Skip to content

Bioinformatics Tools

(You can write manual introductory notes here. The AI will not overwrite them.)

Bioinformatics software, packages, and analytical pipelines.

Last updated: 2026-07-27

Contents

Page Summary Tags Updated
ALADYNOULLI A Bayesian generative framework that jointly models longitudinal EHR diagnoses, age and polygenic risk to recover latent time-varying disease signatures and patient-specific signature loadings. tool, bayesian, gwas, rvas, machine-learning, statistical-genetics 2026-07-19
AlphaFold 2 A deep-learning system for protein structure prediction from amino-acid sequence and evolutionary information. tool, protein-structure-prediction, deep-learning, computational-biology 2026-07-19
AlphaFold 3 A diffusion-based model for joint structure prediction of proteins, nucleic acids, ligands, ions and modified residues. tool, protein-structure-prediction, deep-learning, computational-biology, drug-discovery 2026-07-19
AlphaGenome A unified DNA sequence model that predicts thousands of functional genomic tracks at base-pair resolution from 1 Mb of input sequence, for multimodal regulatory variant effect prediction. tool, deep-learning, functional-genomics, genomics, gene-expression, variant-effect-prediction, splicing, chromatin-accessibility 2026-07-26
AlphaMissense An AlphaFold-derived model fine-tuned on population frequency data to predict the pathogenicity of all possible human missense variants. tool, protein-structure-prediction, deep-learning, statistical-genetics, protein-language-model 2026-07-26
AUTOENCODIX An open-source, PyTorch-based end-to-end pipeline unifying five autoencoder architectures for standardized, comparable multi-omics representation learning. tool, deep-learning, computational-biology, cancer-genetics, single-cell, transcriptomics 2026-07-20
AutoMorph An automated deep learning pipeline for retinal vascular morphology quantification, image pre-processing, and quality grading. tool, deep-learning, computer-vision, ophthalmology 2026-07-19
BINN An open-source framework for building biologically informed neural networks from Reactome, used to classify clinical proteomic subphenotypes with SHAP-based pathway interpretability. tool, deep-learning, proteomics, bioinformatics, biomarker 2026-07-20
BioPAN A web tool that maps two-condition mammalian lipidomics data onto curated biosynthetic reactions and candidate genes. tool, lipidomics, pathway-analysis, bioinformatics, mass-spectrometry 2026-07-21
Boltz-2 A structural biology foundation model that jointly predicts biomolecular complex structure and small-molecule binding affinity, approaching FEP-level accuracy at over 1,000x the speed. tool, protein-structure-prediction, deep-learning, drug-discovery, computational-biology 2026-07-22
Borzoi A sequence-to-function model that predicts RNA-seq coverage directly from 524 kb of DNA, deriving expression, splicing and polyadenylation variant effects from one predicted coverage track. tool, deep-learning, functional-genomics, gene-expression, variant-effect-prediction, splicing 2026-07-26
Burden Heritability Regression (BHR) A method that estimates the heritability explained by the gene-wise burden of rare coding variants, and partitions it across genes and functional categories, while distinguishing genuine signal from population-stratification confounding. tool, statistical-genetics, rvas, gwas, bayesian 2026-07-23
CardiOmicScore A multitask deep learning framework that learns disease-specific proteomic and metabolomic risk scores for six cardiovascular diseases from UK Biobank data. tool, cardiovascular-disease, deep-learning, proteomics, metabolomics, polygenic-risk-score, risk-prediction 2026-07-20
CataPro An enzyme kinetic parameter prediction model (kcat, Km, kcat/Km) built on unbiased, sequence-similarity-clustered ten-fold cross-validation datasets, applied to discover and engineer a high-activity vanillin-producing enzyme. tool, enzyme-kinetics, deep-learning, enzyme-engineering, benchmarking 2026-07-20
CatPred A deep learning framework predicting enzyme kcat, Km, and Ki with query-specific uncertainty quantification, evaluated on sequence-identity-stratified out-of-distribution test sets. tool, enzyme-kinetics, deep-learning, uncertainty-quantification, protein-language-model 2026-07-20
