Find open-source science resources

Medical-Qwen3-Swallow-30B-A3B is a medical-domain language model based on tokyotech-llm/Qwen3-Swallow-30B-A3B-RL-v0.2. It is designed to support research and development toward safe and trustworthy AI for Japanese clinical settings.

Generalist deep learning algorithm for cell and nucleus segmentation across diverse image types, with human-in-the-loop training (2.0) and one-click image restoration (3.0), 70K+ training objects (Nature Methods 2021/2022/2025)

General-purpose deep learning backbone for molecular modeling

Access to Biological Web Services from Python.

Universal foundation model for grounded biomedical image interpretation, enabling comprehensive visual understanding, reasoning, and grounding across diverse biomedical imaging modalities with strong zero-shot generalization (55+ stars, Apache 2.0, 2025-2026)

A tool and library for creating quantum chemistry input files.

Sparse identification of nonlinear dynamics

A swiss army knife for manipulating and editing PDB files.

Programmatic data labeling and weak supervision

Multi-agent system with Parser-Planner-Painter architecture converting `paper.pdf` to editable `poster.pptx`, outperforms GPT-4o with 87% fewer tokens

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

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

gemma4-12b-bioinfo is a fine-tuned Gemma 4 12B instruction model for bioinformatics, genomics, and computational biology question answering.

modelid = "DuanYi/R3LMHepG2"

Estimates PCR primer melting temperatures and polymerase-specific annealing temperatures from sequence and buffer inputs, with per-pair QC for hairpins, dimers, and Tm balance. A browser calculator supports interactive single-pair and batch entry (up to 200 pairs) with method comparison and export; a Python library and command-line tool submit the same parameters to the Pepkio Tools API for scripted and pipeline use. Calculator arithmetic for the API client is hosted remotely; sequences are transmitted for programmatic runs while the web interface performs calculations in the browser.

Computes weighed laboratory buffer recipes from target pH, concentration, and volume, accounting for separate preparation and working temperatures when pKa shifts with temperature. Supports calculator mode from dry reagents and stock dilution mode, returning acid and base masses, ionic strength estimates, optional NaCl adjustment, gravimetric and titration routes, and stepwise protocols. A browser calculator supports interactive recipe entry with shareable links; a Python library and command-line tool submit the same parameters to the Pepkio Tools API for scripted and pipeline use. Calculator arithmetic is hosted remotely; the client transmits parameters and returns structured recipe tables, compatibility warnings, and shareable run identifiers.

Plans PCR and qPCR master-mix reagent volumes from stock and final concentrations, reaction counts, and pipetting overage, with consolidated totals when several assays are prepared together. A browser calculator supports interactive recipe entry with printable bench sheets; a Python library and command-line tool submit the same parameters to the Pepkio Tools API for scripted and pipeline use. Calculator arithmetic is hosted remotely; the client transmits parameters and returns structured volume tables, dilution warnings, and shareable run identifiers.

Computes laboratory solution preparation parameters—powder mass to weigh, stock and diluent volumes for single dilutions, and multi-step serial concentration tables—with correction for hydrated salts and supplier purity. A browser calculator supports interactive prep planning with saved recipes and shareable links; a Python client and command-line tool submit the same parameters to the Pepkio Tools API for scripted and pipeline use. Calculator arithmetic is hosted remotely; the client transmits parameters and returns structured protocol steps and shareable run identifiers.

Family of causal genomic foundation models trained on 1T tokens (~6T DNA base pairs) from the Carbon Pretraining Corpus, combining eukaryote genes, mRNA transcripts, and prokaryote genomes with a hybrid text/6-mer tokenizer; Carbon-3B matches or beats Evo2-7B on zero-shot DNA evaluations including sequence recovery, variant effect prediction, and perturbations (Apache 2.0, 201+ stars)

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

Surprisingly simple and efficient frontier probabilistic weather forecaster built on a standard U-Net trained with deterministic MAE pre-training followed by short CRPS fine-tuning via Monte Carlo Dropout, matching or exceeding the probabilistic skill of GenCast and IFS ENS at 1.5° resolution with >10× less training compute than leading CRPS models and >10× lower inference latency than diffusion models; trains in under 12 H200 GPU-days and generates a 15-day ensemble forecast in 3 seconds, with official code and pretrained checkpoints (UCLA, 41+ stars, Apache 2.0)

Plans geometric serial dilution series for molecular biology and biochemistry workflows, rounding transfer volumes to declared pipette ranges and optional 96- or 384-well plate layouts. A browser calculator supports interactive protocol design; a Python client and command-line tool submit the same parameters to the Pepkio Tools API for scripted and pipeline use. Calculator arithmetic is hosted remotely; the client transmits parameters and returns structured step tables and shareable run identifiers.

