Accessible and robust machine learning approaches to improve the opsin genotype-phenotype map

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.