Chai-1 A multi-modal foundation model for biomolecular structure prediction that uses protein language model embeddings to remain accurate without multiple sequence alignments. tool, protein-structure-prediction, deep-learning, computational-biology, drug-discovery, protein-language-model 2026-07-22
Chemosensory Mendelian Randomization Pipeline A bioinformatics pipeline for selecting valid genetic instruments for dietary exposures using taste and olfactory receptor variants. tool, genetics, mendelian-randomization, chemosensory-perception, diet 2026-07-19
CoMET (Cosmos Medical Event Transformer) A family of decoder-only transformers pretrained on 115 billion medical events from 118 million patients, generating patient health timelines autoregressively for zero-shot clinical prediction. tool, foundation-model, deep-learning, transformer, clinical-informatics, risk-prediction 2026-07-26
DECODE A proteogenomic pipeline for detecting, validating and quantifying amino acid substitutions produced by alternate RNA decoding. tool, pipeline, proteomics, mass-spectrometry, bioinformatics 2026-07-19
DeepMet A chemical language model that anticipates previously unrecognized mammalian metabolites and integrates with mass spectrometry data for de novo metabolite discovery. tool, metabolomics, mass-spectrometry, deep-learning, cheminformatics, structure-elucidation 2026-07-20
DeGAs / dPRS A latent-component decomposition of genome-wide SNP-trait associations used to compute an interpretable, component-resolved polygenic risk score. tool, polygenic-risk-score, gwas, statistical-genetics, disease-subtyping, clustering 2026-07-21
Delphi-2M A modified generative pretrained transformer (GPT-2) architecture designed to model continuous-time human disease progression and multi-disease occurrence trajectories. tool, deep-learning, multi-morbidity 2026-07-19
DETANGO A disentangled protein language model that decomposes a mutation's evolutionary implausibility into stability-driven and function-driven components, identifying stable-but-inactive variants and allosteric sites. tool, protein-language-model, deep-learning, enzyme-engineering, drug-target 2026-07-24
DLKcat A deep learning model that predicts enzyme turnover numbers (kcat) from protein sequence and substrate structure, used to parameterize enzyme-constrained genome-scale metabolic models at scale; its generalization claims are disputed. tool, enzyme-kinetics, deep-learning, metabolic-modeling 2026-07-20
DreaMS Deep Representations Empowering the Annotation of Mass Spectra, a transformer-based foundation model for mass spectrometry data. tool, mass-spectrometry, foundation-model, transformer 2026-07-20
DrugRepurposing Pipeline An R/Python codebase for benchmarking and performing TWAS-based drug candidate prioritisation using gene expression signature matching. tool, twas, drug-repurposing, gsea, spearman-correlation 2026-07-19
DrugCLIP A contrastive-learning system for rapid protein-pocket and small-molecule retrieval in virtual screening. tool, drug-discovery, deep-learning, cheminformatics, protein-structure-prediction 2026-07-22
Empirical Research Assistance (ERA) An AI system that systematically and automatically creates empirical software to solve scorable tasks. tool 2026-07-20
ESP (Enzyme Substrate Prediction) A general machine-learning model predicting whether a small molecule is a substrate of a given enzyme, using a task-specific fine-tuned ESM-1b enzyme representation. tool, enzyme-kinetics, machine-learning, protein-language-model, cheminformatics 2026-07-23
ENCODE-rE2G A supervised predictive model of enhancer-gene regulatory interactions. tool, statistical-genetics, enhancer, variant-to-gene, benchmarking 2026-07-26
Enformer A transformer-based sequence model predicting 5,313 human genomic tracks at 128 bp resolution from 200 kb of DNA, with a 100 kb receptive field — the common ancestor of Borzoi and AlphaGenome. tool, deep-learning, functional-genomics, gene-expression, variant-effect-prediction, transformer, enhancer 2026-07-26
EnzGFM An enzyme-specific protein language model using a hierarchically pre-trained Mamba-Transformer hybrid architecture, paired with an agentic pipeline for enzyme mutagenesis and engineering workflows. tool, protein-language-model, enzyme-engineering, deep-learning 2026-07-20
