{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T14:49:49Z","timestamp":1792162189261,"version":"4.4.0"},"reference-count":48,"publisher":"American Chemical Society (ACS)","issue":"10","license":[{"start":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T00:00:00Z","timestamp":1790467200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T00:00:00Z","timestamp":1790467200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T00:00:00Z","timestamp":1790467200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100013066","name":"Key Scientific Research Project of Colleges and Universities in Henan Province","doi-asserted-by":"publisher","award":["26B130003"],"award-info":[{"award-number":["26B130003"]}],"id":[{"id":"10.13039\/501100013066","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,16]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurate prediction of enzyme optimal pH (pHopt) is fundamental to biocatalyst engineering, pharmaceutical development, and process optimization, yet developing a reliable computational method remains challenging. To address this limitation, we present trPHopt, which is based on a structure-guided hybrid framework integrating the Graph Convolutional Network (GCN) with the Transformer. At the feature representation, trPHopt introduces new structural features to better characterize residue microenvironments relevant to pHopt. At the model architecture level, our method adopts a parallel dual-stream encoder: a structure-guided multi-head self-attention stream that incorporates geometric features as attention biases to capture long-range residue dependencies, and a Dense GCN stream that aggregates fused residue representations over distance-weighted residue graphs. The encoder-layer outputs are combined through a residual fusion gate, with the GCN contribution modulated by a learnable scalar coefficient. To alleviate the bias toward neutral predictions caused by label distribution imbalance, we further employ a two-stage calibration strategy that couples the coarse-grained acidic\/neutral\/alkaline classifier with a confidence-aware calibrator under a logical consistency constraint. On the independent test set, trPHopt consistently outperforms classical machine learning models and state-of-the-art methods, achieving an RMSE of 0.794 and an R2 of 0.527. These results demonstrate that trPHopt provides an accurate and practical method for enzyme pHopt prediction.<\/jats:p>","DOI":"10.1021\/acssynbio.6c00421","type":"journal-article","created":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T20:01:56Z","timestamp":1790539316000},"page":"4240-4251","source":"Crossref","is-referenced-by-count":0,"title":["Structure-Guided Hybrid GCN\u2212Transformer Framework for Enzyme Optimal pH Prediction"],"prefix":"10.1021","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0435-2701","authenticated-orcid":true,"given":"Lianci","family":"Tao","sequence":"first","affiliation":[{"name":"Xinxiang University , , ,","place":["Xinxiang, China, 453003"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jilong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Technology , , ,","place":["Beijing, China, 100124"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenxiao","family":"Xiang","sequence":"additional","affiliation":[{"name":"Shandong University , , ,","place":["Qingdao, China, 266237"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Yang","sequence":"additional","affiliation":[{"name":"Xinxiang University , , ,","place":["Xinxiang, China, 453003"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Wei","sequence":"additional","affiliation":[{"name":"Xinxiang University , , ,","place":["Xinxiang, China, 453003"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Kang","sequence":"additional","affiliation":[{"name":"Xinxiang University , , ,","place":["Xinxiang, China, 453003"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,9,27]]},"reference":[{"key":"2026101610070510000_cit1","doi-asserted-by":"publisher","first-page":"20547","DOI":"10.1021\/acs.jafc.5c03673","article-title":"An overview of industrial enzyme engineering to achieve a pH adaptability-activity trade-off: Current status and future perspectives","volume":"73","author":"Hu","year":"2025","journal-title":"J. Agric. Food Chem."},{"key":"2026101610070510000_cit2","doi-asserted-by":"publisher","first-page":"900","DOI":"10.1016\/j.bbapap.2008.03.008","article-title":"The kinetic properties producing the perfunctory pH profiles of catalase-peroxidases","volume":"1784","author":"Moore","year":"2008","journal-title":"Biochim. Biophys. Acta - Proteins Proteom."