Find open-source science resources

Sage-SciPerception Scientific perception for language models · 书生·元征 Connect

A DNA annotation model from the Carbon family.

A PyTorch reference implementation of the tokenizer described in the

Sequence and structure, designed together.Baker Lab × NVIDIA GenAIR Project page

Drugs scaffold decoration, and CrossDocked scaffold decoration in protein pockets.

measure the binding of transcription factors and other DNA-associated proteins.

Blog | Hugging Face Bio | Code

protein binders with RFD4-Proteina entirely on a MacBook: target

protein design framework that translates human design intent into novel

Blog | Carbon-X | Carbon-X-Base | Hugging Face Bio | Code

*GenerRNA is a PFN™ generative pre-trained language model for

This U‑Net model predicts tilt, z scanner drift, and

Sequence and structure, designed together.Baker Lab × NVIDIA GenAIR Project page

A System-1 decision model for biomedicine, pharma and clinical

Trained checkpoints of CausalBind.

proteins. Introduced in Zatom-2: Multitask Pretraining on Atomistic Data

A domain-adapted Qwen3.5-9B for aging and longevity biology. L

protein language model that has learned the rules of protein

Contrastive LEarning with Soft Targets from TCRdist. Checkpoint SCEPTR6LACsoft800k20ep_bs1024

protein's 3D subcellular localization volume from a matched nuclear

This model card provides an overview of the intended use

state-of-the-art protein language model trained on billions of protein sequences…

state-of-the-art protein language model trained on billions of protein sequences…

state-of-the-art protein language model trained on billions of protein sequences…

protein language model that has learned the rules of protein

protein language model that has learned the rules of protein

protein language model that has learned the rules of protein

protein structure prediction and design that defines a new frontier

protein structure prediction and design that defines a new frontier

# Geneformer Geneformer is a foundational transformer model pretrained on a

See the upstream model card for full details, training data

The locus-to-gene (L2G) model prioritises likely causal genes

Model for Latent Space Optimization and Generation of Proteins - github repo

Senba is a source-anchored adaptation of MarS-FM (Valence

provides the pretrained Protenix v2 model weights for protein structure prediction.

Many full-length RNAs, particularly mRNAs, exceed the ~1K context

OmniTCR is a component-aware autoregressive foundation model for learning

PertMind is a biological language model built around a central

protein language model for the phosphotransferase superfamily (EC 2.7.-: protein

This model is a fine-tuned version of ESMC-600M

!OpenDDE banner

protein variant classifier that predicts whether a mutated protein sequence

UBio-MolFM is a foundation-model suite for molecular modeling

protein embeddings where biological similarity maps to embedding proximity. Intended

protein secondary structure prediction. It processes raw single amino acid

protein–ligand binding-affinity model. Given a protein sequence and a ligand

💻 GitHub Repo • 🤗 Model Collections • 📖 MemSFT Paper

ProtSent-V2 35M plus one more contrastive pass on a

protein embeddings where biological similarity maps to embedding proximity. Intended

yields a protein-protein association network without task-specific training.