EnzyACT A deep learning method fusing protein-language-model sequence embeddings with a localized structural graph to predict how single and multiple point mutations change enzyme activity. tool, enzyme-kinetics, deep-learning, protein-language-model, enzyme-engineering 2026-07-22
EnzymeTuning A GAN-based top-down framework that globally optimizes kcat values within enzyme-constrained genome-scale metabolic models against in vivo proteomics and growth-phenotype data. tool, enzyme-kinetics, generative-adversarial-network, metabolic-modeling 2026-07-20
ePRS A transfer learning penalization framework that adapts polygenic scores from deeply phenotypically refined cohorts using large-scale GWAS summary statistics. tool, polygenic-risk-score, transfer-learning, genetics 2026-07-19
expiMap A biologically informed deep learning architecture for single-cell reference mapping that encodes query cells into interpretable gene-program latent dimensions. tool, deep-learning, single-cell, computational-biology 2026-07-20
EZSpecificity A cross-attention, SE(3)-equivariant graph neural network that predicts enzyme substrate specificity from enzyme-substrate sequence and structure. tool, enzyme-kinetics, deep-learning, protein-language-model, cheminformatics 2026-07-22
FFRangio A wire-free computational method that estimates fractional flow reserve (FFR) using standard coronary angiography. cardiology, hemodynamics, medical-imaging, machine-learning, computational-simulation 2026-07-19
FIDDLE A deep learning method that predicts molecular formulas directly from tandem mass spectra, outperforming SIRIUS and BUDDY on accuracy and runtime. tool, mass-spectrometry, deep-learning, cheminformatics, structure-elucidation 2026-07-20
FUSION A suite of tools for performing transcriptome-wide and regulome-wide association studies (TWAS and RWAS) using summary statistics. tool, twas, regulome, gene-expression 2026-07-19
flashfmZero An R package for latent-factor GWAS and joint Bayesian fine-mapping of high-dimensional correlated traits. tool, r-package, fine-mapping, multi-trait, statistical-genetics 2026-07-19
Gene-SGAN A multi-view, weakly-supervised deep clustering method that discovers disease subtypes jointly from imaging and genetic data. tool, deep-learning, generative-adversarial-network, medical-imaging, disease-subtyping, clustering, genetics 2026-07-21
GENEB A diagnostic benchmark evaluating frozen representations from 40 genomic foundation models across 100 tasks in 13 functional categories under a unified linear-probing protocol. tool, benchmark, benchmarking, foundation-model, genomics, deep-learning 2026-07-26
Geneformer A transformer-based model for single-cell transcriptomics designed to enable transfer learning in network biology. tool, single-cell, foundation-model, transcriptomics 2026-07-20
Genomic SEM An R package for structural equation modeling of the joint genetic architecture of multiple traits directly from GWAS summary statistics. tool, r-package, gwas, statistical-genetics, polygenic-risk-score, bayesian 2026-07-21
gpu-coloc A GPU-accelerated tool for genetic colocalization analysis across millions of traits. tool, colocalization, statistical-genetics 2026-07-19
GMMAT A generalized linear mixed model association test for GWAS that controls for population structure and relatedness. tool, gwas, statistical-genetics, relatedness 2026-07-21
GWIS A method for approximating GWAS summary statistics for a phenotype defined as a function of other phenotypes. tool, gwas, statistical-genetics, summary-statistics, method 2026-07-20
Heckmann Enzyme Turnover ML Model An early (2018) machine learning model predicting E. coli enzyme turnover numbers from structural, network, and biochemical features, used to improve proteome-allocation genome-scale metabolic models. tool, enzyme-kinetics, machine-learning, metabolic-modeling, protein-structure-prediction 2026-07-20
HyPrColoc An efficient deterministic Bayesian algorithm for multi-trait colocalization using GWAS summary statistics. tool, colocalization, bayesian, multi-trait, gwas 2026-07-19
