Find open-source science resources

Structure-aware protein language model using 3D structural vocabulary (Foldseek) for joint sequence-structure pretraining, achieving SOTA on protein engineering and fitness prediction benchmarks (ICML 2024, Westlake University & Repl)

This package addresses the mean-variance relationship in spatially resolved transcriptomics data. Precision weights are generated for individual observations using Empirical Bayes techniques. These weights are used to rescale the data and covariates, which are then used as input in spatially variable gene detection tools.

Scientific foundation model and AI research copilot for idea generation, cross-disciplinary connection discovery, and hypothesis formation; trained with a decoupled reward-comment RL architecture and achieves GPT-4o-competitive novelty/rationale on STEM and social-science idea-generation benchmarks (270+ stars, MIT License, 2026)

This tutorial aims to illustrate the process of computing classical molecular interaction potentials from protein structures step by step, using the BioExcel Building Blocks library (biobb)

This tutorial aims to illustrate how to compute a fast-growth mutation free energy calculation, step by step, using the BioExcel Building Blocks library (biobb). The particular example used is the Staphylococcal nuclease protein (PDB code 1STN), a small, minimal protein, appropriate for a short tutorial.

The Bibliographic Ontology Specification provides main concepts and properties for describing citations and bibliographic references (i.e. quotes, books, articles, etc) on the Semantic Web.

Bilingual protein language model translating between protein sequence and structure, finetuned from ProtT5-XL on 17M AlphaFoldDB structures using Foldseek's 3Di structural alphabet, enabling sequence-to-structure prediction, structure-to-sequence inverse folding, and unified protein representation learning (RostLab, 310+ stars)

systemPipeR is a workflow management environment for reproducible data analysis that integrates R with command-line software. It enables researchers to design, execute, and report complex workflows on local machines and HPC systems. The framework combines R-based analysis with external tools through a Common Workflow Language (CWL) interface, manages workflow dependencies and restart capabilities, and automatically generates reproducible scientific analysis reports. The companion package systemPipeRdata provides ready-to-use workflow templates that simplify workflow setup and customization. Alternatively, workflow templates can be loaded from dedicated GitHub repositories.

Multimodal deep learning framework integrating peptide-MHC protein sequence, structure, and biochemical properties to predict class-I immunogenicity for infectious disease epitopes and cancer neoepitopes with cancer-wildtype contrastive learning, enabling personalized vaccine design (Krishnaswamy Lab, Yale University)

cogeqc aims to facilitate systematic quality checks on standard comparative genomics analyses to help researchers detect issues and select the most suitable parameters for each data set. cogeqc can be used to asses: i. genome assembly and annotation quality with BUSCOs and comparisons of statistics with publicly available genomes on the NCBI; ii. orthogroup inference using a protein domain-based approach and; iii. synteny detection using synteny network properties. There are also data visualization functions to explore QC summary statistics.

First benchmark for automatic video generation from scientific papers (NeurIPS 2025)

RFantibody is a pipeline for structure-based de novo antibody and nanobody design, integrating backbone design with RFdiffusion, sequence design with ProteinMPNN, and structure prediction with RoseTTAFold2. It provides a comprehensive toolset for generating and filtering high-quality antibody designs.

Interactive personal genome analysis toolkit using Claude Code and Python. Parses raw genotyping data from consumer DNA services and analyzes SNPs across 17 categories including health risks, pharmacogenomics, ancestry, and nutrition, with a terminal-style HTML dashboard.

Chemoinformatics and drug discovery section in deeplearning-biology repo.

Open-source platform for building, extending, and experimenting with scientific agents, providing modular agent construction tools and standardized evaluation pipelines for accelerating autonomous scientific discovery research (748+ stars, MIT License)

The GENESIS package provides methodology for estimating, inferring, and accounting for population and pedigree structure in genetic analyses. The current implementation provides functions to perform PC-AiR (Conomos et al., 2015, Gen Epi) and PC-Relate (Conomos et al., 2016, AJHG). PC-AiR performs a Principal Components Analysis on genome-wide SNP data for the detection of population structure in a sample that may contain known or cryptic relatedness. Unlike standard PCA, PC-AiR accounts for relatedness in the sample to provide accurate ancestry inference that is not confounded by family structure. PC-Relate uses ancestry representative principal components to adjust for population structure/ancestry and accurately estimate measures of recent genetic relatedness such as kinship coefficients, IBD sharing probabilities, and inbreeding coefficients. Additionally, functions are provided to perform efficient variance component estimation and mixed model association testing for both quantitative and binary phenotypes.

