Beyond model organisms: robust prediction of functional properties across protein evolution

Biological discovery and design are increasingly being guided by surrogate models trained on high-throughput technologies in place of costly experimentation. However, existing datasets are often biased by overrepresentation from model organisms, leading to failures when performing evolutionary studies in non-model species. We present a hybrid framework that leverages high-throughput molecular assays and active learning to quantify biological properties across evolutionary space. We focus on transcriptional activators, which contain activation domains (ADs) that promote gene expression. ADs are intrinsically disordered and poorly conserved, which limits their study using alignment-based algorithms. Here, we develop ADhunter, a high-capacity regression model that outperforms state-of-the-art algorithms in identifying and quantifying the strength of ADs. Predictive uncertainty is used to guide evolutionary sampling across 7,842,516 proteins from 2,400 fungal genomes. We functionally characterized 9,836 ADs from 1,071 fungal genomes, providing a 15.5-fold expansion in genome representation compared to existing datasets. Comprehensive sampling improves model generalizability and provides the first functional annotation for 3,416 proteins in non-model fungi, highlighting the importance of sampling from non-model organisms to build evolutionarily robust models for predicting biological properties.