Find open-source science resources

Meta FAIR's foundation model of vision, audition, and language for in-silico neuroscience, predicting fMRI brain responses to naturalistic multimodal stimuli (video, audio, text) through unified Transformer architecture mapped to the cortical surface (2026)

Foundation model for universal prompt-driven medical image segmentation extending SAM3 to clinical imaging, supporting 2D public benchmarks and 3D training/evaluation with text and box prompts; pretrained weights available on HuggingFace (189+ stars)

DANTE is a software tool for genotyping and characterizing tandem repeats (TRs) from both second- and third-generation sequencing data. It supports the analysis of short-read massively parallel sequencing (sr-MPS) and long-read massively parallel sequencing (lr-MPS), enabling accurate repeat characterization across a wide range of loci. A key feature of DANTE is its ability to determine genotypes at nucleotide resolution, including the characterization and phasing of complex repeat motifs. For sr-MPS data, the tool determines allele size and sequence composition of alleles for which spanning reads are generated. In addition, it identifies alleles that exceed the sequencing read length by estimating their presence from partial read evidence and supports the visualisation of the sequence composition of partial reads. For lr-MPS data, where complete repeat regions are typically sequenced, DANTE determines the allele size and sequence composition of identified alleles.

SPAdes (St. Petersburg genome assembler) is an assembly toolkit containing various assembly pipelines and the de-facto standard for prokaryotic genome assemblies.

Access to Biological Web Services from Python.

Ontology, part of the SI Reference Point, covering measurement units (SI base units and SI units with special names) and prefixes.

Sparse identification of nonlinear dynamics

A swiss army knife for manipulating and editing PDB files.

Lifecycle-Aware Memory (LAM) primitive and benchmark for long-horizon research agents, achieving 65.95% mean reproduction on PaperBench and 94.66% on SurveyBench through Capital Chunk Memory (CCM) with versioned content, structural multi-hop relevance, and provenance-grounded composition; 10 peer-reviewed acceptances at FSE/ICML/TOSEM/AEI/ICoGB (1.3K+ stars)

This package provides a periodic table of the elements with support for mass, density and xray/neutron scattering information.

Minimap2 is an pairwise aligner for genomic and spliced nucleotide sequences. It can perform the assembly-to-assembly alignment, and works with gzip'd FASTQ, FASTA formats. It also finds overlaps between long-reads.

All-atom biomolecular structure prediction for protein-nucleic acid-small molecule-metal ion complexes, enabling accurate modeling of covalent modifications and assemblies beyond proteins (Baker Lab, Science 2024)

Benchmark quantifying end-to-end autonomous AI research abilities of LLM agents across 20 tasks from SOTA machine learning papers spanning NLP, code, math, biochemical modelling, and time series forecasting, with normalized score metrics against human SOTA and HuggingFace dataset

First physics-aligned interactive benchmark for LLM agents in engineering construction, designing rockets/cars/bridges in physics simulator with 3D spatial geometry library

dominatR is an R package for quantifying and visualizing feature dominance in datasets. dominatR applies concepts drawn from physics such as center of mass and shannon's entropy to effectively visualize features (e.g. genes) that are present within a specific context or condition. The package integrates, dataframes, matrices and SummerizedExperiment objects and is able to perform common genomic normalization methods. The key aspect is the generation of plots that serve to highlight context-relevant feature dominance.

Arc Institute's single-cell foundation model enabling in-context learning at inference time via a novel tabular attention architecture, trained on 150M uniformly-preprocessed cells for generalizing biological effects and generating unseen cell profiles in novel contexts (2025)

Benchmark evaluating AI agents on 75 curated Kaggle-style ML engineering competitions with reproducible Docker-based grading harness, human baselines, and end-to-end task lifecycle, used as a primary benchmark for autonomous ML research agents (e.g., InternAgent #1 at 36.44%)

toscca is an R package to perform Thresholded Ordered Sparse Canonical Correlation Analysis (TOSCCA).

Dataset and benchmarking framework integrating histology and spatial transcriptomics, enabling multimodal analysis of whole-slide images with matched spatial gene expression for advancing computational pathology and tissue microenvironment research (Mahmood Lab, Harvard Medical School, 411+ stars)

Unified latent diffusion transformer that jointly generates periodic crystals and non-periodic molecules, scaling to 500M parameters with SOTA results on QM9, MP20, and GEOM-DRUGS (Meta FAIR, ICML 2025, 310+ stars)

De novo assembler for single molecule sequencing reads using repeat graphs.

