Learning graph representations of biochemical networks and its application to enzymatic link prediction

Jiang, Julie; Liu, Liping; Hassoun, Soha

doi:10.1093/bioinformatics/btaa881

Cited by 11 publications

(7 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…eQuilibrator ( Beber et al , 2022 ; Noor et al , 2013 )], or likelihood of a biochemical conversion between a substrate and a product [e.g. DeepRFC ( Kim et al , 2021 ) and ELP ( Jiang et al , 2021 )], SOM prediction determines the likelihood of an enzyme class acting on a particular atom or bond within a molecule. Therefore, when paired with a rule-based method, the SOM likelihood can be assumed a proxy for the likelihood of reaction occurrence.…”

Section: Resultsmentioning

confidence: 99%

Using graph neural networks for site-of-metabolism prediction and its applications to ranking promiscuous enzymatic products

2023

View full text Add to dashboard Cite

Motivation While traditionally utilized for identifying site-specific metabolic activity within a compound to alter its interaction with a metabolizing enzyme, predicting the Site-of-Metabolism (SOM) is essential in analyzing the promiscuity of enzymes on substrates. The successful prediction of SOMs and the relevant promiscuous products has a wide range of applications that include creating extended metabolic models that account for enzyme promiscuity and the construction of novel heterologous synthesis pathways. There is therefore a need to develop generalized methods that can predict molecular SOMs for a wide range of metabolizing enzymes. Results This paper develops a Graph Neural Network (GNN) model for the classification of an atom (or a bond) being an SOM. Our model, GNN-SOM, is trained on enzymatic interactions, available in the KEGG database, that span all enzyme commission numbers. We demonstrate that GNN-SOM consistently outperforms baseline Machine Learning (ML) models, when trained on all enzymes, on Cytochrome P450 (CYP) enzymes, or on non-CYP enzymes. We showcase the utility of GNN-SOM in prioritizing predicted enzymatic products due to enzyme promiscuity for two biological applications: the construction of Extended Metabolic Models (EMMs) and the construction of synthesis pathways. Availability A python implementation of the trained SOM predictor model can be found at https://github.com/HassounLab/GNN-SOM Supplementary information Not applicable

show abstract

Section: Resultsmentioning

confidence: 99%

Using graph neural networks for site-of-metabolism prediction and its applications to ranking promiscuous enzymatic products

2023

View full text Add to dashboard Cite

show abstract

“…Machine-learning (ML) approaches have taken advantage of available enzymatic data and solve many important questions such the likelihood of enzymatic transformations between a compound pair, e.g. support vector machines ( Kotera et al , 2013 ), graph embedding ( Jiang et al , 2021 ), identifying enzyme commission numbers that act on molecules, e.g. using hierarchical classification of enzymes on molecules ( Visani et al, 2021 ), and predicting the likelihood of a sequence catalyzing a reaction or quantifying the affinity of sequences on substrates using Gaussian processes ( Mellor et al , 2016 ).…”

Section: Introductionmentioning

confidence: 99%

Boost-RS: boosted embeddings for recommender systems and its application to enzyme–substrate interaction prediction

Liu

Hassoun

2022

Bioinformatics

Self Cite

View full text Add to dashboard Cite

Motivation Despite experimental and curation efforts, the extent of enzyme promiscuity on substrates continues to be largely unexplored and under documented. Providing computational tools for the exploration of the enzyme-substrate interaction space can expedite experimentation and benefit applications such as constructing synthesis pathways for novel biomolecules, identifying products of metabolism on ingested compounds, and elucidating xenobiotic metabolism. Recommender systems (RS), which are currently unexplored for the enzyme-substrate interaction prediction problem, can be utilized to provide enzyme recommendations for substrates, and vice versa. The performance of Collaborative-Filtering (CF) recommender systems however hinges on the quality of embedding vectors of users and items (enzymes and substrates in our case). Importantly, enhancing CF embeddings with heterogeneous auxiliary data, specially relational data (e.g., hierarchical, pairwise, or groupings), remains a challenge. Results We propose an innovative general RS framework, termed Boost-RS, that enhances RS performance by “boosting” embedding vectors through auxiliary data. Specifically, Boost-RS is trained and dynamically tuned on multiple relevant auxiliary learning tasks Boost-RS utilizes contrastive learning tasks to exploit relational data. To show the efficacy of Boost-RS for the enzyme-substrate prediction interaction problem, we apply the Boost-RS framework to several baseline CF models. We show that each of our auxiliary tasks boosts learning of the embedding vectors, and that contrastive learning using Boost-RS outperforms attribute concatenation and multi-label learning. We also show that Boost-RS outperforms similarity-based models. Ablation studies and visualization of learned representations highlight the importance of using contrastive learning on some of the auxiliary data in boosting the embedding vectors. Availability and implementation A Python implementation for Boost-RS is provided at https://github.com/HassounLab/Boost-RS

show abstract

“…Prediction of putative enzymatic links, e.g. Selenzyme ( Carbonell et al., 2018 ), XTMS ( Carbonell et al., 2014 ) and ELP ( Jiang et al., 2020 ), allows the construction of novel biosynthesis or biodegradation pathways. The study of enzyme promiscuity also elucidates the evolution of metabolic networks ( Carbonell et al., 2011 ).…”

Section: Introductionmentioning

confidence: 99%

Enzyme promiscuity prediction using hierarchy-informed multi-label classification

2021

Self Cite

View full text Add to dashboard Cite

Motivation As experimental efforts are costly and time consuming, computational characterization of enzyme capabilities is an attractive alternative. We present and evaluate several machine-learning models to predict which of 983 distinct enzymes, as defined via the Enzyme Commission (EC) numbers, are likely to interact with a given query molecule. Our data consists of enzyme-substrate interactions from the BRENDA database. Some interactions are attributed to natural selection and involve the enzyme’s natural substrates. The majority of the interactions however involve non-natural substrates, thus reflecting promiscuous enzymatic activities. Results We frame this “enzyme promiscuity prediction” problem as a multi-label classification task. We maximally utilize inhibitor and unlabelled data to train prediction models that can take advantage of known hierarchical relationships between enzyme classes. We report that a hierarchical multi-label neural network, EPP-HMCNF, is the best model for solving this problem, outperforming k-nearest neighbours similarity-based and other machine learning models. We show that inhibitor information during training consistently improves predictive power, particularly for EPP-HMCNF. We also show that all promiscuity prediction models perform worse under a realistic data split when compared to a random data split, and when evaluating performance on non-natural substrates compared to natural substrates. Availability and implementation We provide Python code for EPP-HMCNF and other models in a repository termed EPP (Enzyme Promiscuity Prediction) at https://github.com/hassounlab/EPP. Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

Learning graph representations of biochemical networks and its application to enzymatic link prediction

Cited by 11 publications

References 41 publications

Using graph neural networks for site-of-metabolism prediction and its applications to ranking promiscuous enzymatic products

Using graph neural networks for site-of-metabolism prediction and its applications to ranking promiscuous enzymatic products

Boost-RS: boosted embeddings for recommender systems and its application to enzyme–substrate interaction prediction

Enzyme promiscuity prediction using hierarchy-informed multi-label classification

Contact Info

Product

Resources

About