Тип публикации: статья из журнала

Год издания: 2023

Идентификатор DOI: 10.1093/bioinformatics/btac724

Аннотация: <jats:title>Abstract</jats:title> <jats:sec> <jats:title>Motivation</jats:title> <jats:p>Multiple sequence alignments (MSAs) of homologous sequences contain information on structural and functional constraints and their evolutionary histories. Despite their importance for many downstream tasks, such as structure prediction, MSA genПоказать полностьюeration is often treated as a separate pre-processing step, without any guidance from the application it will be used for.</jats:p> </jats:sec> <jats:sec> <jats:title>Results</jats:title> <jats:p>Here, we implement a smooth and differentiable version of the Smith–Waterman pairwise alignment algorithm that enables jointly learning an MSA and a downstream machine learning system in an end-to-end fashion. To demonstrate its utility, we introduce SMURF (Smooth Markov Unaligned Random Field), a new method that jointly learns an alignment and the parameters of a Markov Random Field for unsupervised contact prediction. We find that SMURF learns MSAs that mildly improve contact prediction on a diverse set of protein and RNA families. As a proof of concept, we demonstrate that by connecting our differentiable alignment module to AlphaFold2 and maximizing predicted confidence, we can learn MSAs that improve structure predictions over the initial MSAs. Interestingly, the alignments that improve AlphaFold predictions are self-inconsistent and can be viewed as adversarial. This work highlights the potential of differentiable dynamic programming to improve neural network pipelines that rely on an alignment and the potential dangers of optimizing predictions of protein sequences with methods that are not fully understood.</jats:p> </jats:sec> <jats:sec> <jats:title>Availability and implementation</jats:title> <jats:p>Our code and examples are available at: https://github.com/spetti/SMURF.</jats:p> </jats:sec> <jats:sec> <jats:title>Supplementary information</jats:title> <jats:p>Supplementary data are available at Bioinformatics online.</jats:p> </jats:sec>

Журнал: Bioinformatics

Выпуск журнала: Т. 39, № 1

ISSN журнала: 13674803

Издатель: Oxford University Press

• Petti Samantha (NSF-Simons Center for the Mathematical and Statistical Analysis of Biology, Harvard University, Cambridge, MA 02138, USA)
• Bhattacharya Nicholas (Department of Mathematics, University of California Berkeley, Berkeley, CA 94720, USA)
• Rao Roshan (Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA 94720, USA)
• Dauparas Justas (Institute for Protein Design, University of Washington, Seattle, WA 98195, USA)
• Thomas Neil (Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA 94720, USA)
• Zhou Juannan (Department of Biology, University of Florida, Gainesville, FL 32611, USA)
• Rush Alexander M (Department of Computer Science, Cornell Tech, New York, NY 10044, USA)
• Koo Peter (Simons Center for Quantitative Biology, Cold Spring Harbor Laboratory, Cold Spring Harbor, NY 11724, USA)
• Ovchinnikov Sergey (John Harvard Distinguished Science Fellowship, Harvard University, Cambridge, MA 02138, USA)

• Ядро РИНЦ (eLIBRARY.RU)