Handcrafted versus non-handcrafted (self-supervised) features for the classification of antimicrobial peptides: complementary or redundant?
- 10 October 2022
- journal article
- research article
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 23 (6)
Abstract
Antimicrobial peptides (AMPs) have received a great deal of attention given their potential to become a plausible option to fight multi-drug resistant bacteria as well as other pathogens. Quantitative sequence-activity models (QSAMs) have been helpful to discover new AMPs because they allow to explore a large universe of peptide sequences and help reduce the number of wet lab experiments. A main aspect in the building of QSAMs based on shallow learning is to determine an optimal set of protein descriptors (features) required to discriminate between sequences with different antimicrobial activities. These features are generally handcrafted from peptide sequence datasets that are labeled with specific antimicrobial activities. However, recent developments have shown that unsupervised approaches can be used to determine features that outperform human-engineered (handcrafted) features. Thus, knowing which of these two approaches contribute to a better classification of AMPs, it is a fundamental question in order to design more accurate models. Here, we present a systematic and rigorous study to compare both types of features. Experimental outcomes show that non-handcrafted features lead to achieve better performances than handcrafted features. However, the experiments also prove that an improvement in performance is achieved when both types of features are merged. A relevance analysis reveals that non-handcrafted features have higher information content than handcrafted features, while an interaction-based importance analysis reveals that handcrafted features are more important. These findings suggest that there is complementarity between both types of features. Comparisons regarding state-of-the-art deep models show that shallow models yield better performances both when fed with non-handcrafted features alone and when fed with non-handcrafted and handcrafted features together.Keywords
Funding Information
- CONACyT (A1-S-20638)
- Centro de Investigación Científica y de Educación Superior de Ensenada (501/2018)
This publication has 93 references indexed in Scilit:
- Incorporating key position and amino acid residue features to identify general and species-specific Ubiquitin conjugation sitesBioinformatics, 2013
- AVPpred: collection and prediction of highly effective antiviral peptidesNucleic Acids Research, 2012
- Multifunctional host defense peptides: antiparasitic activitiesThe FEBS Journal, 2009
- Predicting protein–protein interactions based only on sequences informationProceedings of the National Academy of Sciences, 2007
- PROFEAT: a web server for computing structural and physicochemical features of proteins and peptides from amino acid sequenceNucleic Acids Research, 2006
- Prediction of protein cellular attributes using pseudo‐amino acid compositionProteins: Structure, Function, and Bioinformatics, 2001
- Generalized molecular descriptorsJournal of Mathematical Chemistry, 1991
- Coordinated amino acid changes in homologous protein familiesProtein Engineering, Design and Selection, 1988
- Correlation of co-ordinated amino acid substitutions with function in viruses related to tobacco mosaic virusJournal of Molecular Biology, 1987
- Protein Structure Relationships Revealed by Mutational AnalysisScience, 1964