Cargando…
Boost-RS: boosted embeddings for recommender systems and its application to enzyme–substrate interaction prediction
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 applicat...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Oxford University Press
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9113267/ https://www.ncbi.nlm.nih.gov/pubmed/35561204 http://dx.doi.org/10.1093/bioinformatics/btac201 |
_version_ | 1784709554369462272 |
---|---|
author | Li, Xinmeng Liu, Li-Ping Hassoun, Soha |
author_facet | Li, Xinmeng Liu, Li-Ping Hassoun, Soha |
author_sort | Li, Xinmeng |
collection | PubMed |
description | 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) RSs; 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. The enzyme-substrate interaction data is available from the KEGG database (https://www.genome.jp/kegg/). |
format | Online Article Text |
id | pubmed-9113267 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Oxford University Press |
record_format | MEDLINE/PubMed |
spelling | pubmed-91132672022-05-18 Boost-RS: boosted embeddings for recommender systems and its application to enzyme–substrate interaction prediction Li, Xinmeng Liu, Li-Ping Hassoun, Soha Bioinformatics Original Papers 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) RSs; 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. The enzyme-substrate interaction data is available from the KEGG database (https://www.genome.jp/kegg/). Oxford University Press 2022-04-12 /pmc/articles/PMC9113267/ /pubmed/35561204 http://dx.doi.org/10.1093/bioinformatics/btac201 Text en © The Author(s) 2022. Published by Oxford University Press. https://creativecommons.org/licenses/by-nc/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial License (https://creativecommons.org/licenses/by-nc/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is properly cited. For commercial re-use, please contact journals.permissions@oup.com |
spellingShingle | Original Papers Li, Xinmeng Liu, Li-Ping Hassoun, Soha Boost-RS: boosted embeddings for recommender systems and its application to enzyme–substrate interaction prediction |
title | Boost-RS: boosted embeddings for recommender systems and its application to enzyme–substrate interaction prediction |
title_full | Boost-RS: boosted embeddings for recommender systems and its application to enzyme–substrate interaction prediction |
title_fullStr | Boost-RS: boosted embeddings for recommender systems and its application to enzyme–substrate interaction prediction |
title_full_unstemmed | Boost-RS: boosted embeddings for recommender systems and its application to enzyme–substrate interaction prediction |
title_short | Boost-RS: boosted embeddings for recommender systems and its application to enzyme–substrate interaction prediction |
title_sort | boost-rs: boosted embeddings for recommender systems and its application to enzyme–substrate interaction prediction |
topic | Original Papers |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9113267/ https://www.ncbi.nlm.nih.gov/pubmed/35561204 http://dx.doi.org/10.1093/bioinformatics/btac201 |
work_keys_str_mv | AT lixinmeng boostrsboostedembeddingsforrecommendersystemsanditsapplicationtoenzymesubstrateinteractionprediction AT liuliping boostrsboostedembeddingsforrecommendersystemsanditsapplicationtoenzymesubstrateinteractionprediction AT hassounsoha boostrsboostedembeddingsforrecommendersystemsanditsapplicationtoenzymesubstrateinteractionprediction |