Find open-source science resources

Non-invasive decoding of typed sentences from MEG and EEG brain recordings using a convolutional encoder, transformer, and character-level language model; official code for the Nature Neuroscience paper and Meta blog post on brain-AI communication (Meta FAIR, 894+ stars, CC BY-NC 4.0, 2026)

Python Materials Genomics: robust materials analysis library defining classes for structures and molecules with support for many electronic structure codes; foundational toolkit powering the Materials Project (Berkeley Lab, 1.8K+ stars)

seqlib is a type-safe Rust library for working with DNA and RNA sequences.

Open-source SDK for working with quantum computers at the level of extended quantum circuits, operators, and primitives, enabling quantum algorithm development for quantum chemistry, materials science, and optimization research (IBM, 7.4K+ stars, Apache 2.0)

Web-based platform for discovering professional contacts, organizations, and business email addresses using advanced search and filtering capabilities.

A package to 'build' collections of materials properties from the output of computational materials calculations.

StaphScope is an automated, locally-executable computational pipeline designed specifically for comprehensive Staphylococcus aureus genomic surveillance. It addresses the critical bottleneck in MRSA research by integrating seven essential genotyping methods into a single, cohesive workflow.

Deep learning atomistic model across elements, temperatures, and pressures

Large transformer-based single-cell foundation model pretrained on 50 million cells for robust gene network inference, expression denoising, cell embedding, and zero-shot label prediction, leveraging ESM2 protein embeddings and bidirectional transformer architecture (Cantini Lab, 148+ stars, GPL-3.0)

Parallel computing with task scheduling.

Biomedical AI agents

Benchmark evaluating AI agents for end-to-end automated research from re-discovery to new-discovery, with 40 real-science tasks across 10 disciplines, curated datasets from published papers, and expert-curated multimodal rubrics (170+ stars, MIT License)

COSMOS (Causal Oriented Search of Multi-Omic Space) is a method that integrates phosphoproteomics, transcriptomics, and metabolomics data sets based on prior knowledge of signaling, metabolic, and gene regulatory networks. It estimated the activities of transcrption factors and kinases and finds a network-level causal reasoning. Thereby, COSMOS provides mechanistic hypotheses for experimental observations across mulit-omics datasets.

Local-first, conversational AI research partner for multi-omics analysis with CLI, desktop app, and 95+ reproducible skills; keeps raw data local while routing natural-language requests to Python/R/CLI tools with persistent memory, autonomous analysis paths, and multi-method consensus workflows (TianGzlab, 155+ stars, Apache 2.0, 2026)

Offline-first scientific writing workspace powered by Claude, integrating LaTeX, Python, and 100+ scientific skills with local execution, Zotero integration, and privacy-focused design (2026)

Agent skills (SKILL.md + deterministic tools) for the AI4S workflow — topic exploration, literature survey, runnable experiments, publication-grade papers, and integrity audit, with every citation and number traceable to its source (by ai4s-research, maintainers of this list; MIT, 2026)

bambu is a R package for multi-sample transcript discovery and quantification using long read RNA-Seq data. You can use bambu after read alignment to obtain expression estimates for known and novel transcripts and genes. The output from bambu can directly be used for visualisation and downstream analysis such as differential gene expression or transcript usage.

Java-based browser. Fast, efficient, scalable visualization tool for genomics data and annotations. Handles a large variety of formats.

Pathogensurveillance is a population genomics pipeline for pathogen identification, variant detection, and biosurveillance. The pipeline accepts paths to raw reads for one or more organisms and creates reports in the form of an interactive HTML document. Significant features include the ability to analyze unidentified eukaryotic and prokaryotic samples, creation of reports for multiple user-defined groupings of samples, automated discovery and downloading of reference assemblies from NCBI RefSeq, and rapid initial identification based on k-mer sketches followed by a more robust multi gene phylogeny and SNP-based phylogeny.

PyTorch-native atomistic simulation engine for the machine-learned interatomic potential (MLIP) era, enabling batched molecular dynamics and structural relaxation with automatic GPU memory management; supports MACE, Fairchem, SevenNet, ORB, MatterSim and other popular MLIPs with up to 100x speedup over ASE (Radical AI, AI for Science 2026, 468+ stars, MIT License)

AcinetoScope is an automated, comprehensive bioinformatics pipeline designed specifically for the genomic analysis of Acinetobacter baumannii, a WHO Critical Priority pathogen responsible for devastating hospital-acquired infections. It integrates seven analysis types (MLST, ABRicate, AMRFinder, Kaptive 3, APT, PlasmidFinder, and mutation detection) into a single automated workflow — from FASTA to actionable insights. The pipeline offers both gene-centric and sample-centric reporting, dynamic grouping by typing, and is optimised for HPC, cloud, and container environments.

Library of descriptors to aid in the data-mining of materials properties, created by the Lawrence Berkeley National Laboratory.

Scientific machine learning benchmarks & differential equation solvers

Aims to provide useful high-level interfaces that make ML for materials science as easy as possible.

RankMap is a fast and scalable tool for reference-based cell type annotation of single-cell and spatial transcriptomics data. It uses ranked gene expression and multinomial regression to achieve robust predictions, even with partial gene coverage. Compatible with Seurat, SingleCellExperiment, and SpatialExperiment objects, RankMap offers flexible preprocessing and significantly faster runtime than tools like SingleR, Azimuth, and RCTD.

Biological vision foundation model trained on TreeOfLife-200M, yielding extraordinary accuracy on diverse biological visual tasks including habitat classification and trait prediction despite a narrow training objective (Ohio State University Imageomics Institute)

Rust implementations of algorithms and data structures useful for bioinformatics.

