biology & protein: 30 curated resources
biology & protein
30 resources · page 1 of 1
AlphaFold 2
DeepMind AlphaFold GitHub repo: open-source code for AlphaFold 2 protein structure prediction.
AlphaGenome
DeepMind AlphaGenome GitHub repo: API client for the AlphaGenome regulatory variant model.
Boltz
Boltz GitHub repo: open biomolecular interaction models, with Boltz-2 adding binding affinity prediction.
Chai Discovery
Chai Discovery chai-lab GitHub repo: Chai-1 biomolecular structure prediction model.
CZ CELLxGENE
by Chan Zuckerberg Initiative (CZ CELLxGENE)
CZ CELLxGENE Discover: curated, standardised single-cell datasets to find, download and explore, used to train cell models.
DeepVariant
by Google
Google DeepVariant GitHub repo: deep learning pipeline for calling genetic variants from sequencing data.
ESM (EvolutionaryScale)
by Biohub
EvolutionaryScale ESM GitHub repo, now under Biohub: ESM protein language models with tutorials.
ESM (Meta, ESM-2/ESMFold)
Meta ESM GitHub repo: pretrained protein language models ESM-2 and ESMFold.
ESM protein models
by Biohub
Biohub ESM GitHub repo: ESM protein language models including ESMC and ESMFold2, with tutorials.
evo2 (Arc Institute)
Arc Institute Evo 2 GitHub repo: genome modelling and design model across all domains of life.
Inceptive
by Inceptive
Inceptive: company building biological foundation models to design RNA and medicines.
InstaDeep Nucleotide Transformer
InstaDeep Nucleotide Transformer GitHub repo: foundation models for genomics and transcriptomics.
Isomorphic Labs
Isomorphic Labs: DeepMind spin-out applying AlphaFold-line models to drug discovery.
MICrONS Explorer
MICrONS Explorer: data portal for a cubic-millimetre mouse cortex connectome reconstructed with machine learning.
OpenCRISPR
by Profluent
Profluent OpenCRISPR GitHub repo: AI-generated gene editing systems such as OpenCRISPR-1.
OpenFold
AQ Laboratory OpenFold GitHub repo: trainable PyTorch reproduction of AlphaFold 2.
Profluent
by Profluent
Profluent: company using protein language models to design new proteins and gene editors.
AlphaFold 3
DeepMind AlphaFold 3 GitHub repo: AlphaFold 3 inference pipeline.
ProteinMPNN
ProteinMPNN GitHub repo: code for the ProteinMPNN protein sequence design model.
Protenix (ByteDance)
by ByteDance
ByteDance Protenix GitHub repo: open-source biomolecular structure prediction reproducing and extending AlphaFold 3.
RCSB Protein Data Bank
RCSB Protein Data Bank: curated archive of experimentally determined 3D protein structures with search and analysis tools.
Recursion
by Recursion
Recursion: company using AI and automated biology for drug discovery.
RoseTTAFold
RosettaCommons RoseTTAFold GitHub repo: deep learning protein structure prediction models.
snnTorch
by Jason Eshraghian (snnTorch)
snnTorch documentation: tutorials for training spiking neural networks in PyTorch.
SpyTorch
SpyTorch GitHub repo: tutorial on surrogate gradient learning in spiking neural networks.
BirdNET
by K. Lisa Yang Center for Conservation Bioacoustics (Cornell Lab of Ornithology)
BirdNET site from Cornell: AI tool for identifying bird species from sound recordings.
AlphaFold 2 Nature paper
by John Jumper et al. (DeepMind)
Nature paper (2021) on AlphaFold 2, highly accurate protein structure prediction.
Baidu PaddleHelix
by PaddlePaddle
Baidu PaddleHelix GitHub repo: bio-computing platform on PaddlePaddle for drug discovery and protein models.
KAN: Kolmogorov-Arnold Networks
arXiv paper (2024) introducing Kolmogorov-Arnold Networks (KAN) with learnable activation functions on edges.
Still Waters, Rapid Currents: Early Labor Market Transformation under Generative AI (NBER w33777)
by National Bureau of Economic Research (NBER)
NBER working paper w33777 by Humlum and Vestergaard on early labour-market effects of AI chatbots, using Danish data.