In-Person Poster presentation / poster accept
Multiple sequence alignment as a sequence-to-sequence learning problem
Edo Dotan · Yonatan Belinkov · Oren Avram · Elya Wygoda · Noa Ecker · Michael Alburquerque · Omri Keren · Gil Loewenthal · Tal Pupko
MH1-2-3-4 #131
Keywords: [ sequence alignment ] [ natural language processing ] [ molecular evolution ] [ bioinformatics ] [ Machine Learning for Sciences ]
The sequence alignment problem is one of the most fundamental problems in bioinformatics and a plethora of methods were devised to tackle it. Here we introduce BetaAlign, a methodology for aligning sequences using an NLP approach. BetaAlign accounts for the possible variability of the evolutionary process among different datasets by using an ensemble of transformers, each trained on millions of samples generated from a different evolutionary model. Our approach leads to alignment accuracy that is similar and often better than commonly used methods, such as MAFFT, DIALIGN, ClustalW, T-Coffee, PRANK, and MUSCLE.