@article{herrerarocha2026multitask,

title = {Multitask Bayesian Neural Networks for Multiparameter Protein Engineering [Preprint]},

author = {Fabio Herrera-Rocha and David Medina-Ortiz and Desiree Wyrzykala and Tharun Srinivasan Sudha and Mehdi D. Davari},

doi = {10.48550/arxiv.2608.18604},

year  = {2026},

date = {2026-01-01},

urldate = {2026-01-01},

journal = {arXiv},

publisher = {Cornell University},

abstract = {Simultaneously engineering multiple protein properties remains a major challenge. Existing machine learning-based pipelines for protein engineering often model properties separately, failing to capture their dependencies and trade-offs. Here, we systematically evaluate how Bayesian parameterization on Multitask Neural Networks can enable robust simultaneous protein engineering under scarce, noisy experimental data. We curated a comprehensive set of 27 multiparameter protein datasets. Then, we compared three algorithm architectures spanning low to full Bayesian parameterization across 16 sequence representations and dimensionality reduction (2,592 models). Bayesian Last Layer models delivered the strongest overall accuracy, generalization, and calibration, ranking as the top-performing model on 70% of benchmark datasets. Dimensionality reduction improved predictive performance by up to 42% and enhanced calibration up to 57% across architectures. Notably, simple One-Hot encoding achieved top performance on 25% of benchmark datasets, particularly with larger datasets. These results establish practical design principles for reliable and data-efficient multiparameter protein engineering.},

keywords = {Artificial neural network, Bayesian probability, Benchmark (surveying), Curse of dimensionality, Dimensionality reduction, DiP-BioCasNavi, DiP-LeFos, Feature engineering, Ranking (information retrieval), Set (abstract data type)},

pubstate = {published},

tppubtype = {article}

}