Find open-source science resources

encoder-only component of GB.StructureTokenizer for tokenization of protein structures.

protein together with a range of structural and functional tracks

Trinity-Mini-AI-Scientist

SMILES structures based on both disease pathways and protein sequence.

NucleusDiff

protein–protein and peptide–MHC interaction, and more — following the…

protein structure prediction and design that defines a new frontier

SMILES structures based on both disease pathways and protein sequence.

650M with LoRA for predicting protein subcellular localization (10 classes).

Distilling Boltz: Flow Maps for Fast All-Atom Cofolding

!ESMC ProtHash Banner

!Python

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

Gravity-bio-16B-A3B is a biology-focus midtrained model

protein aging clock that predicts chronological age from 85 unique

protein aging clock that predicts chronological age from 92 Olink

Molexar-10M Base is the unconditional base model for Molexar

Molexar-10M Omni is the universal multi-condition model for

> Source code, training scripts, and inference utilities for this

both molecules and proteins within a single decoder-only architecture.

This Hugging Face repository stores the official resources for RAMER

promptable and aligned protein language models for protein sequence generation.

KAU-BioMedLLM is a research prototype for source-grounded biomedical

 

 

 

 

Mirror of the Boltz-2 structure- and affinity-prediction weights

PRISM is an antibody language model that jointly predicts amino

JAX/Equinox parameters for Promera, a dual-purpose biomolecular generative model

protein sequences, 236 million protein structures, and 539 million proteins

This model card provides an overview of the intended use

This model card provides an overview of the intended use

This set of model weights was released with the GitHub

protein language model for protein sequence generation. It is the smallest

protein language model for protein sequence generation. It is the largest

This repository hosts release artifacts for ReCLIP:

!Protein-ligand interaction header

This set of model weights was released with the GitHub

650M, layer 33) for interpretability research on protein language models.

protein sequences and 3D structures, conditioned on and co-folded

Target-Conditioned Molecular Ideation Model for Drug Discovery Research

Gemma 4 E2B fine-tuned on 225K drug–target pairs

- 2025-05-15: We identified a bug in the Bacformer

- 2025-05-15: We identified a bug in the Bacformer

This U‑Net model masks features in Atomic Force Microscopy

# InstaNovo: De novo Peptide Sequencing Model ## Model Description

# InstaNovo: De novo Peptide Sequencing Model ## Model Description

!Model Architecture

A 50% magnitude-pruned version of facebook/esm2t1235MUR50D optimized for efficient