Four recently released ES and ER prediction models are benchmarked and it is suggested that interaction-aware representations from full biomolecular complexes may provide a promising basis for enzyme prioritization.
Abstract
Artificial Intelligence has had a profound impact on the biological sciences, and in particular has accelerated research on protein form and function. Enzymes are no exception: a surge of predictive models have been recently developed to address a range of enzyme tasks. Models addressing enzyme-substrate (ES) or enzyme-reaction (ER) compatibility could be especially valuable for enzyme annotation, biosynthetic pathway elucidation, and biocatalyst retrieval, the central challenge of which is the identification of a true catalyst (or truly compatible reaction) among many similar candidates. While existing models report strong performance on alternative benchmarks, less is known about their capabilities in this regime. Herein, we benchmark four recently released ES and ER prediction models, using tasks and datasets tailored to this setting. We first show that two representative ES prediction models perform near random baselines across two enzyme families when considering enzymes and substrates not encountered during training. To evaluate additional models across a consistent dataset, we next assemble the largest cytochrome P450 (CYP) reaction dataset to date, 2,922 reactions across 768 enzymes, and construct a CYP ranking benchmark requiring the correct enzyme to be prioritized among all CYPs in its native organism. We again find that most models do not outperform sequence-based (BLAST) baselines even after fine-tuning. We finally adapt the bimolecular structure prediction model Boltz to ES prediction by training supervised classifiers on residue-ligand pair embeddings, and show that this approach consistently surpasses the BLAST baselines on our CYP ranking benchmark. Together, our results argue for more discovery-relevant benchmarking and suggest that interaction-aware representations from full biomolecular complexes may provide a promising basis for enzyme prioritization.
Accurate computational prediction of enzyme function, standardized by Enzyme Commission (EC) numbers, is essential for large-scale genome annotation and generative enzyme design. However, it remains unclear whether state-of-the-art predictors learn the intrinsic structural determinants of catalytic activity or merely rely on global sequence similarity to annotated homologues. To address this gap, we introduce EnzymARC, a novel benchmark dataset of putative non-functional decoy sequences generated via structure-guided, systematic disruption of active sites (targeting catalytic residues and surrounding 5 Å, 10 Å, and 15 Å radii) from experimentally annotated enzymes. We evaluated three distinct prediction paradigms against this dataset: homology-based annotation (DIAMOND), contrastive learning with protein language models (CLEAN), and a deep learning model incorporating non-enzyme discrimination (DeepEC). Our findings reveal that current models are highly vulnerable to phylogenetic shortcuts. Both DIAMOND and CLEAN exhibited false positive rates exceeding 90% for low-perturbation decoys, confidently assigning the original EC numbers despite the destruction of the catalytic machinery. While DeepEC demonstrated improved sensitivity at higher perturbation levels—highlighting the benefit of negative training examples—all models struggled to identify targeted active-site disruptions. We demonstrate that modern EC predictors largely fail to distinguish catalytically incompetent variants from functional enzymes, and we propose that integrating structure-aware negative examples into both training and benchmarking is critical for developing functionally robust models in computational enzymology.
João Sartori, Ana Carolina Ramos Guimarães, Lucas de Almeida Machado· bioRxiv· 0 citations
This manuscript introduces EnzGFM, an enzyme-specific hybrid model that improves both accuracy and efficiency across multiple prediction tasks and, together with the EnzGFM-Agent pipeline, demonstrates the ability to identify experimentally validated beneficial variants while reducing screening effort.
It is found that, while AF3 can perform well in favourable settings, this performance is uneven across applications and its predictions and use of confidence metrics will depend strongly on the specific application area and must be interpreted with respect to training-set overlap.
O. Follonier, Yan Liu, Pablo Campomanes et al.· bioRxiv· 1 citation
Accurate enzyme annotation remains a major bottleneck in translating rapidly growing protein sequence data into biological knowledge. Enzyme Commission (EC) prediction is particularly challenging because enzyme functions are organized hierarchically, annotations are often imbalanced across classes, and sequence similarity alone may be insufficient to resolve functional differences. To address these challenges, we developed ESM-ECForest, a two-stage framework that combines protein embeddings generated by the pretrained language model ESM-2 (Evolutionary Scale Modeling 2) with Random Forest classifiers. The first stage distinguishes enzymes from non-enzymes, whereas the second assigns one or more EC numbers to proteins predicted to be enzymatic. On an external benchmark comprising 25,778 protein sequences, ESM-ECForest achieved the highest weighted F1 score among the evaluated methods at all four EC levels, decreasing from 0.94 at Level 1 to 0.90 at Level 4. The largest relative improvements were observed for lyases (EC 4), ligases (EC 6), and translocases (EC 7), although EC 6 and EC 7 remained the most difficult classes internally. Visualization of the ESM-2 embedding space using Uniform Manifold Approximation and Projection (UMAP) revealed clustering patterns consistent with enzyme functional relationships, indicating that biologically relevant information is retained in the pretrained representations prior to supervised classification. These results support the use of pretrained protein language model embeddings as an effective foundation for enzyme annotation. By combining large-scale sequence representations with a lightweight supervised classifier, ESM-ECForest provides a scalable approach for EC prediction and may facilitate functional annotation of protein sequences derived from large genomic and metagenomic datasets.
Harnessing enzyme specificity requires a thorough understanding of enzyme promiscuity, which determines enzymes’ catalytic scope; however, measuring this scope still relies heavily on labor-intensive analytical approaches. While data-driven approaches have emerged to predict the catalytic scope of enzymes, these methods continue to face challenges such as restricted datasets and insufficient integration of enzyme structural information and reaction transformations. Here, we introduce MAERM, an innovative mixed-attention model designed to predict enzyme-reaction matching relationships. Built on our MAERM-DB, a dataset with broad coverage of validated and chemoenzymatic catalysis data, MAERM utilizes a local-global attention module to integrate multimodal enzyme information with fine-grained reaction representations, thereby predicting enzyme-reaction matching probabilities. Results show that MAERM consistently outperforms all baselines, with an average F1-score of 0.984. Notably, on challenging test samples with less than 40% sequence identity to the training set, MAERM outperforms the second-ranked model by 5.9% in F1-score. In addition, MAERM achieves the highest top-10 success rate of 51.7% on Enzyme-405 and the highest balanced accuracy of 0.697 on BioCat-547, further supporting its generalizability in enzyme screening and chemoenzymatic catalysis. Finally, MAERM can serve as an efficient scoring module. When integrated with ProteinMPNN, MAERM has successfully guided novel enzyme design for two carbonyl reduction reactions, resulting in enhanced catalytic potential for the native substrate and demonstrating broad compatibility. Overall, MAERM has the potential to reduce the experimental cost of measuring enzymes’ catalytic scope, facilitate enzyme design, and ultimately accelerate the design-build-test-learn cycle in enzyme engineering.
Tiantao Liu, Silong Zhai, Shaolong Lin et al.· bioRxiv· 0 citations
This mini review traces the evolution of AI-driven methods in protein research, from early residue-contact prediction using coevolutionary information to transformative breakthroughs, the rise of protein language models (PLMs), and the emerging era of generative design and functional modeling.
Guodong Min, Huan Peng· Methods in molecular biology· 0 citations
