GraphKM: machine and deep learning for KM prediction of wildtype and mutant enzymes

Michaelis constant (K M ) 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 M are difficult and time-consuming, prediction of the K M values from machine and deep learnin...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	BMC bioinformatics Ročník 25; číslo 1; s. 1 - 12
Hlavní autoři:	He, Xiao, Yan, Ming
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	London BioMed Central 28.03.2024 BioMed Central Ltd Springer Nature B.V BMC
Témata:	Algorithms Amino acids Application programming interface Artificial intelligence Bioinformatics Biology Biomedical and Life Sciences Computational Biology/Bioinformatics Computer Appl. in Life Sciences Datasets Deep learning Enzyme kinetics Enzymes Genetic aspects Graph neural network Graph neural networks Graphical representations Identification and classification Kinetics Learning algorithms Life Sciences Machine learning Michaelis constant Microarrays Mutants Mutation (Biology) Neural networks Prediction models Protein engineering Protein research Proteins Substrates Tree boosting China Deep learning Neural networks Michaelis constant Tree boosting Graph neural network
ISSN:	1471-2105, 1471-2105
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Michaelis constant (K M ) 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 M are difficult and time-consuming, prediction of the K M 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 M 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 M prediction models, we collected an independent K M dataset (HXKm) from literatures.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ISSN:	1471-2105 1471-2105
DOI:	10.1186/s12859-024-05746-1