De novo generation of functional terpene synthases using TpsGPT

Hamsini Ramanathan, Roman Bushuiev, Matouš Soldát, Jiří Kohout, Téo Hebra, Joshua David Smith, Tomas Pluskal

Track: Track 1: Original Research/Position/Education/Attention Track

Keywords: Terpene Synthases, Generative AI, Protein Language Models, ProtGPT2, De Novo Enzyme Engineering

TL;DR: Fine-tuning ProtGPT2 enables scalable generation of de novo and valid Terpene Synthase enzymes, providing a cost-effective alternative to traditional experimental approaches.

Abstract: Terpene synthases (TPS) are a key family of enzymes responsible for generating the diverse terpene scaffolds that underpin many natural products, including front-line anticancer drugs such as Taxol. However, de novo TPS design through directed evolution is costly and slow. We introduce TpsGPT, a generative model for scalable TPS protein design, built by fine-tuning the protein language model ProtGPT2 on 79k TPS sequences mined from UniProt. TpsGPT generates de novo enzyme candidates in silico and evaluates them using multiple validation metrics, including EnzymeExplorer classification, ESMFold structural confidence (pLDDT), sequence diversity, CLEAN classification, InterPro domain detection, and Foldseek structure alignment. From an initial pool of 28k generated sequences, we identified seven putative TPS enzymes that satisfied all validation criteria. Experimental validation confirmed TPS enzymatic activity in at least two of these sequences. Our results show that fine-tuning of a protein language model on a carefully curated, enzyme-class-specific dataset, combined with rigorous filtering, can enable the de novo generation of functional, evolutionarily distant enzymes.

Submission Number: 200