Recent Publications

^†Corresponding author, ^#First author

RNA3DB: A structurally-dissimilar dataset split for training and benchmarking deep learning models for RNA structure prediction
Szikszai M, Magnus M, Sanghi S, Kadyan S, Bouatta N, Rivas E. (2024)
Journal of Molecular Biology

• Coverage: MCB Harvard
   

OpenProteinSet: Training data for structural biology at scale
Ahdritz G, Bouatta N,^† Kadyan S, Jarosch L, Berenberg D, Fisk I, Watkins A,  Ra S, Bonneau R, AlQuraishi M. (2023)
NeurIPS (Datasets and Benchmarks Track)

• The largest database for training AlphaFold2-like systems.
• Featured by Hugging Face Daily Papers.
   

Structural biology at the scale of proteomes
Bouatta N,^† and AlQuraishi M. (2023)
Nature Structural & Molecular Biology
 

OpenFold: Retraining AlphaFold2 yields new insights into its learning mechanisms and capacity for generalization
Ahdritz G, Bouatta N,^†,# Kadyan S, Xia Q, Gerecke W, O'Donnell T, Berenberg D, Fisk I, Zanichelli N, Zhang B, Nowaczynski A, Wang B, Stepniewska-Dziubinska M, Zhang S, Ojewole A, Guney M, Biderman S, Watkins A,  Ra S, Lorenzo P, Nivon L,  Weitzner B, Ban Y, Sorger P, Mostaque E, Zhang Z, Bonneau R, AlQuraishi M. (2022)
Nature Methods

• Media coverage: Didero, TechCrunch, Weights & Biases, GeekWire, Riken, Nature Methods, Nature Biotechnology.
• OpenFold software is offered as a service by leading cloud and compute providers, including Amazon (I, II) and NVIDIA (I, II). 
• Used by Meta AI for the creation of the ESM Metagenomic Atlas, which contains over 600 million predicted protein structures.
   

Single-sequence protein structure prediction using language models and deep learning
Chowdhury R, Bouatta N,^†,# Biswas S, Floristean C, Rochereau C, Kharkar A, Ahdritz G, Zhang J, Church G, Sorger P, and AlQuraishi M. (2022). 
Nature Biotechnology

• Featured as the cover of the Nov. 2022 issue of Nature Biotechnology.
• Associated commentary: Michaud J, Madani A, Fraser J. (2022) A language model beats alphafold2 on orphans. Nature Biotechnology.
• Derek Lowe (2021) Another Way to Do Protein Structure Prediction, In the Pipeline, Science.
• More coverage: Forbes (I, II)

Protein structure prediction by AlphaFold2: are attention and symmetries all you need?
Bouatta N,^†  Sorger P,  AlQuraishi M. (2021)
Acta Crystallographica D 

• Featured as the cover of the August 2021 issue of Acta Crystallographica D.