Identifying enzymes capable of catalyzing specific chemical transformations across large sequence databases remains a major challenge in biocatalyst discovery. Conventional fingerprint-based methods capture global molecular structure but fail to represent bond-breaking and bond-forming events, limiting generalization to structurally novel reactions. We introduce a dual-track evaluation framework to distinguish true generalization from memorization, assessing retrieval on structurally isolated reactions (n = 50) within a 63,259-sequence enzyme pool. The strongest fingerprint baseline achieves R@10 = 0.020. To address this limitation, we develop GATv2-ECR, a heterogeneous dual-tower model integrating reaction-center graph encoding, a frozen ESM-2 sequence encoder, contrastive learning, and EC-aware soft reranking. GATv2-ECR achieves R@10 = 0.160 on isolated queries and R@10 = 0.308 on an out-of-distribution subset (n = 39), capturing mechanistically relevant features and supporting generalizable enzyme retrieval under open-world conditions.
Si-Yuan Wang, Dan Wang, Ying Ren et al.· Journal of Chemical Informat...· 0 citations
Improving enzyme stability without compromising catalytic activity remains a major challenge in protein engineering. Here, we present a co-evolution-guided strategy to enhance both thermostability and catalytic performance of the flavin-dependent monooxygenase MonCI, an enzyme involved in monensin biosynthesis. By combining sequence covariation analysis with structural filtering, a focused library of 15 single mutants yielded 4 variants with increased stability and activity. Combinatorial assembly generated triple, quadruple and quintuple mutants, with the best-performing quadruple variants exhibiting up to a 10 °C increase in melting temperature, a 2.3-fold increase in specific activity, and a 2.1-fold longer half-life, accompanied by enhanced turnover despite reduced substrate affinity. Crystal structures and molecular dynamics simulations reveal that stabilization arises from strengthened intramolecular networks of hydrogen bonds, salt bridges, and hydrophobic interactions, while epistatic effects limit additive improvements. This work provides mechanistic insight into how co-evolving residues modulate enzyme structure and function, presents a useful co-evolution-guided strategy for enzyme design, and advances MonCI as a promising biocatalyst for asymmetric epoxidation.
Hongli Xiao, Jing Li, Jiajie Zhou et al.· International Journal of Bio...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
