OUP accepted manuscript

2021

Subfields: Natural Language Processing

Citations in the corpus

• Generalized Biomolecular Modeling and Design with RoseTTAFold All-Atom (2023, neutral): “…the leading non – deep-learning protein – small molecule docking method AutoDock Vina, developed by the CAMEO organizers, that predicts the protein structure by homology modeling ( 19 – 24 ), runs AutoDock to dock the small molecules, and ranks the poses using the Vina scoring function( 9 , 19 ).”
• Critical assessment of protein intrinsic disorder prediction (CAID) ‐ Results of round 2 (2023, methodology): “To establish a comparison baseline, we also incorporated the AlphaFold-disorder package, 9 which utilizes AlphaFold2 predicted structures publicly available in databases 10,11 to infer predictions for disorder and binding.”
• Evolutionary-scale prediction of atomic level protein structure with a language model (2022, background): “[28] Mihaly Varadi, Stephen Anyango, Mandar Deshpande, Sreenath Nair, Cindy Natassia, Galabina Yordanova, David Yuan, Oana Stroe, Gemma Wood, Agata Laydon, Augustin ŽÂıdek, Tim Green, Kathryn Tunyasuvunakool, Stig Petersen, John Jumper, Ellen Clancy, Richard Green, Ankur Vora, Mira Lutfi, Michael Fi”
• Genenames.org: the HGNC resources in 2023 (2022, methodology): “And for all genes with a UniProtKB/Swiss-Prot (reviewed) protein link, we have also added links to view protein structures predicted by the Artificial Intelligence algorithm AlphaFold2 at the AlphaFold Protein Structure Database (31) from the Pro- tein Resources section of our Symbol Reports (Figure”
• How accurately can one predict drug binding modes using AlphaFold models? (2023, background): “Up- to-date AF2 models for any human protein are readily available for download ( Tunyasuvunakool et al., 2021 ; Varadi et al., 2022 ).”
• CavitySpace: A Database of Potential Ligand Binding Sites in the Human Proteome (2022, methodology): “AlphaFold was then applied to build protein structure models for human proteome [28,29], which dramatically”
• Benchmarking AlphaFold for protein complex modeling reveals accuracy determinants (2021, methodology): “…were also observed for previously reported docking model ranking methods ZRANK2 15 and IRAD 29 (Table 1), while an interface energy score from Rosetta 45 (cross-interface binding energy) resulted in the highest model classification accuracy, based on the binary classification AUC metrics (Table 1).”
• The next-generation Open Targets Platform: reimagined, redesigned, rebuilt (2022, background): “The recent inclusion of the AlphaFold protein structure predictions in the target profile page allows the identification of potential druggable pockets in previously unresolved 3D models (34).”
• OpenFold: retraining AlphaFold2 yields new insights into its learning mechanisms and capacity for generalization (2023, unknown): “Having established parity, we find that OpenFold is remarkably robust at generalizing even when the size and diversity of its training set is deliberately limited, including near-complete elisions of classes of secondary structure elements.”
• The expanding genetic and clinical landscape associated with Meier-Gorlin syndrome (2023, unknown): “The AlphaFold prediction (AlphaFoldDB ID: HUMAN_DONS) (Fig.”
• DNSN-1 recruits GINS for CMG helicase assembly during DNA replication initiation in C. elegans (2023, unknown): “…DNSN-1 complex bound to a fork DNA substrate, initial models for individual subunits were taken from the AlphaFold Protein Structure Database (65, 66) and fitted as rigid-bodies to our cryo-EM density using UCSF Chimera (64) for MCM-2-7 subunits, the NTDs, AAA+ domains and winged-helix (WH)…”