},{"key":"2026101610070510000_cit3","doi-asserted-by":"publisher","first-page":"1084","DOI":"10.1104\/pp.84.4.1084","article-title":"pH Effects on the Activity and Regulation of the NAD Malic Enzyme","volume":"84","author":"Willeford","year":"1987","journal-title":"Plant Physiology"},{"key":"2026101610070510000_cit4","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1002\/bit.27169","article-title":"One-shot optimization of multiple enzyme parameters: Tailoring glucose oxidase for pH and electron mediators","volume":"117","author":"Ostafe","year":"2020","journal-title":"Biotechnol. Bioeng."},{"key":"2026101610070510000_cit5","doi-asserted-by":"publisher","first-page":"14454","DOI":"10.1021\/acscatal.3c03417","article-title":"Accelerating biocatalysis discovery with machine learning: a paradigm shift in enzyme engineering, discovery, and design","volume":"13","author":"Markus","year":"2023","journal-title":"ACS Catal."},{"key":"2026101610070510000_cit6","first-page":"gzab019","article-title":"Machine learning for enzyme engineering, selection and design","volume":"34","author":"Feehan","year":"2021","journal-title":"Protein Eng. Des. Sel."},{"key":"2026101610070510000_cit7","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1038\/s42256-025-01026-6","article-title":"Machine learning prediction of enzyme optimum pH","volume":"7","author":"Gado","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"2026101610070510000_cit8","doi-asserted-by":"publisher","first-page":"3013","DOI":"10.1021\/acssynbio.4c00465","article-title":"Approaching optimal pH enzyme prediction with large language models","volume":"13","author":"Zaretckii","year":"2024","journal-title":"ACS Synth. Biol."},{"key":"2026101610070510000_cit9","doi-asserted-by":"publisher","first-page":"bbaf114","DOI":"10.1093\/bib\/bbaf114","article-title":"Seq2Topt: a sequence-based deep learning predictor of enzyme optimal temperature","volume":"26","author":"Qiu","year":"2025","journal-title":"Briefings Bioinf."},{"key":"2026101610070510000_cit10","doi-asserted-by":"publisher","first-page":"4897","DOI":"10.1021\/acssynbio.5c00679","article-title":"Deep learning-based prediction of enzyme optimal pH and design of point mutations to improve acid resistance","volume":"14","author":"Qiu","year":"2025","journal-title":"ACS Synth. Biol."},{"key":"2026101610070510000_cit11","doi-asserted-by":"publisher","first-page":"4772","DOI":"10.3168\/jds.2021-21760","article-title":"Engineering the optimum pH of \u03b2-galactosidase from Aspergillus oryzae for efficient hydrolysis of lactose","volume":"105","author":"Shi","year":"2022","journal-title":"J. Dairy Sci."},{"key":"2026101610070510000_cit12","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/s12257-012-0455-x","article-title":"Shifting the optimum pH of Bacillus circulans xylanase towards acidic side by introducing arginine","volume":"18","author":"Pokhrel","year":"2013","journal-title":"Biotechnol. Bioprocess Eng."},{"key":"2026101610070510000_cit13","doi-asserted-by":"publisher","first-page":"D439","DOI":"10.1093\/nar\/gkab1061","article-title":"AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models","volume":"50","author":"Varadi","year":"2022","journal-title":"Nucleic Acids Res."},{"key":"2026101610070510000_cit14","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"key":"2026101610070510000_cit15","doi-asserted-by":"publisher","first-page":"1056","DOI":"10.1038\/s41594-022-00849-w","article-title":"A structural biology community assessment of AlphaFold2 applications","volume":"29","author":"Akdel","year":"2022","journal-title":"Nat. Struct. Mol. Biol."},{"key":"2026101610070510000_cit16","doi-asserted-by":"publisher","first-page":"3142","DOI":"10.1021\/acs.jcim.2c00026","article-title":"AI-based protein structure prediction in drug discovery: impacts and challenges","volume":"62","author":"Schauperl","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"2026101610070510000_cit17","doi-asserted-by":"publisher","first-page":"5634","DOI":"10.1038\/s41596-021-00628-9","article-title":"The trRosetta server for fast and accurate protein structure prediction","volume":"16","author":"Du","year":"2021","journal-title":"Nat. Protoc."},{"key":"2026101610070510000_cit18","doi-asserted-by":"publisher","first-page":"10977","DOI":"10.1021\/acs.jcim.5c01830","article-title":"TCNeKP: A Novel Deep Learning Architecture for Enzyme Catalytic Activity Prediction","volume":"65","author":"Lei","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"2026101610070510000_cit19","doi-asserted-by":"publisher","first-page":"bbaf476","DOI":"10.1093\/bib\/bbaf476","article-title":"Autoregressive enzyme function prediction with multi-scale multi-modality fusion","volume":"26","author":"Rong","year":"2025","journal-title":"Briefings Bioinf."