MyESL: A software for evolutionary sparse learning in molecular phylogenetics and genomics

Evolutionary sparse learning (ESL) uses supervised machine learning to build evolutionary models where genomic sites and loci are parameters. It uses the Least Absolute Shrinkage and Selection Operator (LASSO) with bi-level sparsity to connect a specific phylogenetic hypothesis with sequence variation across genomic loci. The MyESL software addresses the need for open-source tools to perform ESL analyses, offering features to pre-process input phylogenomic alignments, post-process output models to generate molecular evolutionary metrics, and make LASSO regression adaptable and efficient for phylogenetic trees and alignments. The core of MyESL, which constructs models with logistic regressions using bi-level sparsity, is written in C++. Its input data pre-processing and result post-processing tools are developed in Python. Compared to other tools, MyESL is more computationally efficient and provides evolution-friendly input and output options. These features have already enabled the use of MyESL in two phylogenomic applications, one to identify outlier sequences and fragile clades in inferred phylogenies and another to build a genetic model of convergent traits. In addition to the use in a Python environment, MyESL is available as a standalone executable compatible across multiple platforms and can be directly integrated into scripts and third-party software. The source code, executable, and documentation for MyESL are openly accessible at https://github.com/kumarlabgit/MyESL.