Find open-source science resources

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)

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

!image/png

![Language: Multilingual]()

Deep learning library for solving PDEs

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]

Sahal Shaji Mullappilly\, Mohammed Irfan K\, Omair Mohamed, Mohamed Zidan, Fahad Khan, Salman Khan, Rao Muhammad Anwer, and Hisham Cholakkal

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)

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)

A compact protein language model distilled from ProtGPT2 using complementary-regularizer distillation---a method that combines uncertainty-aware position weighting with calibration-aware label smoothing to achieve 31% better perplexity than standard knowledge distillation at 3.8x compression.

A compact protein language model distilled from ProtGPT2 using complementary-regularizer distillation---a method that combines uncertainty-aware position weighting with calibration-aware label smoothing to achieve 54% better perplexity than standard knowledge distillation at 9.4x compression.

A compact protein language model distilled from ProtGPT2 using complementary-regularizer distillation---a method that combines uncertainty-aware position weighting with calibration-aware label smoothing to achieve 87% better perplexity than standard knowledge distillation at 20x compression.

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)

FASTQ and SAM quality control using Python.

A library containing basis sets for use in quantum chemistry calculations. In addition, this library has functionality for manipulation of basis set data.

A Python script that converts positional information from a SAM dataset into interval format with 0-based start and 1-based end. CIGAR string of SAM format is used to compute the end coordinate.

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)

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)

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

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

From Inquiry to Decision: Building Trustworthy Medical AI

File parser/converter for QM, MD and plane-wave DFT programs.

A Neural Machine Translation (NMT) model based on a custom Transformer (Encoder-Decoder) architecture, trained from scratch. This model is designed to translate English sentences into Hebrew using multilingual encoding and specialized layer configurations.

A package for creating fast and accurate interatomic potentials.

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)

PyTorch-based embedding instance segmentation algorithm optimized for accurate, efficient, and portable cell and nucleus segmentation across fluorescence and brightfield microscopy images, achieving state-of-the-art speed and accuracy with lightweight model sizes suitable for edge deployment (224+ stars, Apache 2.0)

Evaluating multimodal autonomous agents in realistic scientific workflows across real scientific software environments (KAlgebra, Celestia, Grass GIS, Lean 4, etc.) with VM-based evaluation infrastructure and agent trajectories

Structure prediction and design of proteins with noncanonical amino acids, enabling AI-powered modeling of synthetic biology constructs and expanded genetic code systems (133+ stars, 2025)

Apache 2.0 single-cell foundation model family scaling to 3B parameters, pretrained on 266M cell profiles including perturbation data and released with training, embedding, and downstream benchmarking workflows for disease-relevant single-cell tasks (2025)

Scientific equation discovery with agentic AI, elevating LLMs from equation proposers to autonomous scientists that write code, analyze data, implement equations, and optimize based on experimental feedback; outperforms baselines by 6-35% across four science disciplines with robustness to noise and out-of-domain generalization (GAIR-NLP / SJTU, 49+ stars, Apache 2.0)

WiNGPT 是一个基于GPT的医疗垂直领域大模型，旨在将专业的医学知识、医疗信息、数据融会贯通，为医疗行业提供智能化的医疗问答、诊断支持和医学知识等信息服务，提高诊疗效率和医疗服务质量。

Matěj Pekár, Vít Musil, Rudolf Nenutil, Petr Holub, Tomáš Brázdil

Foundation model for joint segmentation, detection, and recognition of biomedical objects across nine imaging modalities, with v2 introducing BoltzFormer architecture for end-to-end 3D inference (Microsoft, Nature Methods 2025)

DNA sequence analysis

Open-source toolkit and benchmark for learning-based theorem proving in Lean, providing programmatic Lean interaction, a 98K+ theorem dataset extracted from 217 Lean projects, and ReProver—the first retrieval-augmented LLM-based theorem prover for Lean—with reproducible training pipelines underpinning much subsequent Lean prover research (Caltech & NVIDIA, NeurIPS 2023 Outstanding Paper, Datasets & Benchmarks)

Aloe: A Family of Fine-tuned Open Healthcare LLMs

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.

Discrete diffusion framework for generative protein sequence design over evolutionary-scale databases, supporting unconditional generation, evolutionary-guided conditional design, motif scaffolding, and intrinsically disordered region generation through order-agnostic autoregressive diffusion, enabling sequence-only protein design without structural priors (Microsoft Research, Nature Communications 2024)

an automated workflow for the generation and storage of DFT calculations for organic molecules.

ICML 2025 drug discovery generalist using masked discrete diffusion and fragment-based generation with molecular context guidance (NVIDIA)

Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.

PII Detection Model | 44M Parameters | Open Source