김규리 (서울대학교) | 한빛사논문 > 한빛사

한빛사논문

조회602

서울대학교

Cold Spring Harbor Perspect. Biol., Feb 05 2024, a041465 | https://doi.org/10.1101/cshperspect.a041465 Petabase-Scale Homology Search for Structure Prediction

Sewon Lee^1,10, Gyuri Kim^1,10, Eli Levy Karin², Milot Mirdita¹, Sukhwan Park³, Rayan Chikhi⁴, Artem Babaian^5,6, Andriy Kryshtafovych⁷and Martin Steinegger^1,3,8,9

¹School of Biological Sciences, Seoul National University, Gwanak-gu, Seoul 08826, South Korea

²ELKMO, Copenhagen 2720, Denmark

³Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul 08826, South Korea

⁴Institut Pasteur, Université Paris Cité, G5 Sequence Bioinformatics, 75015 Paris, France

⁵Department of Molecular Genetics, University of Toronto, Toronto, Ontario M5S 1A8, Canada

⁶Donnelly Centre for Cellular and Biomolecular Research, University of Toronto, Toronto, Ontario M5S 3E1, Canada

⁷Genome Center, University of California, Davis, California 95616, USA

⁸Artificial Intelligence Institute, Seoul National University, Seoul 08826, South Korea

⁹Institute of Molecular Biology and Genetics, Seoul National University, Seoul 08826, South Korea

¹⁰These authors contributed equally to this work.

Correspondence: Martin Steinegger

Abstract

The recent CASP15 competition highlighted the critical role of multiple sequence alignments (MSAs) in protein structure prediction, as demonstrated by the success of the top AlphaFold2-based prediction methods. To push the boundaries of MSA utilization, we conducted a petabase-scale search of the Sequence Read Archive (SRA), resulting in gigabytes of aligned homologs for CASP15 targets. These were merged with default MSAs produced by ColabFold-search and provided to ColabFold-predict. By using SRA data, we achieved highly accurate predictions (GDT_TS > 70) for 66% of the non-easy targets, whereas using ColabFold-search default MSAs scored highly in only 52%. Next, we tested the effect of deep homology search and ColabFold's advanced features, such as more recycles, on prediction accuracy. While SRA homologs were most significant for improving ColabFold's CASP15 ranking from 11th to 3rd place, other strategies contributed too. We analyze these in the context of existing strategies to improve prediction.

논문정보

형식Research article
게재일2024년 02월 (BRIC 등록일 2024-02-06)
연구진국내(교신)+국외 연구진
분야 생명과학 > 유전학

댓글 작성 로그인

CV 열람하기

연락처 보기