IWAE Cross-Platform Metabolomics Imputation An ensemble of importance-weighted autoencoders that imputes an entire Metabolon metabolomics dataset from a different platform's features. tool, metabolomics, deep-learning, imputation, statistics 2026-07-20
JointPRS A data-adaptive hierarchical Bayesian framework for multi-population genetic risk prediction incorporating genetic correlation. tool, polygenic-risk-score, multi-ancestry, statistical-genetics 2026-07-19
KcatNet A geometric deep learning model for genome-wide enzyme turnover number (kcat) prediction that localizes catalytic pockets and generalizes to enzymes dissimilar from its training set. tool, enzyme-kinetics, deep-learning, protein-language-model, metabolic-modeling 2026-07-22
LIPID Imputation An elastic-net framework for harmonising plasma lipidomic datasets measured at different chromatographic resolutions. tool, lipidomics, lipid-metabolism, imputation, cardiovascular-disease, statistics 2026-07-20
LIPID MAPS An open lipidomics infrastructure providing community standards, curated databases, analysis tools, spectra, pathways, and training. project, lipidomics, bioinformatics, mass-spectrometry, dataset 2026-07-21
LIPID MAPS Lipidomics Tools Guide An interactive decision guide for selecting open, graphical software across the major stages of lipidomics data analysis. tool, lipidomics, bioinformatics, mass-spectrometry, pipeline 2026-07-21
LipiDetective A transformer-based deep learning model that identifies molecular lipid species directly from tandem mass spectra, independent of instrument or experimental setup. tool, lipidomics, mass-spectrometry, transformer, deep-learning, tum 2026-07-21
LeafCutter Annotation-free quantification of RNA splicing from split RNA-seq reads via intron-excision clusters, used for differential splicing and sQTL mapping. tool, splicing, transcriptomics, statistical-genetics, twas 2026-07-26
LeafCutter2 Extends LeafCutter by classifying each splice junction as productive or NMD-inducing from start/stop codons alone, enabling unproductive-splicing QTL (u-sQTL) mapping. tool, splicing, transcriptomics, statistical-genetics, colocalization 2026-07-26
LipidIN A platform-independent lipidomics annotation framework combining an ultra-fast spectral query engine with a "reverse lipidomics" fingerprint-regeneration network. tool, lipidomics, mass-spectrometry, deep-learning, transformer 2026-07-20
LimeMap A curated, editable pathway map for visualizing omega-3 and omega-6 lipid mediators, related enzymes, receptors, and ion channels. tool, lipidomics, pathway-analysis, inflammation, computational-biology 2026-07-21
McMLP A two-step deep learning method using coupled multilayer perceptrons to predict post-dietary-intervention metabolite concentrations from baseline gut microbiome and metabolome. tool, deep-learning, metabolomics, diet, nutrition 2026-07-20
MendelianRandomization An R package for performing Mendelian randomization analyses using summarized data. tool, r-package, mendelian-randomization 2026-07-19
M-CSA (Mechanism and Catalytic Site Atlas) A manually curated database of enzyme catalytic residues and stepwise reaction mechanisms, formed by merging the MACiE and CSA databases. dataset, bioinformatics, enzyme-kinetics, reference 2026-07-23
Multi-scale Erythrocyte Metabolism Platform A structural systems biology workflow (GEM-PRO) integrating protein structures, molecular dynamics, and genome-scale modeling of the human erythrocyte to mechanistically predict how sequence variants alter drug responses. tool, metabolic-modeling, protein-structure-prediction, pharmacogenetics, computational-biology 2026-07-20
MetaboXcan A TWAS-analogous framework that trains genetic predictors of plasma metabolite levels and performs four complementary association analyses to link genetic loci to disease via metabolic mechanisms. tool, metabolomics, twas, statistical-genetics, imputation 2026-07-20
MetaXcan A suite of command-line tools for association mapping of imputed transcriptome and other molecular traits. tool, twas, pwas, association-mapping 2026-07-19
MetDNA3 A two-layer interactive networking platform for untargeted metabolomics that fuses a GNN-expanded metabolic reaction network with a data-driven feature network. tool, metabolomics, mass-spectrometry, deep-learning, cheminformatics 2026-07-20
