Benchmarking Molecular Methods of Protein Engineering and Surveying Protein Search Space to Bolster Artificial Intelligence-Based Designs
- 1Auburn University
Abstract
Proteins are complex macromolecules that drive functionality in cells across all life on Earth. Protein engineering and AI-based designs facilitate exploration of the vast search space. Herein, we explore and compare mutagenic methodologies in combination with fast and efficient phenotypic evaluation of a pink fluorophore (Magenta) to map protein search space and inform AI-based designer algorithms. We binned mutated variants as neutral, deleterious, or catastrophic based on the observed phenotype and fitness measurement (relative fluorescent units, RFUs). Importantly, we found that for a given fluorophore, about 80% of random mutations were deleterious for the artificially selected phenotype resulting in decreased fitness, 20% were neutral mutations, and 0.8% enhanced the artificially selected phenotype. Using error prone PCR (epPCR), we were able to identify four candidates in the first round and one candidate in the second round of epPCR for enhanced fluorescence and in toto enhanced RFUs by 35% after two rounds of epPCR. We compared these rates of true positive enhanced RFU generated sequences against a state of the art evolutionary algorithm approach and found that biological computation beats it in its current state. We conclude with suggestions for key improvements to enhance algorithm performance in the future. Taken together, we demonstrated that iterative rounds of variant prediction improved our algorithm, and our study can serve as a reference point for future AI driven modeling studies in red fluorescent protein engineering.
Related
- Artificial Intelligence for Predictive Microbiome Engineering: Integrating Community Design and Environmental Validation
- Explainable Artificial Intelligence (XAI) and Molecular Modeling Techniques to Discover Putative HER2 Inhibitors
- PMO-Dock: Benchmarking Docking, Specificity, and Generalization in Molecular Optimization
- Engineering Wheat for Compound Climate Extremes: Molecular Trade-Offs, Stress Memory, and Precision Genome Editing for Yield-Stable Resilience
- Toward Enactive Artificial Intelligence
BibTeX
@misc{ramamoorthy2026benchmarking,
title = {{Benchmarking Molecular Methods of Protein Engineering and Surveying Protein Search Space to Bolster Artificial Intelligence-Based Designs}},
author = {S. Ramamoorthy and R. Browning and J. Brandt and K. Tisdale and A. Schultz and M. V. L. Dalinger and N. Hengartner and D. R. Tauritz and J. F. Beckmann},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.16.759664},
url = {https://www.biorxiv.org/content/10.64898/2026.10.16.759664v1},
note = {CC BY-ND},
}
RIS
TY - UNPB
TI - Benchmarking Molecular Methods of Protein Engineering and Surveying Protein Search Space to Bolster Artificial Intelligence-Based Designs
AU - S. Ramamoorthy
AU - R. Browning
AU - J. Brandt
AU - K. Tisdale
AU - A. Schultz
AU - M. V. L. Dalinger
AU - N. Hengartner
AU - D. R. Tauritz
AU - J. F. Beckmann
PY - 2026
DA - 2026/10/16
PB - bioRxiv
DO - 10.64898/2026.10.16.759664
UR - https://www.biorxiv.org/content/10.64898/2026.10.16.759664v1
AB - Proteins are complex macromolecules that drive functionality in cells across all life on Earth. Protein engineering and AI-based designs facilitate exploration of the vast search space. Herein, we explore and compare mutagenic methodologies in combination with fast and efficient phenotypic evaluation of a pink fluorophore (Magenta) to map protein search space and inform AI-based designer algorithms. We binned mutated variants as neutral, deleterious, or catastrophic based on the observed phenotype and fitness measurement (relative fluorescent units, RFUs). Importantly, we found that for a given fluorophore, about 80% of random mutations were deleterious for the artificially selected phenotype resulting in decreased fitness, 20% were neutral mutations, and 0.8% enhanced the artificially selected phenotype. Using error prone PCR (epPCR), we were able to identify four candidates in the first round and one candidate in the second round of epPCR for enhanced fluorescence and in toto enhanced RFUs by 35% after two rounds of epPCR. We compared these rates of true positive enhanced RFU generated sequences against a state of the art evolutionary algorithm approach and found that biological computation beats it in its current state. We conclude with suggestions for key improvements to enhance algorithm performance in the future. Taken together, we demonstrated that iterative rounds of variant prediction improved our algorithm, and our study can serve as a reference point for future AI driven modeling studies in red fluorescent protein engineering.
ER -