},{"key":"2026101610070510000_cit20","doi-asserted-by":"publisher","first-page":"110348","DOI":"10.1016\/j.compbiomed.2025.110348","article-title":"A multimodal deep learning framework for enzyme turnover prediction with missing modality","volume":"193","author":"Sun","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"2026101610070510000_cit21","doi-asserted-by":"publisher","first-page":"btad718","DOI":"10.1093\/bioinformatics\/btad718","article-title":"DeepProSite: structure-aware protein binding site prediction using ESMFold and pretrained language model","volume":"39","author":"Fang","year":"2023","journal-title":"Bioinformatics"},{"key":"2026101610070510000_cit22","doi-asserted-by":"crossref","unstructured":"Rives, A.; Meier, J.; Sercu, T.; Goyal, S.; Lin, Z.; Liu, J.; Guo, D.; Ott, M.; Zitnick, C. L.; Ma, J.\n          Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences; Proceedings of the national academy of sciences, 2021; Vol. 118, p e2016239118.","DOI":"10.1073\/pnas.2016239118"},{"key":"2026101610070510000_cit23","doi-asserted-by":"publisher","first-page":"arXiv:2006.05205 2020","DOI":"10.48550\/arXiv.2006.05205","article-title":"On the bottleneck of graph neural networks and its practical implications","author":"Alon","year":"2020","journal-title":"arXiv"},{"key":"2026101610070510000_cit24","doi-asserted-by":"publisher","first-page":"btad189","DOI":"10.1093\/bioinformatics\/btad189","article-title":"Structure-aware protein self-supervised learning","volume":"39","author":"Chen","year":"2023","journal-title":"Bioinformatics"},{"key":"2026101610070510000_cit25","doi-asserted-by":"publisher","first-page":"btac715","DOI":"10.1093\/bioinformatics\/btac715","article-title":"sAMPpred-GAT: prediction of antimicrobial peptide by graph attention network and predicted peptide structure","volume":"39","author":"Yan","year":"2023","journal-title":"Bioinformatics"},{"key":"2026101610070510000_cit26","doi-asserted-by":"crossref","unstructured":"Xiong, H.; Yao, A.\n          Deep imbalanced regression via hierarchical classification adjustment. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024; pp 23721\u221223730.","DOI":"10.1109\/CVPR52733.2024.02239"},{"key":"2026101610070510000_cit27","first-page":"7","volume-title":"Ssr-Net: A Compact Soft Stagewise Regression Network for Age Estimation","author":"Yang","year":"2018"},{"key":"2026101610070510000_cit28","doi-asserted-by":"publisher","first-page":"3548","DOI":"10.1021\/acs.jcim.3c02011","article-title":"ESPDHot: An Effective Machine Learning-Based Approach for Predicting Protein\u2212DNA Interaction Hotspots","volume":"64","author":"Tao","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"2026101610070510000_cit29","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1016\/j.jbiotec.2017.04.020","article-title":"The BRENDA enzyme information system\u2212From a database to an expert system","volume":"261","author":"Schomburg","year":"2017","journal-title":"J. Biotechnol."},{"key":"2026101610070510000_cit30","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1093\/nar\/28.1.374","article-title":"AAindex: amino acid index database","volume":"28","author":"Kawashima","year":"2000","journal-title":"Nucleic Acids Res."},{"key":"2026101610070510000_cit31","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1038\/nrm3920","article-title":"Intrinsically disordered proteins in cellular signalling and regulation","volume":"16","author":"Wright","year":"2015","journal-title":"Nat. Rev. Mol. Cell Biol."},{"key":"2026101610070510000_cit32","doi-asserted-by":"publisher","first-page":"1182","DOI":"10.1111\/febs.13202","article-title":"Functional roles of transiently and intrinsically disordered regions within proteins","volume":"282","author":"Uversky","year":"2015","journal-title":"The FEBS journal"},{"key":"2026101610070510000_cit33","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1016\/j.tibs.2023.08.001","article-title":"Intrinsically disordered regions are poised to act as sensors of cellular chemistry","volume":"48","author":"Moses","year":"2023","journal-title":"Trends Biochem. Sci."},{"key":"2026101610070510000_cit34","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1007\/s10930-009-9201-4","article-title":"Intrinsically disordered proteins and their environment: effects of strong denaturants, temperature, pH, counter ions, membranes, binding partners, osmolytes , and macromolecular crowding","volume":"28","author":"Uversky","year":"2009","journal-title":"The protein journal"},{"key":"2026101610070510000_cit35","doi-asserted-by":"publisher","first-page":"W329","DOI":"10.1093\/nar\/gky384","article-title":"IUPred2A: context-dependent prediction of protein disorder as a function of redox state and protein binding","volume":"46","author":"Me\u0301sza\u0301ros","year":"2018","journal-title":"Nucleic Acids Res."