MetGenX A structure-informed encoder-decoder neural network that generates de novo metabolite structures from MS2 spectra using retrieved template molecules. tool, metabolomics, mass-spectrometry, deep-learning, cheminformatics, structure-elucidation 2026-07-20
MIST Metabolite Inference with Spectrum Transformers, a machine learning tool for molecular structure elucidation from mass spectrometry data. tool, mass-spectrometry, machine-learning, transformer 2026-07-19
MIXPRS A multi-population and multi-method polygenic risk score integration framework that operates solely on GWAS summary statistics. tool, polygenic-risk-score, statistical-genetics, multi-ancestry, data-fission 2026-07-19
Multi-INTACT A Bayesian method that jointly models multiple gene products (e.g., transcript and protein levels) with TWAS and colocalization evidence to implicate causal genes. tool, twas, pwas, colocalization, bayesian, statistical-genetics 2026-07-20
mtVAE A variational autoencoder trained on population-scale blood metabolomics that learns nonlinear, pathway-organized latent representations transferable to unseen disease cohorts. tool, metabolomics, deep-learning, statistics, biomarker 2026-07-20
MultiSuSiE A Python package for multi-ancestry fine-mapping designed for whole-genome sequencing data. tool, fine-mapping, multi-ancestry, wgs 2026-07-19
mvSuSiE An R package for multitrait fine-mapping extending the Sum of Single Effects model. tool, fine-mapping, multitrait 2026-07-19
N-GWAMA / MA-GWAMA Two multivariate GWAS meta-analysis methods that pool summary statistics of genetically correlated traits while correcting for unknown sample overlap. tool, gwas, statistical-genetics, summary-statistics, multi-trait 2026-07-20
NAC4ED A high-throughput computational platform that screens enzyme mutants for catalytic activity using near-attack-conformation population from molecular dynamics, avoiding transition-state searches. tool, enzyme-kinetics, enzyme-engineering, computational-biology 2026-07-23
NetMoST A network-based machine learning method that clusters patients into disease biotypes from polygenic SNP allele biomarkers. tool, machine-learning, polygenic-risk-score, disease-subtyping, clustering, neuropsychiatric 2026-07-21
OmicsPred A centralised resource for hosting and disseminating genetic prediction models of multi-omic traits. tool, dataset, imputation, transcriptomics, proteomics, metabolomics 2026-07-19
Open Targets A public-private platform for therapeutic target identification and prioritization, integrating genetics, omics, and drug data. tool, drug-discovery, genetics, gwas, variant-to-gene 2026-07-20
OpenGWAS A public database and API for genome-wide association study (GWAS) summary statistics. tool, dataset, gwas, mendelian-randomization 2026-07-19
P-NET A biologically informed, fully-interpretable sparse deep neural network that encodes 3,007 curated pathways to predict prostate cancer disease state from mutation/copy-number data, implicating MDM4 as a therapeutic target. tool, deep-learning, cancer-genetics, oncology, computational-biology 2026-07-20
PanMETAI A TabPFN tabular-foundation-model-based diagnostic algorithm integrating ¹H NMR serum metabolomics with clinical/protein features to detect pancreatic ductal adenocarcinoma. tool, metabolomics, nmr-spectroscopy, machine-learning, oncology, biomarker 2026-07-20
PGS Catalog An open, expertly-curated database of published polygenic scores with full scoring files and standardized metadata, created to address widespread PGS irreproducibility. dataset, polygenic-risk-score, genetics, reference 2026-07-20
PGS Catalog Calculator (pgsc_calc) A reproducible Nextflow pipeline for calculating PGS Catalog scores on individual-level data with genetic-ancestry-aware normalization. tool, polygenic-risk-score, pipeline, nextflow 2026-07-20
Pangolin A deep learning model predicting tissue-specific splice site usage as well as probability, trained on quantitative SpliSER measurements across four tissues and four species. tool, splicing, variant-effect-prediction, deep-learning, medical-genomics, benchmarking 2026-07-26