Our scLANE model uses truncated power basis spline models to build flexible, interpretable models of single cell gene expression over pseudotime or latent time. The modeling architectures currently supported are Negative-binomial GLMs, GEEs, & GLMMs. Downstream analysis functionalities include model comparison, dynamic gene clustering, smoothed counts generation, gene set enrichment testing, & visualization.

Mass spectrometry (MS) data backend supporting import and handling of MS/MS spectra from NIST MSP Format (msp) files. Import of data from files with different MSP *flavours* is supported. Objects from this package add support for MSP files to Bioconductor's Spectra package. This package is thus not supposed to be used without the Spectra package that provides a complete infrastructure for MS data handling.

This ontology integrates cell type markers for cells in the Cell Ontology from various sources along with details of marker context (anatomical context, assay), confidence (where available) and provenance. [from repository]

First benchmark evaluating LLMs' ability to rediscover scientific laws through interactive experimentation across 324 tasks in 12 physics domains, featuring memorization-resistant metaphysical shifts of canonical laws (HKUST)

a Bayesian normalization procedure derived from first principles. Sanity estimates expression values and associated error bars directly from raw unique molecular identifier (UMI) counts without any tunable parameters.

ramr is an R package for detection of epimutations (i.e., infrequent aberrant DNA methylation events) in large data sets obtained by methylation profiling using array or high-throughput methylation sequencing. In addition, package provides functions to visualize found aberrantly methylated regions (AMRs), to generate sets of all possible regions to be used as reference sets for enrichment analysis, and to generate biologically relevant test data sets for performance evaluation of AMR/DMR search algorithms.

Provides functionality for untargeted LC-MS metabolomics research as specified in the associated protocol article in the 'Metabolomics Data Processing and Data Analysis—Current Best Practices' special issue of the Metabolites journal (2020). This includes tabular data preprocessing and quality control, uni- and multivariate analysis as well as quality control visualizations, feature-wise visualizations and results visualizations. Raw data preprocessing and functionality related to biological context, such as pathway analysis, is not included.

GenBio AI's software stack for the AI-Driven Digital Organism, supporting adaptation and finetuning of multiscale biological foundation models across DNA, RNA, protein, structure, and single-cell tasks with reproducible CLIs and pretrained model zoo (2025)

Analyze and visualize Mutation Annotation Format (MAF) files from large scale sequencing studies. This package provides various functions to perform most commonly used analyses in cancer genomics and to create feature rich customizable visualzations with minimal effort.

Flow-matching protein folding model using only general-purpose transformer layers, scaled to 3B parameters and trained on 8.6M+ distilled structures; challenges the reliance on complex domain-specific architectures and supports PyTorch and MLX backends with model sizes from 100M to 3B parameters (985+ stars, MIT License)

Foundation models for genomics and transcriptomics pretrained on 3,000+ human genomes and 850+ diverse species, enabling chromatin accessibility prediction, splice site detection, and promoter classification across multiple model scales (InstaDeep, NVIDIA & TUM, Nature Methods 2023)

FASTQ and SAM quality control using Python.

Provides means to interactively visualize guide RNAs (gRNAs) in GuideSet objects via Shiny application. This GUI can be self-contained or as a module within a larger Shiny app. The content of the app reflects the annotations present in the passed GuideSet object, and includes intuitive tools to examine, filter, and export gRNAs, thereby making gRNA design more user-friendly.

This is a package that includes pre-processing and quality control functions that can remove margin events, compensate and transform the data and that will use PeacoQCSignalStability for quality control. This last function will first detect peaks in each channel of the flowframe. It will remove anomalies based on the IsolationTree function and the MAD outlier detection method. This package can be used for both flow- and mass cytometry data.

In high resolution mass spectrometry (HR-MS), the measured masses can be decomposed into potential element combinations (chemical sum formulas). Where additional mass/intensity information of respective isotopic peaks is available, decomposition can take this information into account to better rank the potential candidate sum formulas. To compare measured mass/intensity information with the theoretical distribution of candidate sum formulas, the latter needs to be calculated. This package implements fast algorithms to address both tasks, the calculation of isotopic distributions for arbitrary sum formulas (assuming a HR-MS resolution of roughly 30,000), and the ranked list of sum formulas fitting an observed peak or isotopic peak set.

BWA-MEM drop-in replacement: 2-3x faster, 2-5x cheaper, 100% identical output on standard CPUs.

lumpy: a general probabilistic framework for structural variant discovery.

