Find open-source science resources

Target-Conditioned Molecular Ideation Model for Drug Discovery Research

protein-nucleic acid-small molecule-metal ion complexes, enabling accurate

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

Deployable biomedical deep-research agent blueprint combining on-prem multimodal

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

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

protein design framework enabling DNA-encoding of chemistry for programmable

protein design achieving state-of-the-art performance on unconditional

Semi-flexible molecular diffusion model for structure-based drug design

gMISpy is a Python package designed to compute genetic Minimal

bifidoAnnotator is a bioinformatics tool designed for fine-grained annotation

Protein structure prediction

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

Tool to build force field input files for molecular simulation

proteins, nucleic acids, ligands, ions, and post-translational modifications within

Hybrid deep learning and alignment-based tool for identifying viruses

protein conformational ensembles, covering both experimental PDB states and molecular

protein language model using 3D structural vocabulary (Foldseek) for joint

protein language model distilled from ProtGPT2 using complementary-regularizer distillation

protein language model distilled from ProtGPT2 using complementary-regularizer distillation

protein language model distilled from ProtGPT2 using complementary-regularizer distillation

protein backbone generation, 37× faster than RFDiffusion with 0.972 designability

proteins with noncanonical amino acids, enabling AI-powered modeling of synthetic

protein sequence design over evolutionary-scale databases, supporting unconditional generation

protein binders based on the Protenix foundation model, achieving 17-82% nanomolar

protein structure prediction and design pipelines (Columbia AlQuraishi Lab & OpenFold

Full spaCy pipeline and models for scientific/biomedical documents, enabling named

protein-ligand conformational ensemble prediction and docking, generating diverse solutions

protein language models via sparse autoencoders, enabling mechanistic understanding of PLM representations

Experiments with expanded ensembles to explore chemical space.

This model is a lightweight model pre-trained on SELFIES

> [!NOTE] > This model has been optimized using NVIDIA

> [!NOTE] > This model has been optimized using NVIDIA

protein's amino acid sequence and full atomistic structure, including

Protein Data Bank integrating dynamic behaviors and physical properties into

protein interaction networks, and scientific knowledge graph learning across PyTorch

protein language models demonstrating versatile generative and predictive capabilities for protein

protein backbone generator utilizing hierarchical fold class labels for conditioning

protein language model family, including PMC-15B supporting sequence- and structure

protein binding pocket, enabling scaffold hopping and linker design workflows

protein function prediction from amino acid sequences using the Gene

protein function prediction from amino acid sequences using the Gene

protein function prediction from amino acid sequences using the Gene

protein activities, enabling rapid protein engineering with minimal experimental data

protein function prediction from amino acid sequences using the Gene

protein function prediction from amino acid sequences using the Gene

protein function prediction from amino acid sequences using the Gene

Universal 3D molecular pretraining framework with 209M conformations, scaling to

Diffusion-based molecular docking achieving SOTA blind docking performance, treating

View label scheme (20 labels for 1 components)