phASER Read-backed haplotype phasing using RNA-seq reads, producing long-range rare-variant phase and haplotype-level allelic expression quantification. tool, transcriptomics, statistical-genetics, medical-genomics, variant 2026-07-26
PhenomeXcan A gene-based, queryable resource mapping the transcriptome-mediated effects of 8.87 million GWAS variants across 4,091 traits and 22,515 genes, prioritized with the fastENLOC colocalization method. tool, twas, gwas, colocalization, bayesian, dataset 2026-07-20
Pleiotropic Decomposition Regression (PDR) A method that decomposes a SNP's multi-trait effect-size vector into a small number of independent, biologically interpretable pleiotropic components. tool, gwas, statistical-genetics, polygenic-risk-score, pleiotropy 2026-07-21
PLINK A comprehensive open-source C/C++ toolset for whole-genome association and population-based linkage analyses, highly optimized with bit-parallel operations. tool, gwas, statistical-genetics, quality-control 2026-07-19
PPIFlow A flow-matching generative model for de novo protein binder design that, combined with an in silico affinity-maturation pipeline, produces picomolar-to-nanomolar binders without experimental optimization. tool, protein-structure-prediction, deep-learning, drug-discovery, enzyme-engineering 2026-07-22
PredictDB A repository of genetic prediction models of tissue-specific gene expression and splicing. tool, dataset, transcriptomics, gene-expression 2026-07-19
PRSet A pathway-based polygenic risk scoring tool that computes and tests gene-set-restricted PRS instead of a single genome-wide score. tool, polygenic-risk-score, gwas, statistical-genetics, disease-subtyping, clustering 2026-07-21
Protenix An open-source reproduction of AlphaFold 3 for predicting structures of proteins, ligands, nucleic acids and biomolecular complexes. tool, protein-structure-prediction, deep-learning, computational-biology, bioinformatics 2026-07-19
RealKcat A gradient-boosted enzyme kinetics classifier trained on a manually re-curated 27k-entry dataset, designed specifically to capture loss of catalytic activity from active-site mutations. tool, enzyme-kinetics, machine-learning, protein-language-model, benchmarking 2026-07-22
RICE (polygenic Risk predictions Integrating Common and rarE variants) A PRS framework that constructs separate common-variant and rare-variant scores via ensemble learning and gene-level burden testing, then combines them, improving prediction over common-variant-only PRS especially for lipid traits and in non-European ancestries. tool, polygenic-risk-score, rvas, multi-ancestry, statistical-genetics 2026-07-27
Recon3D The most comprehensive human genome-scale metabolic network reconstruction at publication, integrating 3D metabolite/protein structure data to enable structurally-resolved analysis of metabolic gene variation and drug response. tool, metabolic-modeling, genomics, protein-structure-prediction, computational-biology 2026-07-20
RatXcan A cross-species extension of PrediXcan/TWAS to outbred heterogeneous stock rats, correcting for close familial relatedness and target-trait polygenicity-driven inflation. tool, twas, statistical-genetics, multi-trait, gwas 2026-07-20
REGENIE A highly efficient machine learning method for genome-wide and exome-wide association studies in large cohorts. tool, gwas, statistical-genetics 2026-07-19
Ret-AAE A deep learning framework utilizing retinal adversarial autoencoders to generate low-dimensional representations of CFP and OCT images. tool, deep-learning, computer-vision, ophthalmology, cohort 2026-07-19
RisQ A transformer-based multimodal framework that learns a unified representation of human health across diseases, modalities, and time. tool, multimodal, risk-prediction, deep-learning 2026-07-19
scBERT A large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data. tool, single-cell, foundation-model, transcriptomics 2026-07-20
scPrediXcan A cell-type-specific TWAS framework that trains deep-learning gene-expression predictors (ctPred) from single-cell data, outperforming canonical bulk/pseudobulk TWAS at identifying candidate causal genes. tool, twas, single-cell, deep-learning, statistical-genetics 2026-07-26
Spec2Mol An end-to-end encoder-decoder deep learning architecture that translates MS/MS spectra directly into candidate SMILES molecular structures. tool, mass-spectrometry, metabolomics, deep-learning, cheminformatics, structure-elucidation 2026-07-20
