code to detect gene length bias as in Jia et al.

Suppl. for Genomics (2004) 84:785-795 " The influence of neighboring nucleotide composition on single nucleotide polymorphisms (SNPs) in the mouse genome and its comparison with human SNPs" .