Fully open-source (Apache 2.0) biomolecular structure prediction reproducing AlphaFold3, free for academic and commercial use (Columbia AlQuraishi Lab & OpenFold Consortium, 2025)

The spicyR package provides a framework for performing inference on changes in spatial relationships between pairs of cell types for cell-resolution spatial omics technologies. spicyR consists of three primary steps: (i) summarizing the degree of spatial localization between pairs of cell types for each image; (ii) modelling the variability in localization summary statistics as a function of cell counts and (iii) testing for changes in spatial localizations associated with a response variable.

Ensemble of automated machine learning protocols that can be run sequentially through a single command line. The program works for regression and classification problems.

University of Cambridge's foundation model for time-series satellite imagery, enabling efficient extraction of temporal patterns from Earth observation for land classification, canopy height prediction, and other remote sensing tasks

Predicts transcription factor binding sites in up to 316 vertebrate species by scoring JASPAR matrices against Ensembl promoter sequences and combining the match with seven contextual experimental datapoints, including evolutionary conservation, CAGE-defined transcription start sites, eQTLs, ChIP-seq peaks, ATAC-seq accessibility, DNase footprints and gene expression correlation, into a single score per site.

GSABenchmark is a package designed for benchmarking scRNA-seq gene set analysis (scGSA) methods. It provides both traditional and novel benchmark metrics, as well as visualization tools. Currently, GSABenchmark supports 17 scGSA methods.

Cell Set Overlap Analysis (CSOA) is a tool for calculating per-cell gene signature scores in an scRNA-seq dataset. CSOA constructs a set for each gene in the signature, consisting of the cells that highly express the gene. Next, all overlaps of pairs of cell sets are computed, ranked, filtered and scored. The CSOA per-cell score is calculated by summing up all products of the overlap scores and the min-max-normalized expression of the two involved genes. CSOA can run on a Seurat object, a SingleCellExperiment object, a matrix and a dgCMatrix.

A local command-line tool for ancestral sequence reconstruction with gap-state inference using IQ-TREE. It supports nucleotide, amino acid, and codon sequence alignments and reports site-wise posterior probabilities of ancestral states.

Tools for manipulating paired ranges and working with Hi-C data in R. Functionality includes manipulating/merging paired regions, generating paired ranges, extracting/aggregating interactions from `.hic` files, and visualizing the results. Designed for compatibility with plotgardener for visualization.

Phylogeny-aware genomic language model trained on whole-genome alignments across multiple evolutionary timescales, predicting functional constraints and variant effects for human, mouse, chicken, fly, worm, and Arabidopsis genomes (344+ stars, MIT License)

AlphaFold/ESMFold accessible implementation with AF3 JSON export, database updates

`amplican` performs alignment of the amplicon reads, normalizes gathered data, calculates multiple statistics (e.g. cut rates, frameshifts) and presents results in form of aggregated reports. Data and statistics can be broken down by experiments, barcodes, user defined groups, guides and amplicons allowing for quick identification of potential problems.

Ultra-fast, sensitive search and clustering suite for protein and nucleotide sequence sets.

Quantum chemisttry web platform that brings all the necessary tools to perform quantum chemistry in a user-friendly web interface.

RiSPICE (Rice SNP Prioritization Integrating Chromatin Effects) is a computational framework for prioritizing non-coding rice variants by integrating predicted chromatin effects from a fine-tuned DNA language model.

AI-driven desktop workbench for computational materials science with an interactive 3D structure editor, natural-language CatBot assistant, visual DAG workflow engine, remote-cluster access, and HPC job submission for VASP, ORCA, CP2K, Quantum ESPRESSO, GPAW, DFTB+, SIESTA, and LAMMPS (172+ stars, AGPL-3.0, 2026)

Data management of large-scale whole-genome sequencing variant calls with thousands of individuals: genotypic data (e.g., SNVs, indels and structural variation calls) and annotations in SeqArray GDS files are stored in an array-oriented and compressed manner, with efficient data access using the R programming language.

REFUTE is an open benchmark for scientific critique honesty and epistemic calibration on recent life-science and biomedical literature. It tests whether models keep claims inside what the evidence allows (overclaim / planted-flaw / falsifier selection) and whether stated confidence is calibrated, with judge-free MCQ axes plus open-ended critique scoring.

SpatialFeatureExperiment (SFE) is a new S4 class for working with spatial single-cell genomics data. The voyager package implements basic exploratory spatial data analysis (ESDA) methods for SFE. Univariate methods include univariate global spatial ESDA methods such as Moran's I, permutation testing for Moran's I, and correlograms. Bivariate methods include Lee's L and cross variogram. Multivariate methods include MULTISPATI PCA and multivariate local Geary's C recently developed by Anselin. The Voyager package also implements plotting functions to plot SFE data and ESDA results.

Pirat enables the imputation of missing values (either MNARs or MCARs) in bottom-up LC-MS/MS proteomics data using a penalized maximum likelihood strategy. It does not require any parameter tuning, it models the instrument censorship from the data available. It accounts for sibling peptides correlations and it can leverage complementary transcriptomics measurements.

Microsoft's AI-powered geospatial Earth science application for natural-language exploration, visualization, and analysis of 130+ satellite collections, with STAC integration, multi-agent backend, MCP server, and deployable React/FastAPI stack (MIT, 2025)

LLM agents for working with the SRA (Sequence Read Archive) and associated bioinformatics databases, enabling natural language querying of high-throughput sequencing data and metadata across genomic repositories (Arc Institute, 169+ stars, 2024-2026)

The Open Forcefield Toolkit provides implementations of the SMIRNOFF format, parameterization engine, and other tools.