SSimp A method and software for directly imputing GWAS summary statistics at untyped variants from tag-SNV summary statistics and reference-panel LD. tool, gwas, statistical-genetics, summary-statistics, imputation 2026-07-20
scCello A cell-ontology-guided transcriptome foundation model adding cell-type coherence and ontology-alignment losses to pretraining, improving generalization to unseen cell types, tissues, and donors. tool, single-cell, foundation-model, transcriptomics 2026-07-20
scFoundation A large-scale foundation model for single-cell transcriptomics containing 100 million parameters. tool, single-cell, foundation-model, transcriptomics 2026-07-20
scGPT A generative pretrained transformer foundation model for single-cell multi-omics. tool, single-cell, foundation-model, transcriptomics 2026-07-20
SCimilarity An autoencoder-based metric learning framework for cell atlas scale search and annotation. tool, single-cell, foundation-model, transcriptomics 2026-07-19
scVI Single-cell Variational Inference model for deep generative modeling of single-cell transcriptomics. tool, single-cell, transcriptomics, deep-learning 2026-07-19
SDPRX A hierarchical Bayesian cross-population complex trait prediction tool using a Dirichlet process mixture model. tool, polygenic-risk-score, multi-ancestry, statistical-genetics, bayesian 2026-07-19
sMultiXcan An extension of MetaXcan that integrates predicted gene expression across multiple tissues to detect gene-trait associations. tool, twas, multi-tissue, summary-statistics 2026-07-19
SpliceAI A 32-layer dilated residual network that predicts splice donor and acceptor probability from 10 kb of pre-mRNA sequence, yielding the delta score used to call cryptic splice variants. tool, statistical-genetics, splicing, variant-effect-prediction, deep-learning 2026-07-26
sPrediXcan A bioinformatics tool that computes gene-level association summary statistics from GWAS summary statistics and gene expression prediction models. tool, twas, gene-expression, summary-statistics 2026-07-19
Structural Km Predictor A genome-scale, organism-independent Michaelis constant (Km) prediction model combining a graph-neural-network substrate fingerprint with an enzyme-sequence representation. tool, enzyme-kinetics, machine-learning, metabolic-modeling 2026-07-20
SuShiE A Python package for multiancestry fine-mapping of molecular phenotypes using JAX. tool, fine-mapping, multi-ancestry, jax 2026-07-19
SuSiEx A command-line tool for cross-population genetic fine-mapping. tool, fine-mapping, multi-ancestry 2026-07-19
TopEC A 3D graph neural network that predicts Enzyme Commission classes from localized, angle-and-distance-aware active-site geometry rather than global fold or sequence homology. tool, protein-structure-prediction, deep-learning, bioinformatics 2026-07-27
Tractor A local-ancestry-informed generalized linear model for GWAS in admixed cohorts, producing ancestry-specific effect sizes. tool, gwas, statistical-genetics, admixture, local-ancestry, multi-ancestry 2026-07-21
Tractor-Mix A local-ancestry-informed generalized linear mixed model enabling well-calibrated GWAS in admixed cohorts with sample relatedness. tool, gwas, statistical-genetics, admixture, local-ancestry, relatedness, multi-ancestry, r-package 2026-07-21
TranscriptFormer A generative, autoregressive single-cell foundation model trained on 112 million cells across 12 species spanning 1.53 billion years of evolution, outperforming UCE on evolutionarily distant cross-species tasks. tool, single-cell, foundation-model, transcriptomics, protein-language-model 2026-07-20
TurNuP An organism-independent turnover number (kcat) prediction model combining differential reaction fingerprints with a retrained protein Transformer, designed to generalize to enzymes dissimilar from its training set. tool, enzyme-kinetics, machine-learning, metabolic-modeling 2026-07-20
TwoSampleMR An R package for performing two-sample Mendelian randomization analyses using GWAS summary data. tool, r-package, mendelian-randomization 2026-07-19
