Find open-source science resources

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.

Scientific machine learning benchmarks & differential equation solvers

Rust implementations of algorithms and data structures useful for bioinformatics.

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.

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

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

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.

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.

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)

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

iSEEfier provides a set of functionality to quickly and intuitively create, inspect, and combine initial configuration objects. These can be conveniently passed in a straightforward manner to the function call to launch iSEE() with the specified configuration. This package currently works seamlessly with the sets of panels provided by the iSEE and iSEEu packages, but can be extended to accommodate the usage of any custom panel (e.g. from iSEEde, iSEEpathways, or any panel developed independently by the user).

Nallo is a bioinformatics analysis pipeline for long-reads from both PacBio and (targeted) ONT-data, focused on rare-disease. The pipeline detects a wide range of genetic variants, performs genome assembly, and reports CpG methylation. It also enables annotation and ranking of variants based on their predicted functional consequences.

Tools for adding mutations to existing `.bam` files, used for testing mutation callers.

A developed and benchmarked reproducible machine learning framework for microbiome-based colorectal cancer (CRC) screening. By systematically evaluating normalization strategies, taxonomic resolutions, and class imbalance handling. This R package allows users to apply the full pipeline or selectively run specific components depending on their analytical needs. It establishes a scalable foundation for developing interpretable microbiome-based screening tools to support early CRC detection. This approach could be easily implemented in a national screening programme, to improve early detection rates for this disease.

The geomeTriD (Three-Dimensional Geometry) Package provides interactive 3D visualization of chromatin structures using the WebGL-based 'three.js' (https://threejs.org/) or the rgl rendering library. It is designed to identify and explore spatial chromatin patterns within genomic regions. The package generates dynamic 3D plots and HTML widgets that integrate seamlessly with Shiny applications, enabling researchers to visualize chromatin organization, detect spatial features, and compare structural dynamics across different conditions and data types.

A python extension, written in C, for quick access to bigBed files and access to and creation of bigWig files.

Create MSP files containing the isotopic patterns for given molecules with given adducts. The tool is based on enviPat and the RforMassSpectrometry toolbox.

Workflow optimized for the analysis of rare diseases, designed to detect SNVs, INDELs , CNVs and SVs in targeted sequencing data (CES/WES) and whole genome sequencing (WGS), built on Nextflow and following nf-core standards. It has an advanced variant annotation optimized for rare diseases diagnosis and discovery.

Graph neural network interatomic potential package supporting efficient multi-GPU parallel molecular dynamics simulations, enabling large-scale atomistic modeling with machine learning potentials (MDIL-SNU, MIT License)

Another cross-platform, efficient, practical and pretty CSV/TSV toolkit.

Visualization intermediate language that lets AI agents create expressive, polished charts from simple, human-editable specs, compiling the same input to 30+ chart types across Vega-Lite, ECharts, and Chart.js with an MCP server for agent integration (1.9K+ stars, MIT License, 2026)

Comprehensive collection of 125+ ready-to-use scientific skill modules for Claude AI across bioinformatics, cheminformatics, clinical research, ML, and materials science

Physics-Informed Neural networks for Advanced modeling in PyTorch

Generate QC reports summarizing the output from an alevin, alevin-fry, or simpleaf run. Reports can be generated as html or pdf files, or as shiny applications.

Fast sample-swap and relatedness checks on BAMs/CRAMs/VCFs/GVCFs.

Curated, multilingual library of 182 installable AI agent skills for end-to-end academic research spanning literature discovery, scientific writing, grant development, bioinformatics, drug discovery, clinical research, machine learning, and data analysis (779+ stars, MIT License, 2026)

Python wrapper for [samtools](https://github.com/samtools/samtools).

Coordinate-based genomic visualization package for R. It grants users the ability to programmatically produce complex, multi-paneled figures. Tailored for genomics, plotgardener allows users to visualize large complex genomic datasets and provides exquisite control over how plots are placed and arranged on a page.

102 executable tasks from 44 peer-reviewed papers across 4 disciplines with containerized evaluation

Diffusion-based generative model for inorganic materials design, steering generation by chemistry, symmetry, bulk modulus, band gap, or magnetic properties, 2× more likely to produce stable novel structures than prior methods, experimentally validated with synthesized TaCr₂O₆ (Microsoft, Nature 2025)

Bioconductor has a rich ecosystem of metadata around packages, usage, and build status. This package is a simple collection of functions to access that metadata from R. The goal is to expose metadata for data mining and value-added functionality such as package searching, text mining, and analytics on packages.

Reinforcement-learning-trained AI agent for treatment reasoning over a universe of 212 biomedical tools, performing multi-step evidence gathering and spawning parallel reasoning branches to reach evidence-grounded clinical decisions (55+ stars, MIT License, 2026)

PinPath enables flexible visualization of (omics) data onto pathways diagrams, allowing users to pinpoint where the relevant changes occur. It supports pathway diagrams from WikiPathways and KEGG, as well as custom GPML and KGML files. Data can be displayed on both native pathway layouts and network representations

This package provides functionality to combine the existing pieces of the transcriptome data and results, making it easier to generate insightful observations and hypothesis. Its usage is made easy with a Shiny application, combining the benefits of interactivity and reproducibility e.g. by capturing the features and gene sets of interest highlighted during the live session, and creating an HTML report as an artifact where text, code, and output coexist. Using the GeneTonicList as a standardized container for all the required components, it is possible to simplify the generation of multiple visualizations and summaries.

GlycoTraitR is an R package for analyzing glycoproteomics data, particularly glycopeptide-spectrum matches (GPSMs). It supports results generated by the pGlyco3 and Glyco-Decipher search engines. The package parses glycan structures, computes monosaccharide compositions and structural traits, and performs differential analysis of glycan heterogeneity. It constructs trait-by-PSM matrices stored in a SummarizedExperiment object, supports user-defined structural motifs, and provides visualization utilities for interpreting glycan trait changes.

Biological simulation tools

Differentiable PDE solving framework for machine learning with built-in fluid simulation, supporting PyTorch/JAX/TensorFlow backends and enabling neural network training within physical simulations (TUM, MIT License)

Large-scale knowledge graph and pip-installable client for literature-grounded automated scientific research, connecting papers, authors, institutions, venues, keywords, citations, and a four-level research taxonomy across medicine, social sciences, engineering, computer science, materials science, and more (ZJU NLP, arXiv 2026, 136+ stars, MIT License)

AI co-author covering the entire research lifecycle — from an under-specified research direction to a published paper; includes ResearchStudio-Idea for evidence-grounded research ideation and ResearchStudio-Reel for turning finished papers into posters, narrated videos, blogs, and interactive reels; runs as skills on Claude Code and Codex (1.2K+ stars, MIT License, 2026)

LLMs as copilots for theorem proving in Lean 4, exposing native tactics (`suggest_tactics`, `search_proof`, `select_premises`) that embed language model inference and premise retrieval directly inside the Lean proof environment, supporting local CTranslate2/CUDA inference as well as remote model APIs for interactive and automated proof search (Caltech & NVIDIA, NeurIPS 2024, 1.2K+ stars)

Galaxy workflow for BlockClust pipeline.

LLM-driven machine learning engineering agent using agentic tree search to autonomously draft, debug and benchmark ML code; wins 4× more medals than the best linear agent on OpenAI's MLE-Bench (75 Kaggle competitions) (1.3K+ stars, MIT License)