Awesome Computational Biology

A knowledge collection of databases, software and papers related to computational biology.

Computational biology involves the development and application of data-analytical and theoretical methods, mathematical modelling and computational simulation techniques to the study of biological, ecological, behavioural, and social systems. - Wikipedia

Contents

• Databases
  • scRNA
  • Compound
  • Pathway
  • Mass Spectra
  • Protein
  • Genome
  • Disease
  • Interaction
  • Clinical Trial
• API
• Preprocess
• Machine Learning Tasks and Models
  • Drug Response Prediction
  • Drug Repurposing
  • Drug Target Interaction
  • Compound Protein Interaction
  • Pre-trained embedding
  • LLM for biology

Databases

scRNA

• Gene Expression Omnibus - Public functional genemics database.
• Single Cell PORTAL - Public database for single cell RNA.
• Single Cell Expression Atlas - Public database for single cell RNA.

Compound

• PubChem - One of the biggest chemical database such as compounds, genes and proteins.
• ChEBI - Chemical database focused on small chemical compounds.
• ChEMBL - Database of bioactive molecules with drug-like properties.
• ChemSpider - Chemical structure database.
• KEGG COMPOUND - Collection of small molecules and biopolymers.
• LIPID MAPS - Database of lipids.
• Rhea - Database of chemical reactions.
• Drug Repurposing Hub - Collections of drug repurposing data containing drug, moa, target etc.
• Therapeutic Target Database - collections of drug-target, target-disease, and drug-disease dataset.
• ZINC ligand discovery database - Free database of commercially-available compounds for virtual screening.
• MoleculeNet - Benchmark for molecular machine learning.
• Ames Mutagenicity dataset - Dataset for predicting mutagenicity.
• ADCdb - Database for antibody-drug conjugates.

Pathway

• PathwayCommons - Database of Pathways and Interactions.
• KEGG PATHWAY - Collection fo drawn pathway maps.
• WikiPathways - Database of biological pathways.

Mass Spectra

• MassBank - Open souce databases and tools for mass spectrometry reference spectra.
• MoNA MassBank of North America - Meta database of metabolite mass spectra, metadata and associated compounds.

Protein

• THE HUMAN PROTEIN ATLAS - One of the biggest human protein database contained cells, tissues, and organs.
• PROTEIN DATA BANK - Database of the 3D shapes of proteins, nucleic acids, and complex assemblies.
• UniProt - The collection of functional information on proteins.
• AlphaFold Protein Structure Database - Database of 3D protein structures.
• RCSB Protein Data Bank (PDB) - Repository of 3D structural data of large biological molecules.
• Critical Assessment of Structure Prediction (CASP) - Experiment for advancing the methods of predicting protein structure from sequence.
• Uniclust - Collection of clustered protein sequence databases.
• CATH database - Hierarchical classification of protein domain structures.

Genome

• Human Genome Resources at NCBI - Database of image, proteomics, transcriptomics and systems biology.
• GenBank - Database of genetic sequence offered by NCBI.
• UCSC Genome Browser - Genome blowser offered by UCSC.
• cBioPortal - Database of Cancer Genomics. This has overall metaview for a lot of patients.
• 10x Genomics Dataset - Collection of single-cell datasets.
• The Genotype-Tissue Expression (GTEx) - Resource for studying human gene expression and regulation.
• Dependency Map (DepMap) - Genome-wide CRISPR-Cas9 screens in cancer cell lines.
• Catalogue Of Somatic Mutations In Cancer (COSMIC) - Comprehensive resource for exploring somatic mutations in human cancers.
• MGnify - Free resource for archiving, analysis, and browsing of metagenomic and metatranscriptomic data.
• JASPAR - Open-access database of curated, non-redundant transcription factor binding profiles.

Disease

• KEGG DRUG - Comprehensive drug information resource for approved drugs.
• DrugBank - A database of drug and target maintained by the University of Alberta.

Interaction

• Drug Gene Interaction
  • DGIdb - A database of drug-gene interactions and the druggable genome.
  • Comparative Toxicogenomics Database - A database of Chemical-gene interactions, Chemical-disease associations, Gene-disease associations, and Chemical-phenotype associations.
  • SNAP - A dataset which contains Drug-gene interactions.
  • Therapeutics Data Commons - A database for a lot of tasks such as drug-target, drug-response, drug-drug interaction.
• Drug (-Cell line) Response
  • NCI60 A database which focus on 60 cancer cell lines with many drugs.
  • Genomics of Drug Sensitivity in Cancer (GDSC) - A database of drug sensitibity which has 1000 human cancer cell lines and 100s compounds.
  • Cancer Cell Line Encyclopedia - A database of cancer cell lines. This has 1000 cell lines.
  • CellMiner Cross Database (CellMinerCDB) - Integration of multiple cancer cell line databases.
• Chemical Protein Interaction
  • STITCH - A database of Chemical Protein Interaction.
  • BindingDB - A database of compounds and targes.
  • PDBBind - Database of experimentally measured binding affinity data for biomolecular complexes.
  • CrossDocked2020 - Large-scale dataset for machine learning in structure-based virtual screening.
• Protein-Protein Interaction
  • STRING - Protein-Protein Interaction Networks for several organisms.
  • BioGRID - Database of Protein, Genetic and Chemical Interactions.
  • HIPPIE - Human Protein-Protein Interaction database.
• Knowledge Graph
  • Drug Mechanism Database (DrugMechDB): database of the mechanism of action from a drug to a disease.
  • DRKG - A library for biological knowledge graph.

Clinical Trial

• ClinicalTrials.gov - Database of privately and publicly funded clinical studies.
• ICD10 - International Classification of Diseases, 10th revision.
• EU Drug Regulating Authorities Clinical Trials DB (EudraCT) - European database of clinical trials.
• MIMIC-IV - Freely accessible critical care database.

API

• PubMed esearch: API for searching articles in PubMed.

Preprocess

• Chemistry Development Kit - A software of cheminformatics and Machine Learning.
• RDKit - A software of cheminformatics and Machine Learning.
• Scanpy - scRNA analysis library in Python.
• Seurat - scRNA analysis library in R.

Machine Learning Tasks and Models

Drug Response Prediction

• drGAT: A model for drug response prediction with gene explainability with attention mechanism.
• MOFGCN: GCN + heterogeneous network
• DeepDSC: Autoencoder + Fully Connected NN
• DGDRP: Multi-view embedding NN.
• DeepAEG: GNN Embedding + Attention

Drug Repurposing

• DeepPurpose - A DL Library for Drug Repurposing.

Drug Target Interaction

• NeoDTI - A library for Drug Target Interaction.

Compound Protein Interaction

• MCPINN - A library for drug discovery using Compound Protein Interaction and Machine Learning.
• TransformerCPI - A library for Compound Protein Interaction prediction using Transformer.

Pre-trained embedding

• Evolutionary Scale Modeling - a library for protein embeddings.
• ChemBERTa-2 - a library for chemical embeddingg and prediction.

LLM for biology

• AI4Chem/ChemLLM-7B-Chat - LLM for chemical and molecule science
• BioGPT - LLM for Biomedical text generation
• GeneGPT - LLM for biomedical information with several API.
• GenePT - foundation LLM for single cell data
• scPRINT - scPRINT is pretrained on 50M cells to denoise and perform zero imputation of any single cell RNAseq profile.