Accessible and robust machine learning approaches to improve the opsin genotype-phenotype map
Molecular Biology and Evolution · 2026
DOI: 10.1093/molbev/msag138 ↗Kurz gefasst
Fachartikel in der Zeitschrift Molecular Biology and Evolution, 2026. Verfasst von Seth A Frazer und 1 weiteren Autor:innen. Beteiligte Einrichtung: Ecology, Evolution, and Marine Biology, University of California, Santa Barbara, CA 93106. Hauptthemen laut MEDLINE: Machine Learning, Opsins, Genetic Association Studies. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 79 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Predicting phenotypes from genetic variation is a central challenge in biology. Here, machine learning (ML) offers great promise, but its use is often limited by poor accessibility, difficulty with interpretability, and a “data-cliff”—a gap between abundant sequences and scarce functional measurements. To develop more robust methods for genotype–phenotype prediction, an outstanding model system is opsin genes, visual pigments with extensive phenotypic information that strongly influence animal spectral sensitivity. Here, we advance ML characterization of the opsin genotype–phenotype map through four main contributions. First, we introduce the Opsin Phenotype Tool for Inference of Color Sensitivity, a user-friendly platform for predicting maximum wavelength sensitivity (λmax) from amino acid sequences, featuring integrated modules for SHapley Additive exPlanations and 3D structural mapping to reveal sequence-specific mechanistic drivers. Second, we show that encoding sequences with amino acid physicochemical properties improves predictive performance and interpretability over standard encoding methods and performs competitively with state-of-the-art protein language models, while retaining biological explainability. Finally, we present the Mine-N-Match pipeline, which systematically links published opsin sequences to compiled data on in vivo λmax values, expanding genotype–phenotype coverage and improving prediction, especially for undersampled taxa. By integrating accessible software, biologically informed encoding, and data harmonization, our framework improves confidence, accuracy, and interpretability of genotype–phenotype predictions for animal opsins. An accurate genotype–phenotype map will allow simulating molecular evolution of function, reconstructing the history of visual phenotypes, designing functional proteins, and generating new hypotheses that can be tested with heterologous phenotyping.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Ecology, Evolution, and Marine Biology, University of California, Santa Barbara, CA 93106.
ORCID-Profile: Seth A Frazer, Todd H Oakley
Zitieren
APA
Frazer, S. A., & Oakley, T. H. (2026). Accessible and robust machine learning approaches to improve the opsin genotype-phenotype map. Molecular Biology and Evolution. https://doi.org/10.1093/molbev/msag138
Vancouver
Frazer SA, Oakley TH. Accessible and robust machine learning approaches to improve the opsin genotype-phenotype map. Molecular Biology and Evolution. 2026. doi:10.1093/molbev/msag138
BibTeX
@article{Frazer2026,
author = {Frazer, Seth A and Oakley, Todd H},
title = {Accessible and robust machine learning approaches to improve the opsin genotype-phenotype map},
journal = {Molecular Biology and Evolution},
year = {2026},
doi = {10.1093/molbev/msag138}
}
EUVIMED