{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T23:13:39Z","timestamp":1781046819274,"version":"3.54.1"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T00:00:00Z","timestamp":1711584000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T00:00:00Z","timestamp":1711584000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Michaelis constant (K<jats:sub>M<\/jats:sub>) is one of essential parameters for enzymes kinetics in the fields of protein engineering, enzyme engineering, and synthetic biology. As overwhelming experimental measurements of K<jats:sub>M<\/jats:sub> are difficult and time-consuming, prediction of the K<jats:sub>M<\/jats:sub> values from machine and deep learning models would increase the pace of the enzymes kinetics studies. Existing machine and deep learning models are limited to the specific enzymes, i.e., a minority of enzymes or wildtype enzymes. Here, we used a deep learning framework PaddlePaddle to implement a machine and deep learning approach (GraphKM) for K<jats:sub>M<\/jats:sub> prediction of wildtype and mutant enzymes. GraphKM is composed by graph neural networks (GNN), fully connected layers and gradient boosting framework. We represented the substrates through molecular graph and the enzymes through a pretrained transformer-based language model to construct the model inputs. We compared the difference of the model results made by the different GNN (GIN, GAT, GCN, and GAT-GCN). The GAT-GCN-based model generally outperformed. To evaluate the prediction performance of the GraphKM and other reported K<jats:sub>M<\/jats:sub> prediction models, we collected an independent K<jats:sub>M<\/jats:sub> dataset (HXKm) from literatures.<\/jats:p>","DOI":"10.1186\/s12859-024-05746-1","type":"journal-article","created":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T13:01:42Z","timestamp":1711630902000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["GraphKM: machine and deep learning for KM prediction of wildtype and mutant enzymes"],"prefix":"10.1186","volume":"25","author":[{"given":"Xiao","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,28]]},"reference":[{"key":"5746_CR1","doi-asserted-by":"crossref","unstructured":"Bao, W., Gu, Y., Chen, B., and Yu, H. (2023) Golgi_DF: Golgi proteins classification with deep forest. 17","DOI":"10.3389\/fnins.2023.1197824"},{"key":"5746_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.chemolab.2021.104351","volume":"215","author":"W Bao","year":"2021","unstructured":"W Bao B Yang B Chen 2021 2-hydr_Ensemble: Lysine 2-hydroxyisobutyrylation identification with ensemble method Chemom Intell Lab Syst 215 104351","journal-title":"Chemom Intell Lab Syst"},{"key":"5746_CR3","doi-asserted-by":"publisher","first-page":"2467","DOI":"10.1101\/gr.1262503","volume":"13","author":"CG Moles","year":"2003","unstructured":"CG Moles P Mendes JR Banga 2003 Parameter estimation in biochemical pathways: a comparison of global optimization methods Genome Res 13 2467 2474","journal-title":"Genome Res"},{"key":"5746_CR4","doi-asserted-by":"publisher","first-page":"2832","DOI":"10.1016\/j.febslet.2013.06.043","volume":"587","author":"K Smallbone","year":"2013","unstructured":"K Smallbone HL Messiha KM Carroll CL Winder N Malys WB Dunn E Murabito N Swainston JO Dada F Khan P Pir E Simeonidis I Spasi\u0107 J Wishart D Weichart NW Hayes D Jameson DS Broomhead SG Oliver SJ Gaskell JEG McCarthy NW Paton HV Westerhoff DB Kell P Mendes 2013 A model of yeast glycolysis based on a consistent kinetic characterisation of all its enzymes FEBS Lett 587 2832 2841","journal-title":"FEBS Lett"},{"key":"5746_CR5","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1016\/j.engappai.2017.04.004","volume":"62","author":"MA Remli","year":"2017","unstructured":"MA Remli S Deris MS Mohamad S Omatu JM Corchado 2017 An enhanced scatter search with combined opposition-based learning for parameter estimation in large-scale kinetic models of biochemical systems Eng Appl Artif Intell 62 164 180","journal-title":"Eng Appl Artif Intell"},{"key":"5746_CR6","doi-asserted-by":"publisher","first-page":"2205","DOI":"10.1016\/j.asoc.2013.01.019","volume":"13","author":"S