Baidu's open-source reproduction of AlphaFold3 in PaddlePaddle, providing pretrained weights and inference pipelines for unified biomolecular structure prediction across proteins, nucleic acids, ligands, ions, and post-translational modifications within the PaddleHelix biocomputing platform (Baidu, bioRxiv 2024)

Hybrid deep learning and alignment-based tool for identifying viruses, plasmids, and other mobile genetic elements in isolates, metagenomes, and metatranscriptomes, combining neural-network gene-content classifiers with nucleotide-sequence signatures; also performs viral taxonomic assignment, provirus detection in host genomes, and functional annotation, with precomputed databases of 200K+ viral and 1M+ plasmid genomes and web apps on Galaxy and NMDC EDGE (Berkeley Lab & DOE Joint Genome Institute, 334+ stars, actively maintained)

Genetic variant annotation and effect prediction toolbox.

The Generative Artificial Intelligence Delegation Taxonomy (GAIDeT) assigns identifiers to contributor roles as an extension to the Contributor Roles Taxonomy (CRediT) to support promoting transparency and accountability in academic publishing when AI contribtors are involved in research. It is operationalized in the [GAIDeT Declaration Generator](https://panbibliotekar.github.io/gaidet-declaration/), an interactive tool for researchers to disclose the delegation of tasks to generative AI (GAI) tools in accordance with the GAIDeT taxonomy.

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)

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)

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

Self-supervised vision foundation model for generalized structural brain MRI analysis, pretrained on ~49,000 scans from diverse datasets and generalizing across brain age prediction, dementia/MCI classification, IDH mutation detection, glioma survival prediction, time-to-stroke estimation, MR sequence classification, and brain tumor segmentation; outperforms task-specific models especially with limited training data (Mass General Brigham & Harvard Medical School, 129+ stars)

Lightweight supervised slide foundation model with 0.9M parameters pretrained on 24K whole-slide images for pan-cancer morphological classification, achieving competitive performance with much larger self-supervised models (TITAN, GigaPath) while enabling finetuning on consumer-grade GPUs; includes standardized MIL implementations and benchmarking across 15+ classification tasks (Mahmood Lab, Harvard Medical School, 153+ stars)

A [Jupyter](https://jupyter.org/) widget to interactively view molecular structures and trajectories.

SCENIC+ is a python package to build gene regulatory networks (GRNs) using combined or separate single-cell gene expression (scRNA-seq) and single-cell chromatin accessibility (scATAC-seq) data.

Official implementation of the second-generation fully autonomous scientific discovery system, extending the original with agentic tree search and reduced template dependency to achieve workshop-level accepted papers (6.7K+ stars, 2025)

First fully autonomous open-ended scientific discovery system with official implementation: hypothesis→experiment→writing→review simulation (13.8K+ stars, 2024)

Biocaml aims to be a high-performance user-friendly library for Bioinformatics.

Graph neural network operating entirely at the atomic level for protein-ligand conformational ensemble prediction and docking, generating diverse solutions through rapid stochastic denoising to model conformational heterogeneity (Baker Lab, bioRxiv 2025)

Conversational data analysis using natural language

AI-assisted mutation nomination approach optimizing protein function by integrating structural and evolutionary constraints into protein inverse folding models, compatible with ProteinMPNN, LigandMPNN, ESM-IF1, and SaProt (Chinese Academy of Sciences, 359+ stars)

Another list focuses on Python stuff related to Chemistry.

HOSO is an ontology of informational entities and processes related to healthcare organizations and services.

Cheminformatic extension for the SQLAlchemy database.

HEPRO is an ontology of informational entities and processes related to health procedures and health activities.

SIMD C library for global, semi-global, and local pairwise sequence alignments

NIST's open-source platform for data-driven atomistic materials design, integrating DFT datasets (JARVIS-DFT), machine learning property prediction (JARVIS-ML), and a comprehensive leaderboard for benchmarking materials AI methods across the periodic table (384+ stars)

Large-scale flow-based protein backbone generator utilizing hierarchical fold class labels for conditioning with a tailored scalable transformer architecture, enabling controllable de novo protein design (264+ stars)

DeepSeek's open-source large language model for formal theorem proving in Lean 4, integrating informal and formal mathematical reasoning through recursive subgoal decomposition and reinforcement learning powered by DeepSeek-V3, with open weights and ProverBench evaluation (2025)