Find open-source science resources

Manipulation and analysis of geometric objects.

An interactive platform that performs statistical analyses on metabolomics datasets and allows visualising results with ease. The interface gives users autonomy in creating figures suited to their reporting and publication needs.

Simulations of spiking neural networks.

Open-source biomedical AI platform integrating multimodal foundation models (BioMedGPT, PharmolixFM, LangCell) with agentic workflows and 45+ Claude Code skills for drug discovery, protein engineering, and single-cell omics analysis (PharMolix & Tsinghua AIR, 1K+ stars, 2023-2026)

Utilities for working with CSV/Tab-delimited files.

Long-context generative genomic foundation model using 6-mer tokenization for DNA sequence modeling and generation, with v2 model families for prokaryote and eukaryote genomes and pretrained weights available on HuggingFace (GenerTeam, 460+ stars, MIT License, 2025-2026)

Open-source implementation of AlphaEvolve's evolutionary coding agent paradigm, enabling LLMs to autonomously discover and optimize algorithms through iterative evolution, matching the approach behind DeepMind's breakthrough matrix multiplication discovery (6.2K+ stars, 2025)

!Screenshot 2026-07-05 at 2.33.47 AM

This repository contains LoRA finetunes of DiffusionGemma (image-conditioned discrete-diffusion LLM) for radiology visual question answering, each paired with an autoregressive Gemma-4 finetune as a controlled baseline. It corresponds to the paper Discrete Diffusion Language Models for Interactive…

Multi-agent system for drug-discovery gene target validation. LangGraph agents over an MCP data layer (~26 data sources, ~44 tools) score evidence across six independent lenses (genetics, biology, safety, clinical, commercial, regulatory) into a provenanced dossier. Configurable local/cloud LLM routing with full Langfuse/OTEL traceability.

Toolkit for large-scale whole-slide image processing supporting 22+ patch encoders (UNI, CONCH, Virchow, H-Optimus-0, etc.), slide encoders (TITAN, GigaPath, PRISM, CHIEF, Madeleine, Feather), tissue segmentation, and multi-GPU inference with end-to-end pipeline and smart resume for standardized deployment of computational pathology foundation models (Mahmood Lab, Harvard Medical School, 553+ stars)

A classification of subjects in Hochschule (universities of applied sciences)

The EVORAO Ontology provides a structured and harmonized vocabulary for describing shareable pathogens as characterized biological materials, along with their derived products and associated services, organized into collections. Developed within the EVORA project, it supports consistent metadata annotation across research infrastructures, promoting findability, accessibility, interoperability, and reusability (FAIR). By aligning with relevant standards and ontologies, EVORAO facilitates cross-domain collaboration, integration, and sharing of pathogenic resources and services to enhance pandemic preparedness and response. While initially focused on virology, EVORAO is designed to be extensible and also supports metadata harmonization for other pathogens. [from repository]

Democratizing AlphaFold3: PyTorch reimplementation to accelerate protein structure prediction research

🤗 Blog | 📄 Paper | 💻 Code | 🌐 FineMed | 🩺 DoctoBERT

Pretrained time series foundation model for zero-shot forecasting across diverse scientific and real-world domains; tokenizes continuous time series into discrete bins to train transformer language models on large-scale corpora, achieving strong zero-shot generalization and competitive performance with task-specific supervised models on climate, energy, and health benchmarks (5.3K+ stars, Apache 2.0, 2024-2026)

Medical time series foundation model pretrained on 454B time points from heterogeneous clinical corpora spanning ICU physiological signals and hospital EHR, with continuous-time rotary positional encoding, frequency-specialized Mixture-of-Experts, and neural ODE extrapolation for zero-shot forecasting across irregular and multimodal temporal health data (Microsoft, 399+ stars, MIT License)

Semi-automated research assistant for academic research and software development, supporting Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication (Galaxy-Dawn, 4.5K+ stars, MIT License, 2026)

MCP server, CLI, and agent skills for searching and downloading academic papers from multiple open sources (arXiv, PubMed, bioRxiv, Semantic Scholar, OpenAlex, CORE, Europe PMC, etc.) with unified, deduplicated, LLM-friendly retrieval and an OA-first download fallback chain (OpenAGS, 1.9K+ stars, MIT License, 2025)

Parameter/topology editor and molecular simulator with visualization capability.

Open software framework for Engineering AI built on transformer building blocks, enabling teams to build, train, and operate industrial simulation models across engineering verticals; includes ready-to-use recipes for CFD (AB-UPT on DrivAerML), external aerodynamics, and heat transfer (234+ stars, ENPL non-commercial license, 2026)

Heretic-abliterated version of Qwen/Qwen2.5-0.5B-Instruct for the Evolva drug discovery pipeline.

HantaBERT fine-tunes DNABERT-2 on hantavirus RNA sequences for three simultaneous classification tasks: species/lineage, host, and geographic origin. A single forward pass produces predictions for all three tasks along with a 768-dimensional embedding suitable for phylogenetic visualization.

