OpenFold: Retraining AlphaFold2 yields new insights into its learning mechanisms and capacity for generalization

G Ahdritz, N Bouatta, C Floristean, S Kadyan, Q Xia… - Nature …, 2024 - nature.com
AlphaFold2 revolutionized structural biology with the ability to predict protein structures with
exceptionally high accuracy. Its implementation, however, lacks the code and data required …

Towards the accurate alignment of over a million protein sequences: Current state of the art

L Santus, E Garriga, S Deorowicz, A Gudyś… - Current Opinion in …, 2023 - Elsevier
Large-scale genomics requires highly scalable and accurate multiple sequence alignment
methods. Results collected over this last decade suggest accuracy loss when scaling up …

Best Practices of Using AI-Based Models in Crystallography and Their Impact in Structural Biology

M Graille, S Sacquin-Mora, A Taly - Journal of Chemical …, 2023 - ACS Publications
The recent breakthrough made in the field of three-dimensional (3D) structure prediction by
artificial intelligence softwares, such as initially AlphaFold2 (AF2) and RosettaFold (RF) and …

Parallel loss of sexual reproduction in field populations of a brown alga sheds light on the mechanisms underlying the emergence of asexuality

M Hoshino, G Cossard, FB Haas, EI Kane… - Nature Ecology & …, 2024 - nature.com
Sexual reproduction is widespread, but asexual lineages have repeatedly arisen from
sexual ancestors across a wide range of eukaryotic taxa. The molecular changes …

AQcalc: A web server that identifies weak molecular interactions in protein structures

M Afshinpour, LA Smith, S Chakravarty - Protein Science, 2023 - Wiley Online Library
Weak molecular interactions play an important role in protein structure and function.
Computational tools that identify weak molecular interactions are, therefore, valuable for the …

Seqrutinator: scrutiny of large protein superfamily sequence datasets for the identification and elimination of non-functional homologues

A Amalfitano, N Stocchi, HM Atencio, F Villarreal… - Genome Biology, 2024 - Springer
Seqrutinator is an objective, flexible pipeline that removes sequences with sequencing
and/or gene model errors and sequences from pseudogenes from complex, eukaryotic …

Large-scale structure-informed multiple sequence alignment of proteins with SIMSApiper

C Crauwels, SL Heidig, A Díaz, WF Vranken - Bioinformatics, 2024 - academic.oup.com
SIMSApiper is a Nextflow pipeline that creates reliable, structure-informed MSAs of
thousands of protein sequences in time-frames faster than standard structure-based …

Sensitive inference of alignment-safe intervals from biodiverse protein sequence clusters using EMERALD

A Grigorjew, A Gynter, FHC Dias, B Buchfink, HG Drost… - Genome Biology, 2023 - Springer
 Abstract Sequence alignments are the foundations of life science research, but most
innovation so far focuses on optimal alignments, while information derived from suboptimal …

Augmentation of Structure Information to the Sequence-Based Machine Learning-Assisted Directed Protein Evolution

L Yutzy, K Nguyen, P Vallet, J Li, J Yu, R He, L Yan… - 2024 - chemrxiv.org
Directed evolution (DE) mimics natural selection to improve the functions of a target protein.
Machine learning (ML) has significantly streamlined DE by aiding in several steps, which …

Joint protein sequence-structure co-design via Equivariant diffusion

R Vinod, KK Yang, L Crawford - NeurIPS 2022 Workshop on …, 2022 - openreview.net
Protein macromolecules are known to play key roles in cellular processes. Solving inverse
design problems can allow us to control targeted cellular processes by designing proteins …