Da Ros","year":"2013","unstructured":"S Ros Da G Colusso TA Weschenfelder L Marsillac Terra de F Castilhos de ML Corazza M Schwaab 2013 A comparison among stochastic optimization algorithms for parameter estimation of biochemical kinetic models Appl Soft Comput 13 2205 2214","journal-title":"Appl Soft Comput"},{"key":"5746_CR7","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.3001402","author":"A Kroll","year":"2021","unstructured":"A Kroll MKM Engqvist D Heckmann MJ Lercher 2021 Deep learning allows genome-scale prediction of Michaelis constants from structural features PLoS Biol https:\/\/doi.org\/10.1371\/journal.pbio.3001402","journal-title":"PLoS Biol"},{"key":"5746_CR8","first-page":"80","volume":"17","author":"S Borger","year":"2006","unstructured":"S Borger W Liebermeister E Klipp 2006 Prediction of Enzyme Kinetic Parameters Based on Statistical Learning Genome Inform 17 80 87","journal-title":"Genome Inform"},{"key":"5746_CR9","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1007\/s12539-012-0115-z","volume":"4","author":"S-M Yan","year":"2012","unstructured":"S-M Yan D-Q Shi H Nong G Wu 2012 Predicting Km values of beta-glucosidases using cellobiose as substrate Interdiscipl Sci Comput Life Sci 4 46 53","journal-title":"Interdiscipl Sci Comput Life Sci"},{"key":"5746_CR10","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1186\/s12859-022-05009-x","volume":"23","author":"K Maeda","year":"2022","unstructured":"K Maeda A Hatae Y Sakai FC Boogerd H Kurata 2022 MLAGO: machine learning-aided global optimization for Michaelis constant estimation of kinetic modeling BMC Bioinform 23 455","journal-title":"BMC Bioinform"},{"key":"5746_CR11","doi-asserted-by":"crossref","unstructured":"Gori, M., Monfardini, G., and Scarselli, F. (2005) A new model for learning in graph domains. In Proceedings of 2005 IEEE International Joint Conference on Neural Networks, 2005.","DOI":"10.1109\/IJCNN.2005.1555942"},{"key":"5746_CR12","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","volume":"20","author":"F Scarselli","year":"2009","unstructured":"F Scarselli M Gori AC Tsoi M Hagenbuchner G Monfardini 2009 The graph neural network model IEEE Trans Neural Netw 20 61 80","journal-title":"IEEE Trans Neural Netw"},{"key":"5746_CR13","unstructured":"Keyulu Xu, W. H., Jure Leskovec, Stefanie Jegelka. (2019) How powerful are graph neural networks? In Proceeding of the international conference on learning representations"},{"key":"5746_CR14","unstructured":"Petar Veli\u010dkovi\u0107, G. C., Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, Yoshua Bengio. (2018) Graph attention networks. In: Proceedings of the international conference on learning representations"},{"key":"5746_CR15","unstructured":"Kipf, T. N., Welling, Max. (2017) Semi-supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representations"},{"key":"5746_CR16","unstructured":"Xu, K., Hu, W., Leskovec, J., and Jegelka, S. (2018) How Powerful are Graph Neural Networks?"},{"key":"5746_CR17","unstructured":"Kipf, T., Welling, M. J. A. (2016) Semi-supervised classification with graph convolutional networks. arXiv:abs\/1609.02907"},{"key":"5746_CR18","doi-asserted-by":"publisher","first-page":"1593","DOI":"10.1126\/science.146.3651.1593","volume":"146","author":"C Yanofsky","year":"1964","unstructured":"C Yanofsky V Horn D Thorpe 1964 Protein structure relationships revealed by mutational analysis Science 146 1593 1594","journal-title":"Science"},{"key":"5746_CR19","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1093\/protein\/2.3.193","volume":"2","author":"D Altschuh","year":"1988","unstructured":"D Altschuh T Vernet P Berti D Moras K Nagai 1988 Coordinated amino acid changes in homologous protein families Protein Eng 2 193 199","journal-title":"Protein Eng"},{"key":"5746_CR20","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1002\/prot.340180402","volume":"18","author":"U G\u00f6bel","year":"1994","unstructured":"U G\u00f6bel C Sander R Schneider A Valencia 1994 Correlated mutations and residue contacts in proteins Proteins 18 309 