For a convenient overview and download list, visit our model page for this model.

First agentic LLM for autonomous data science with end-to-end pipeline from data to analyst-grade reports

All-atom generative world model for all-to-all biomolecular interaction design, enabling cross-modality generation of proteins, nucleic acids, small molecules, and cyclic peptides with fine-grained epitope-level control and 2-4 orders of magnitude faster design throughput than modality-specific baselines (316+ stars, Apache 2.0)

Xinghe1-9B (杏核) is a specialized large language model fine-tuned for the formalization, computational derivation, and clinical reasoning of Huangdi Neijing. It is based on the Qwen3.5-9B-Instruct architecture and trained using the V3 Double-Purity SFT dataset.

Multi-modal foundation model for biomolecular structure prediction (proteins, small molecules, DNA, RNA, glycans) achieving SOTA across benchmarks, with optional MSA/template support (Chai Discovery, 2024)

# Overview This is the CellHermes model, based on the LLaMA-3.1-8B-instruct architecture developed by Meta, fine-tuned using single-cell RNA sequencing (scRNA-seq) datasets from CellxGene and PPI network from BioGRID. CellHermes is an innovative framework for adapting existing large language models…

Self-hostable scientific claim-verification and literature-review tool combining Semantic Scholar retrieval, bibliometric scoring, and LLM-based evidence synthesis for large-batch validation workflows

Deep learning with spiking neural networks in Python, providing gradient-based training of SNNs via PyTorch autodifferentiation for brain-inspired computing and neuromorphic research, with online learning capabilities and extensive tutorials (1.9K+ stars, actively maintained)

Learnable latent embeddings for joint behavioral and neural analysis, enabling consistent and interpretable mapping of neural activity to behavior across modalities, species, and experiments (EPFL & Harvard, 1K+ stars)

This repository contains Chemistry fine-tuned Qwen3-4B checkpoints from the local SciKnowEval-style generalization setup.

PlantGeneAnn is a plant genome foundation model that enables the prediction of various plant genomic elements at single-nucleotide resolution. The model is built upon the PlantBiMoE architecture with a 1D U-Net segmentation head, specifically designed for automated plant genome annotation.

Computational toolbox for large scale Calcium Imaging Analysis, including movie handling, motion correction, source extraction, spike deconvolution and result visualization, using machine learning for automated neuron detection and activity inference in two-photon and one-photon calcium imaging data (723+ stars, actively maintained)

👋 Join our LiGHT community. 📖 Check out the MeditronFO blog and MeditronFO preprint. 🔜 If you are a clinician join the MOOVE initiative here.

Sexo-FR is a French-language conversational language model that provides reliable, caring, and evidence-based sexual health information (information en santé sexuelle). It is part of a French public-health initiative whose goal is to make trustworthy sexual-health information more accessible to the…

👋 Join our LiGHT community. 📖 Check out the MeditronFO blog and MeditronFO preprint. 🔜 If you are a clinician join the MOOVE initiative here.

Vision foundation model for the tree of life, pretrained on diverse biological imagery across taxa for zero-shot species identification, trait extraction, and biodiversity research (Ohio State University Imageomics Institute)

Automated academic illustration generation for AI scientists, converting research papers into publication-ready figures using VLMs and diffusion models with iterative refinement (PKU & Google Research, 6.2K+ stars, 2026)

Jolia is a 3D CT foundation model that encodes images into vector representations program. It encodes a whole 3D CT volume into:

First multi-domain generative foundation model for the natural sciences built on a unified scientific grammar, encoding proteins, antibodies, small molecules, chemical reactions, materials, and their spatial interactions into a shared token vocabulary; enables unified generation, prediction, and design across domains under a purely autoregressive paradigm (134+ stars, Apache 2.0, 2026)

Molexar-10M Base is the unconditional base model for Molexar, a unified multimodal molecular foundation model for drug design. It is trained as an autoregressive molecular language model over Fragment-SELFIES, a BRICS-fragment molecular language with validity-preserving decoding and…

Molexar-10M Omni is the universal multi-condition model for Molexar, a unified multimodal molecular foundation model for drug design. It starts from fairydance/molexar-10m-base and is supervised fine-tuned to generate Fragment-SELFIES molecules under scalar molecular-property,…

RBPBench is a multi-function tool to evaluate CLIP-seq and other related genomic region data using a comprehensive collection of known RNA-binding protein (RBP) binding motifs. RBPBench can be used for a variety of purposes, from RBP motif search (database or user-supplied RBP motifs) in genomic regions, over motif enrichment and co-occurrence analysis, in-depth comparisons over multiple datasets via sequence and genomic annotation statistics, to benchmarking CLIP-seq peak caller methods as well as comparisons across cell types and CLIP-seq protocols. RBPBench supports both sequence and structure motifs, as well as regular expressions (sequence and structure patterns). Moreover, users can easily provide their own motif collections.

Deep learning library for solving PDEs