UCE (Universal Cell Embedding) A 650M-parameter zero-shot foundation model mapping any cell from any tissue/species into a shared embedding space via ESM2 protein-embedding gene tokenization. tool, single-cell, foundation-model, transcriptomics, protein-language-model 2026-07-20
UniKP A unified pretrained-language-model framework predicting enzyme kcat, Km, and kcat/Km from protein sequence and substrate structure, with an environmental-factor extension (EF-UniKP). tool, enzyme-kinetics, machine-learning, protein-language-model 2026-07-20
WikiPathways An open, community-curated pathway database that provides machine-readable biological pathways for visualization and multi-omic analysis. tool, bioinformatics, pathway-analysis, metabolomics, lipidomics 2026-07-21

Categories

Recent Changes

  • 2026-07-27: Deep-dive ingests for primary manuscripts: augmented RICE and TopEC with exact mathematical formulations, complete benchmark tables, and §3.3A claim-level citations
  • 2026-07-26: Cleared ingress/. Added GENEB (40-model genomic foundation-model benchmark) and CoMET (Epic Cosmos medical-event transformer)
  • 2026-07-26: Read the Pangolin and Enformer primary sources. Added Pangolin; replaced the Enformer stub with a fully sourced page (confidence: low → high). Recorded a Disputed note on MFASS auPRC values differing between the Pangolin and AlphaGenome papers
  • 2026-07-26: Read and ingested five primary sources on splicing and RNA-seq models. Added Borzoi, LeafCutter, LeafCutter2, phASER and an Enformer stub (primary paper not read); rewrote SpliceAI from its own primary source rather than a secondary description
  • 2026-07-26: Deep-integration pass on the AlphaGenome primary source (Avsec et al. 2026, Nature 649:1206–1217): rewrote AlphaGenome with architecture, training regime, full benchmark tables, variant scoring strategies, ablations and limitations; augmented SpliceAI, ENCODE-rE2G, AlphaMissense and scPrediXcan with cross-links to the new wiki/concepts/ pages Sequence-to-Function Genomic Models and Direction-of-Effect Assignment at GWAS Loci
  • 2026-07-23: Converted 4 user-supplied manuscript PDFs and integrated their findings: added Burden Heritability Regression (BHR) (Weiner/Nadig et al. 2023, Nature) and RICE (Williams et al. 2026, Nat Commun), alongside companion concept pages in wiki/concepts/ on trait-tail architecture and depression's rare-variant architecture
  • 2026-07-23: Ingested a user-supplied deep-research digest on predicting catalytic competence of enzyme-ligand complexes (kept in ingress/ per the user's instruction, not moved to raw/); independently verified and downloaded all 8 cited primary sources before writing. Added ESP (Enzyme Substrate Prediction), TopEC, NAC4ED, and M-CSA, alongside a companion framework page and 5 case-study concepts in wiki/concepts/
  • 2026-07-22: Ingested a user-supplied report on deep learning in structural biology/drug discovery; verified all DOIs (two used bioRxiv's newer 10.64898 prefix, initially mistaken for fabricated) and downloaded/read primary sources before writing. Added Chai-1, Boltz-2, PPIFlow, AlphaMissense, DETANGO, RealKcat, KcatNet, EnzyACT (full text), and EZSpecificity (abstract-only, Nature paywalled, confidence medium); augmented DrugCLIP with verified ProFSA/GenPack/GenomeScreenDB detail. Corrected several report inaccuracies against primary sources
  • 2026-07-21: Added LIPID MAPS, its Lipidomics Tools Guide, BioPAN, LimeMap, and WikiPathways from a 13-paper lipidomics infrastructure ingest; linked LipiDetective to the new shorthand reference
  • 2026-07-21: Added 6 tools from a 13-paper polygenic-risk-score disease-subtyping ingest batch: PRSet, NetMoST, Gene-SGAN, DeGAs / dPRS, Genomic SEM, and Pleiotropic Decomposition Regression (PDR)
  • 2026-07-21: Added Tractor-Mix (local-ancestry- and relatedness-aware GWAS method) from a Nature Genetics paper, plus stubs for its predecessor Tractor and dependency GMMAT
  • 2026-07-20: Added Open Targets
  • 2026-07-20: Created PGS Catalog and substantially expanded PGS Catalog Calculator (pgsc_calc), which previously had an empty sources field
  • 2026-07-20: Added UCE, scCello, and TranscriptFormer (new single-cell foundation models)
  • 2026-07-20: Augmented Geneformer, scGPT, scBERT, and scFoundation with their primary methods papers