MIRit is an R package that provides several methods for investigating the relationships between miRNAs and genes in different biological conditions. In particular, MIRit allows to explore the functions of dysregulated miRNAs, and makes it possible to identify miRNA-gene regulatory axes that control biological pathways, thus enabling the users to unveil the complexity of miRNA biology. MIRit is an all-in-one framework that aims to help researchers in all the central aspects of an integrative miRNA-mRNA analyses, from differential expression analysis to network characterization.

This package estimates tumor purity, copy number, and loss of heterozygosity (LOH), and classifies single nucleotide variants (SNVs) by somatic status and clonality. PureCN is designed for targeted short read sequencing data, integrates well with standard somatic variant detection and copy number pipelines, and has support for tumor samples without matching normal samples.

Universal pretrained neural network potential with charge and magnetic moment awareness, trained on 1.5M+ Materials Project inorganic structures for charge-informed molecular dynamics and phase diagram prediction (Berkeley, Nature Machine Intelligence 2023 Cover)

Implements a variety of methods for combining p-values in differential analyses of genome-scale datasets. Functions can combine p-values across different tests in the same analysis (e.g., genomic windows in ChIP-seq, exons in RNA-seq) or for corresponding tests across separate analyses (e.g., replicated comparisons, effect of different treatment conditions). Support is provided for handling log-transformed input p-values, missing values and weighting where appropriate.

Provides visualization functionality for untargeted LC-MS metabolomics research. Includes quality control visualizations, feature-wise visualizations and results visualizations.

A script to run structural alerts using the RDKit and ChEMBL

Deep learning-based object detection and segmentation for star-convex shapes, widely adopted for cell and nucleus segmentation in fluorescence and electron microscopy via a compact neural network architecture with non-maximum suppression and shape-based post-processing (Nature Methods 2020, 1.2K+ stars)

sRACIPE implements a randomization-based method for gene circuit modeling. It allows us to study the effect of both the gene expression noise and the parametric variation on any gene regulatory circuit (GRC) using only its topology, and simulates an ensemble of models with random kinetic parameters at multiple noise levels. Statistical analysis of the generated gene expressions reveals the basin of attraction and stability of various phenotypic states and their changes associated with intrinsic and extrinsic noises. sRACIPE provides a holistic picture to evaluate the effects of both the stochastic nature of cellular processes and the parametric variation.

Euclidean neural networks for arbitrary point transformations enabling E(3)-equivariant deep learning, foundational library for building geometry-aware neural networks in molecular dynamics, materials science, and physics

Utility package to facilitate integration and analysis of EBI MGnify data in R. The package can be used to import microbial data for instance into TreeSummarizedExperiment (TreeSE). In TreeSE format, the data is directly compatible with miaverse framework.

A polymorphic bayesian genotyping model with wide applicability.

TaxSEA is an R package for Taxon Set Enrichment Analysis, which utilises a Kolmogorov-Smirnov test analyses to investigate differential abundance analysis output for whether there are alternations in a-priori defined sets of taxa from public databases (BugSigDB, MiMeDB, GutMGene, mBodyMap, BacDive and GMRepoV2) and collated from the literature. TaxSEA takes as input a list of taxonomic identifiers (e.g. species names, NCBI IDs etc.) and a rank (E.g. fold change, correlation coefficient). TaxSEA be applied to any microbiota taxonomic profiling technology (array-based, 16S rRNA gene sequencing, shotgun metagenomics & metatranscriptomics etc.) and enables researchers to rapidly contextualize their findings within the broader literature to accelerate interpretation of results.

Rectified Quaternion Flow for efficient protein backbone generation, 37× faster than RFDiffusion with 0.972 designability (ICML 2025)

Physics-informed neural networks

Azure Semantic Kernel multi-agent PPT generation reference

Uniparental disomy (UPD) is a genetic condition where an individual inherits both copies of a chromosome or part of it from one parent, rather than one copy from each parent. This package contains a HMM for detecting UPDs through HTS (High Throughput Sequencing) data from trio assays. By analyzing the genotypes in the trio, the model infers a hidden state (normal, father isodisomy, mother isodisomy, father heterodisomy and mother heterodisomy).

Detection of rare aberrant splicing events in transcriptome profiles. Read count ratio expectations are modeled by an autoencoder to control for confounding factors in the data. Given these expectations, the ratios are assumed to follow a beta-binomial distribution with a junction specific dispersion. Outlier events are then identified as read-count ratios that deviate significantly from this distribution. FRASER is able to detect alternative splicing, but also intron retention. The package aims to support diagnostics in the field of rare diseases where RNA-seq is performed to identify aberrant splicing defects.