317","journal-title":"Proteins"},{"key":"5746_CR21","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1109\/TCBB.2007.70225","volume":"5","author":"J Thomas","year":"2008","unstructured":"J Thomas N Ramakrishnan C Bailey-Kellogg 2008 Graphical models of residue coupling in protein families IEEE\/ACM Trans Comput Biol Bioinform 5 183 197","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"5746_CR22","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","volume":"379","author":"Z Lin","year":"2023","unstructured":"Z Lin H Akin R Rao B Hie Z Zhu W Lu N Smetanin R Verkuil O Kabeli Y Shmueli A Santos Costa dos M Fazel-Zarandi T Sercu S Candido A Rives 2023 Evolutionary-scale prediction of atomic-level protein structure with a language model Science 379 1123 1130","journal-title":"Science"},{"key":"5746_CR23","doi-asserted-by":"crossref","unstructured":"Chen, T., Guestrin, C. (2016) XGBoost: a scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, Association for Computing Machinery, San Francisco, California, USA","DOI":"10.1145\/2939672.2939785"},{"issue":"1189\u20131232","key":"5746_CR24","first-page":"1144","volume":"29","author":"JH Friedman","year":"2001","unstructured":"JH Friedman 2001 Greedy function approximation: a gradient boosting machine Science 29 1189\u20131232 1144","journal-title":"Science"},{"key":"5746_CR25","doi-asserted-by":"publisher","first-page":"D498","DOI":"10.1093\/nar\/gkaa1025","volume":"49","author":"A Chang","year":"2021","unstructured":"A Chang L Jeske S Ulbrich J Hofmann J Koblitz I Schomburg M Neumann-Schaal D Jahn D Schomburg 2021 BRENDA, the ELIXIR core data resource in 2021: new developments and updates Nucl Acids Res 49 D498 d508","journal-title":"Nucl Acids Res"},{"key":"5746_CR26","doi-asserted-by":"publisher","first-page":"D656","DOI":"10.1093\/nar\/gkx1065","volume":"46","author":"U Wittig","year":"2018","unstructured":"U Wittig M Rey A Weidemann R Kania W M\u00fcller 2018 SABIO-RK: an updated resource for manually curated biochemical reaction kinetics Nucl Acids Res 46 D656 d660","journal-title":"Nucl Acids Res"},{"key":"5746_CR27","doi-asserted-by":"publisher","first-page":"D1388","DOI":"10.1093\/nar\/gkaa971","volume":"49","author":"S Kim","year":"2021","unstructured":"S Kim J Chen T Cheng A Gindulyte J He S He Q Li BA Shoemaker PA Thiessen B Yu L Zaslavsky J Zhang EE Bolton 2021 PubChem in 2021: new data content and improved web interfaces Nucl Acids Res 49 D1388 d1395","journal-title":"Nucl Acids Res"},{"key":"5746_CR28","unstructured":"(2023) UniProt: the universal protein knowledgebase in 2023. Nucl Acids Res 51, D523\u2013D531"},{"key":"5746_CR29","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1093\/bioinformatics\/btaa921","volume":"37","author":"T Nguyen","year":"2021","unstructured":"T Nguyen H Le TP Quinn T Nguyen TD Le S Venkatesh 2021 GraphDTA: predicting drug\u2013target binding affinity with graph neural networks Bioinformatics 37 1140 1147","journal-title":"Bioinformatics"},{"key":"5746_CR30","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, \u00c9. (2011) Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825\u20132830"},{"key":"5746_CR31","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1093\/nar\/28.1.27","volume":"28","author":"M Kanehisa","year":"2000","unstructured":"M Kanehisa S Goto 2000 KEGG: Kyoto Encyclopedia of Genes and Genomes Nucl Acids Res 28 27 30","journal-title":"Nucl Acids Res"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-024-05746-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-024-05746-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-024-05746-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T13:02:04Z","timestamp":1711630924000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-024-05746-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,28]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["5746"],"URL":"https:\/\/doi.org\/10.1186\/s12859-024-05746-1","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,28]]},"assertion":[{"value":"16 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 March 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 March 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"135"}}