IDEPI: Rapid Prediction of HIV-1 Antibody Epitopes and Other Phenotypic Features from Sequence Data Using a Flexible Machine Learning Platform

By Ben Murrell, Sasha Moola, Amandla Mabona, Thomas Weighill, D. Sheward, Sergei L. Kosakovsky Pond, Konrad Scheffler. PLoS Comput. Biol., 2014

893 citations recorded by the source corpus.

Since its identification in 1983, HIV-1 has been the focus of a research effort unprecedented in scope and difficulty, whose ultimate goals — a cure and a vaccine – remain elusive. One of the fundamental challenges in accomplishing these goals is the tremendous genetic variability of the virus, with some genes differing at as many as 40% of nucleotide positions among circulating strains. Because of this, the genetic bases of many viral phenotypes, most notably the susceptibility to neutralization by a particular antibody, are difficult to identify computationally. Drawing upon open-source general-purpose machine learning algorithms and libraries, we have developed a software package IDEPI (IDentify EPItopes) for learning genotype-to-phenotype predictive models from sequences with known phenotypes. IDEPI can apply learned models to classify sequences of unknown phenotypes, and also identify specific sequence features which contribute to a particular phenotype. We demonstrate that IDEPI achieves performance similar to or better than that of previously published approaches on four well-studied problems: finding the epitopes of broadly neutralizing antibodies (bNab), determining coreceptor tropism of the virus, identifying compartment-specific genetic signatures of the virus, and deducing drug-resistance associated mutations. The cross-platform Python source code (released under the GPL 3.0 license), documentation, issue tracking, and a pre-configured virtual machine for IDEPI can be found at https://github.com/veg/idepi.

Subfields: Molecular Biology, Virology

View Paper: https://www.semanticscholar.org/paper/3e80018153019250d7fc587335ba7d03ad8785ca

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

In Virology

Citations in the corpus

Pervasive tertiary structure in the dengue virus RNA genome (2018, methodology): “Synonymous substitution rates at individual codon sites were estimated using the phylogenetic-based parametric maximum likelihood FUBAR method (27).”
The 2019‐new coronavirus epidemic: Evidence for virus evolution (2020, methodology): “For this purpose, the following test has been used: fast unconstrained Bayesian approximation (FUBAR).(13) This test allowed us to infer the site‐specific pervasive selection, the episodic diversifying selection across the region of interest, and to identify episodic selection at individual sites.”
Stability-mediated epistasis constrains the evolution of an influenza protein (2013, methodology): “…destabilizing mutations are thus disproportionately important for viral immune escape, and may have been favored by selection for this property (a dN/dS test [Murrell et al., 2013] is inconclusive, probably due to lack of sequence data; Figure 8—figure supplement 3 and Figure 8—source code 2).”
HyPhy 2.5 - a customizable platform for evolutionary hypothesis testing using phylogenies. (2019, background): “…of machine learning and natural language processing (Blei et al. 2003) to limit the number of expensive likelihood calculations for certain key applications, namely high-throughput screens for evidence of natural selection along alignments containing thousands of sequences (Murrell et al. 2013).”
Functional Constraint Profiling of a Viral Protein Reveals Discordance of Evolutionary Conservation and Functionality (2015, methodology): “From the FUBAR output, dN/dS for each codon was calculated by beta/alpha, where beta was the posterior mean non-synonymous substitution rate and alpha was the posterior mean synonymous substitution rate.”