},{"key":"2026101610070510000_cit36","volume-title":"ESM Cambrian: Revealing the Mysteries of Proteins with Unsupervised Learning","author":"Team","year":"2024"},{"key":"2026101610070510000_cit37","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1186\/s12915-025-02418-1","article-title":"AIPred: comprehensive prediction and analysis of non-histone acetylation via protein language model and interpretable machine learning","volume":"23","author":"Geng","year":"2025","journal-title":"BMC Biol."},{"key":"2026101610070510000_cit38","doi-asserted-by":"publisher","first-page":"btag006","DOI":"10.1093\/bioinformatics\/btag006","article-title":"RoBep: a region-oriented deep learning model for B-cell epitope prediction","volume":"42","author":"Xu","year":"2026","journal-title":"Bioinformatics"},{"key":"2026101610070510000_cit39","doi-asserted-by":"publisher","DOI":"10.3791\/68003","article-title":"Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins","author":"Rami\u0301rez-Villarreal","year":"2025","journal-title":"J. Vis. Exp."},{"key":"2026101610070510000_cit40","doi-asserted-by":"crossref","unstructured":"Norn, C.; Wicky, B. I.; Juergens, D.; Liu, S.; Kim, D.; Tischer, D.; Koepnick, B.; Anishchenko, I.; Players, F.; Baker, D.\n          Protein sequence design by conformational landscape optimization; Proceedings of the National Academy of Sciences, 2021; Vol. 118, p e2017228118.","DOI":"10.1101\/2020.07.23.218917"},{"key":"2026101610070510000_cit41","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1021\/ar500301y","article-title":"Theoretical insights into the functioning of metallopeptidases and their synthetic analogues","volume":"48","author":"Zhang","year":"2015","journal-title":"Acc. Chem. Res."},{"key":"2026101610070510000_cit42","doi-asserted-by":"publisher","first-page":"arXiv:2301.06568","DOI":"10.48550\/arXiv.2301.06568","article-title":"Ankh: Optimized protein language model unlocks general-purpose modelling","author":"Elnaggar","year":"2023","journal-title":"arXiv"},{"key":"2026101610070510000_cit43","doi-asserted-by":"publisher","first-page":"lqae150","DOI":"10.1093\/nargab\/lqae150","article-title":"Bilingual language model for protein sequence and structure","volume":"6","author":"Heinzinger","year":"2024","journal-title":"NAR:Genomics Bioinf."},{"key":"2026101610070510000_cit44","doi-asserted-by":"publisher","first-page":"1565","DOI":"10.1038\/nbt1206-1565","article-title":"What is a support vector machine?","volume":"24","author":"Noble","year":"2006","journal-title":"Nat. Biotechnol."},{"key":"2026101610070510000_cit45","doi-asserted-by":"publisher","first-page":"31","DOI":"10.17849\/insm-47-01-31-39.1","article-title":"Random forest","volume":"47","author":"Rigatti","year":"2017","journal-title":"J. Insur. Med."},{"key":"2026101610070510000_cit46","doi-asserted-by":"crossref","unstructured":"Chen, T.; Guestrin, C.\n          Xgboost: A scalable tree boosting system. In Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, 2016; pp 785\u2212794.","DOI":"10.1145\/2939672.2939785"},{"key":"2026101610070510000_cit47","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1162\/neco.1992.4.3.415","article-title":"Bayesian Interpolation","author":"MacKay","year":"1992","journal-title":"Neural Comput."},{"key":"2026101610070510000_cit48","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/bf02478259","article-title":"A logical calculus of the ideas immanent in nervous activity","volume":"5","author":"McCulloch","year":"1943","journal-title":"Bull. Math. Biophys."}],"container-title":["ACS Synthetic Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acssynbio.6c00421","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/asbcd6\/article-pdf\/15\/10\/4240\/68669928\/sb6c00421.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/asbcd6\/article-pdf\/15\/10\/4240\/68669928\/sb6c00421.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T14:23:53Z","timestamp":1792160633000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/asbcd6\/article\/15\/10\/4240\/5439541\/Structure-Guided-Hybrid-GCN-Transformer-Framework"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,27]]},"references-count":48,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,9,27]]},"published-print":{"date-parts":[[2026,10,16]]}},"URL":"https:\/\/doi.org\/10.1021\/acssynbio.6c00421","relation":{},"ISSN":["2161-5063"],"issn-type":[{"value":"2161-5063","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,27]]}}}