State-of-the-art RNA 3D folding model developed with Stanford Das Lab and Kaggle competition winners, featuring a 488M-parameter AF3-like architecture with MSA and template-based modeling, enabling structure-driven drug discovery and RNA therapeutics design (NVIDIA-Digital-Bio, Apache 2.0)

esm3-sm-open-v1 is trained on 2.78 billion natural proteins. With synthetic data augmentation, this led to 3.15 billion protein sequences, 236 million protein structures, and 539 million proteins with function annotations, totaling 771 billion tokens.

Original code at (https://github.com/Edoar-do/HuBERT-ECG)

Original code at (https://github.com/Edoar-do/HuBERT-ECG)

Original code at https://github.com/Edoar-do/HuBERT-ECG

Original code at https://github.com/Edoar-do/HuBERT-ECG

Original code at https://github.com/Edoar-do/HuBERT-ECG

LLM-native molecular language that represents molecules as explicit graph-based code, enabling LLMs to operate and reason on chemistry directly with 5× lower token cost and ~76-80% accuracy on novel molecules vs ~20% for SMILES; supports small molecules, polymers, and Markush structures with lossless RDKit interconversion and Claude Code/Codex agent skills (AtomFlow, arXiv:2605.16480, 281+ stars, MIT License, 2026)

Foundation model for universal cell segmentation achieving state-of-the-art performance across bacteria, tissue, yeast, cell culture, and diverse imaging modalities (brightfield, fluorescence, phase), with pip-installable inference and Napari plugin (vanvalenlab/Caltech, bioRxiv 2024)

CliniGuard Vitals NER is a transformer-based clinical Named Entity Recognition model developed by Genzeon Platforms for automated extraction of vital signs, body measurements, and physiological parameters from clinical text.

CliniGuard NER is a clinical Named Entity Recognition model developed by Genzeon Platforms for automated detection and de-identification of Protected Health Information (PHI) and Personally Identifiable Information (PII) in clinical text.

This model card provides an overview of the intended use of the ESMC SAE models and examples of how to access them, but it does not have a specific model or model weights. To access each SAE model collection, use the links below:

This model card provides an overview of the intended use of the ESMC SAE models and examples of how to access them, but it does not have a specific model or model weights. To access each SAE model collection, use the links below:

This set of model weights was released with the GitHub-compatible esm package format. The models here are kept for backwards compatibility, but we recommend you use the HuggingFace-compatible model weights at biohub/ESMC-6B (or biohub/ESMC-300M / biohub/ESMC-600M) instead.

![Language: English]()

> VIDRAFT FINAL-Bench — chemistry-specialized 218B MoE, served via the DELPHI 5-Phase inference cascade.

GENATATOR-PIPELINE is a Hugging Face pipeline for ab initio gene annotation from genomic DNA. It accepts a FASTA file, finds candidate transcript intervals, assigns transcript type, predicts exon and CDS structure, and writes a GFF3 annotation file.

HealthJudge is a domain-adapted helpfulness evaluator for health-related Community Notes. It is designed to judge whether a note provides helpful context for a potentially misleading social-media post, following the Community Notes helpfulness criteria.

Makes alchemical free energy calculations easier by leveraging the full power and flexibility of the PyData stack.

## Model Description ProtGPT3-112M is a single-sequence autoregressive protein language model for protein sequence generation. It is the smallest model in the ProtGPT3 family, an open-source suite of promptable and aligned protein language models ranging from 112M to 10B parameters.

ProtGPT3-10B is a single-sequence autoregressive protein language model for protein sequence generation. It is the largest model in the ProtGPT3 family, an open-source suite of promptable and aligned protein language models ranging from 112M to 10B parameters.

Programmatic framework for designing state-switching proteins via backpropagation through compositional design constraints parameterized by structure prediction models; enables de novo design of allosteric regulators and fluorescent biosensors for arbitrary small-molecule analytes (79+ stars, MIT License, ICML 2026)

!Protein-ligand interaction header

A HuggingFace-compatible repackaging of PlasmidGPT (Shao, 2024) — a GPT-2-style decoder pretrained on 153k engineered plasmid sequences from Addgene. Loadable with standard AutoModelForCausalLM and AutoTokenizer. Used as the base for PlasmidGPT-SFT and PlasmidGPT-GRPO.

First fully open-source model achieving AlphaFold3-level accuracy with 1000x faster binding affinity prediction (MIT)

Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding

Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding