Find open-source science resources

Single-cell analysis with transformers

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)

Generative AI system for antibiotic discovery that searches billions of synthesizable molecules by combining molecular building blocks through real chemical reactions, experimentally validating novel compounds active against drug-resistant bacteria

The application of 2nd and 3rd generation High Throughput Sequencing (HTS) technologies has deeply reshaped experimental method to investigate microbial communities and obtain a taxonomic and functional profile of the invetigated community. Shotgun Metagenomics allow to quickly obtain a representation of microorganisms genomes characterizing a particular environment. In order to obtain a fast e reliable taxonomic classification of microorganisms genomes we present kMetaShot, an alignment-free taxonomic classifier based on k-mer/minimizer counting.

Design of linear and cyclic peptide binders from protein sequence information.

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)

Google Colab-based no-code toolbox democratizing deep learning in microscopy for biologists without programming experience, enabling AI-powered image segmentation, denoising, super-resolution, and object tracking across diverse imaging modalities (Henriques Lab, 640+ stars)

Target-aware peptide design framework that treats receptor sequence and structure as context via multimodal adapter tuning of protein language models (ESMC + ProteinMPNN features), with reinforcement-learning-based 3D dynamic feedback (ESMFold structure evaluation) to suppress unrealistic peptide conformations; ships with a systematic assessment pipeline covering peptide-target affinity, structure quality, physicochemical properties, diversity, and novelty (142+ stars, Apache 2.0, 2026)

This tutorial aims to illustrate the process of analyzing a membrane molecular dynamics (MD) simulation, step by step, using the BioExcel Building Blocks (biobb)

Bilingual protein language model translating between protein sequence and structure, finetuned from ProtT5-XL on 17M AlphaFoldDB structures using Foldseek's 3Di structural alphabet, enabling sequence-to-structure prediction, structure-to-sequence inverse folding, and unified protein representation learning (RostLab, 310+ stars)

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)

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.

AI-human collaborative research platform where a human researcher works with a team of LLM agents via team and individual meetings to perform scientific research; demonstrated by designing new SARS-CoV-2 nanobodies with wet-lab validation

Deep equivariant generative model predicting ligand-specific protein-ligand complex structures with dynamic receptor conformational flexibility, enabling accurate docking for flexible protein targets

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

Generative AI framework for inverse design of 3D RNA structure and function using geometric deep learning, learning design rules from 3D structures to capture complex tertiary interactions (pseudoknots, non-canonical base pairs) with expert-level accuracy for designing functional RNAs including aptamers and ribozymes (bioRxiv 2025)

Foundation model jointly trained on single-cell and spatial transcriptomics data, enabling unified representation learning across cellular and tissue spatial contexts for cell type prediction, spatial domain inference, and cross-modal integration (theislab, bioRxiv 2024, 164+ stars)

100M-parameter foundation model pretrained on 50M+ human single-cell transcriptomes covering ~20,000 genes, achieving SOTA on gene expression enhancement, drug response and perturbation prediction (Nature Methods 2024)

Family of generative single-cell foundation models (TF-Metazoa, TF-Exemplar, TF-Sapiens) jointly modeling genes and their expression levels via expression-aware autoregressive transformers, trained on up to 112M cells across 12 species spanning 1.53 billion years of evolution; achieves robust zero-shot cell type classification across species, disease state identification in human cells, and prediction of cell-type-specific transcription factors and gene-gene regulatory relationships, pip-installable with pretrained weights (CZI, 166+ stars, MIT License)

Teaching Large Language Models the Language of Biology through single-cell transcriptomics (ICML 2024)

End-to-end deep learning approach for RNA tertiary structure prediction with a flexible nucleobase center representation, achieving ~7 Å C1' RMSD across test RNAs and predicting ~545,000 structures covering 2,200+ RNA families (Kihara Lab, Purdue University, 50+ stars)

State-specific protein-ligand complex structure prediction with a multi-scale deep generative model, enabling conformational state-aware modeling of molecular interactions (329+ stars, 2024)

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)

Automate downloading and querying the latest (or a given) version of ChEMBL.

Strongest open-source automated theorem prover in Lean 4, 8B model matches DeepSeek-Prover-V2-671B at 84.6% MiniF2F, 32B model achieves 90.4% with self-correction, using scaffolded data synthesis and verifier-guided proof refinement (Princeton, 2025)

Pre-trained large generative model translating single-cell transcriptomes to proteomes in an alignment-free manner, generating absent protein abundance data for CITE-seq, spatial CITE-seq, REAP-seq, and NEAT-seq across tissues and diseases; offers three model variants pretrained on 2M human cells, 160K PBMCs, or 18K bulk samples (Tencent AI Lab Healthcare, 96+ stars)

Therapeutics Data Commons: 66 AI-ready datasets across 22 drug discovery tasks with 29 leaderboards, covering target identification, molecular generation, ADMET prediction, and clinical trial outcomes (Harvard MIMS, NeurIPS 2021/2024)

RNA foundation model trained on millions of RNA sequences for generalist RNA sequence understanding, enabling downstream structure prediction, function annotation, and representation learning for non-coding RNAs (ml4bio, 372+ stars)

State-of-the-art pretrained language models for proteins trained on thousands of GPUs and Google TPUs using Transformer architectures, enabling protein property prediction, feature extraction, and transfer learning across diverse downstream tasks (1.3K+ stars, MIT, 2020-2026)

First end-to-end data-driven weather prediction system learning directly from raw, heterogeneous Earth observations rather than physics-based reanalysis, producing both global gridded and arbitrary station forecasts; releases model weights, training code, and an ML-ready observational dataset (2007-2019) for building future end-to-end weather models (221+ stars, CC0-1.0)

Universal medical image segmentation foundation model trained on 1.57M image-mask pairs across 10 imaging modalities and 30+ cancer types (Nature Communications 2024)

General-purpose pathology foundation model pretrained on 100K+ diagnostic whole-slide images across 20 major tissue types, achieving state-of-the-art transfer learning across 30+ clinical tasks and serving as a universal feature extractor for digital pathology (Mahmood Lab, 722+ stars)

Kolmogorov-Arnold Networks with learnable activation functions on edges instead of fixed node activations, achieving strong performance in function fitting, PDE solving, and scientific discovery with enhanced interpretability as an alternative to MLPs (MIT, 16.3K+ stars, 2024)

Chemical language model

A python package for optimizing chemical reactions using machine learning (contains 10 algorithms + several benchmarks).

Deep learning-based protein sequence design (inverse folding) from backbone structures, achieving 52.4% sequence recovery vs 32.9% for Rosetta, core tool in modern protein design pipelines (Baker Lab, Science 2022)

Library with several compositional and structural material descriptors, along with a few pre-trained neural network models of material properties.

A Deep Learning Library for Compound and Protein Modeling DTI, Drug Property, PPI, DDI, Protein Function Prediction.

In silico derivatization for GC. The GC-derivatization tool converts carbonyl groups to C═N-OCH3 (MeOX) and transforms acidic protons into -Si(CH3)3 (TMS). Key functionalities include checking for specific groups, removing derivatization groups, and adding derivatization groups to molecules.

Neural differential equations in PyTorch

Climate data benchmark for ML models

Generative pre-training for genomics

First system to make novel, verifiable scientific discoveries by pairing LLMs with evolutionary search, solving open problems in combinatorics (cap set problem) and discovering faster matrix multiplication algorithms

Psi4-based reference implementations and Jupyter notebook-based tutorials for foundational quantum chemistry methods.

Weather prediction benchmark

by Sebastian Raschka.

A Chemical Knowledge Graph and Toolkit, writting in IUPAC/SMILES/SMARTS, for common small molecules from diverse communities to aid users in selecting compounds for forcefield parametirization.

Wrapper for RDKit's RunReactants to improve stereochemistry handling