Harnessing machine learning to guide phylogenetic-tree search algorithms

Inferring a phylogenetic tree is a fundamental challenge in evolutionary studies. Current paradigms for phylogenetic tree reconstruction rely on performing costly likelihood optimizations. With the aim of making tree inference feasible for problems involving more than a handful of sequences, inferen...

Full description

Saved in:
Bibliographic Details
Published in:Nature communications Vol. 12; no. 1; pp. 1983 - 9
Main Authors: Azouri, Dana, Abadi, Shiran, Mansour, Yishay, Mayrose, Itay, Pupko, Tal
Format: Journal Article
Language:English
Published: London Nature Publishing Group UK 31.03.2021
Nature Publishing Group
Nature Portfolio
Subjects:
631/114/1305
631/114/2397
631/181/735
631/181/757
Accuracy
Algorithms
Animals
Artificial intelligence
Computer applications
Computing time
Databases, Genetic - statistics & numerical data
Databases, Protein - statistics & numerical data
Empirical analysis
Evolution, Molecular
Humanities and Social Sciences
Humans
Inference
Learning algorithms
Machine Learning
Models, Genetic
multidisciplinary
Optimization
Phylogenetics
Phylogeny
Reconstruction
Run time (computers)
Science
Science (multidisciplinary)
Search algorithms
Sequences
Trees
ISSN:2041-1723, 2041-1723
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Inferring a phylogenetic tree is a fundamental challenge in evolutionary studies. Current paradigms for phylogenetic tree reconstruction rely on performing costly likelihood optimizations. With the aim of making tree inference feasible for problems involving more than a handful of sequences, inference under the maximum-likelihood paradigm integrates heuristic approaches to evaluate only a subset of all potential trees. Consequently, existing methods suffer from the known tradeoff between accuracy and running time. In this proof-of-concept study, we train a machine-learning algorithm over an extensive cohort of empirical data to predict the neighboring trees that increase the likelihood, without actually computing their likelihood. This provides means to safely discard a large set of the search space, thus potentially accelerating heuristic tree searches without losing accuracy. Our analyses suggest that machine learning can guide tree-search methodologies towards the most promising candidate trees. Likelihood optimization in phylogenetic tree reconstruction is computationally intensive, especially as the number of sequences and taxa included increase. Here, Azouri et al. show how an artificial intelligence approach can reduce computational time without losing accuracy of tree inference.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2041-1723
2041-1723
DOI:10.1038/s41467-021-22073-8