Teasing out missing reactions in genome-scale metabolic networks through hypergraph learning
Abstract GEnome-scale Metabolic models (GEMs) are powerful tools to predict cellular metabolism and physiological states in living organisms. However, due to our imperfect knowledge of metabolic processes, even highly curated GEMs have knowledge gaps (e.g., missing reactions). Existing gap-filling m...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-04-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-023-38110-7 |
| _version_ | 1797836355596713984 |
|---|---|
| author | Can Chen Chen Liao Yang-Yu Liu |
| author_facet | Can Chen Chen Liao Yang-Yu Liu |
| author_sort | Can Chen |
| collection | DOAJ |
| description | Abstract GEnome-scale Metabolic models (GEMs) are powerful tools to predict cellular metabolism and physiological states in living organisms. However, due to our imperfect knowledge of metabolic processes, even highly curated GEMs have knowledge gaps (e.g., missing reactions). Existing gap-filling methods typically require phenotypic data as input to tease out missing reactions. We still lack a computational method for rapid and accurate gap-filling of metabolic networks before experimental data is available. Here we present a deep learning-based method — CHEbyshev Spectral HyperlInk pREdictor (CHESHIRE) — to predict missing reactions in GEMs purely from metabolic network topology. We demonstrate that CHESHIRE outperforms other topology-based methods in predicting artificially removed reactions over 926 high- and intermediate-quality GEMs. Furthermore, CHESHIRE is able to improve the phenotypic predictions of 49 draft GEMs for fermentation products and amino acids secretions. Both types of validation suggest that CHESHIRE is a powerful tool for GEM curation to reveal unknown links between reactions and observed metabolic phenotypes. |
| first_indexed | 2024-04-09T15:08:34Z |
| format | Article |
| id | doaj.art-7116d52c8719454ea23bf8591bcad107 |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-04-09T15:08:34Z |
| publishDate | 2023-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-7116d52c8719454ea23bf8591bcad1072023-04-30T11:20:52ZengNature PortfolioNature Communications2041-17232023-04-0114111110.1038/s41467-023-38110-7Teasing out missing reactions in genome-scale metabolic networks through hypergraph learningCan Chen0Chen Liao1Yang-Yu Liu2Channing Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital and Harvard Medical SchoolProgram for Computational and Systems Biology, Memorial Sloan Kettering Cancer CenterChanning Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital and Harvard Medical SchoolAbstract GEnome-scale Metabolic models (GEMs) are powerful tools to predict cellular metabolism and physiological states in living organisms. However, due to our imperfect knowledge of metabolic processes, even highly curated GEMs have knowledge gaps (e.g., missing reactions). Existing gap-filling methods typically require phenotypic data as input to tease out missing reactions. We still lack a computational method for rapid and accurate gap-filling of metabolic networks before experimental data is available. Here we present a deep learning-based method — CHEbyshev Spectral HyperlInk pREdictor (CHESHIRE) — to predict missing reactions in GEMs purely from metabolic network topology. We demonstrate that CHESHIRE outperforms other topology-based methods in predicting artificially removed reactions over 926 high- and intermediate-quality GEMs. Furthermore, CHESHIRE is able to improve the phenotypic predictions of 49 draft GEMs for fermentation products and amino acids secretions. Both types of validation suggest that CHESHIRE is a powerful tool for GEM curation to reveal unknown links between reactions and observed metabolic phenotypes.https://doi.org/10.1038/s41467-023-38110-7 |
| spellingShingle | Can Chen Chen Liao Yang-Yu Liu Teasing out missing reactions in genome-scale metabolic networks through hypergraph learning Nature Communications |
| title | Teasing out missing reactions in genome-scale metabolic networks through hypergraph learning |
| title_full | Teasing out missing reactions in genome-scale metabolic networks through hypergraph learning |
| title_fullStr | Teasing out missing reactions in genome-scale metabolic networks through hypergraph learning |
| title_full_unstemmed | Teasing out missing reactions in genome-scale metabolic networks through hypergraph learning |
| title_short | Teasing out missing reactions in genome-scale metabolic networks through hypergraph learning |
| title_sort | teasing out missing reactions in genome scale metabolic networks through hypergraph learning |
| url | https://doi.org/10.1038/s41467-023-38110-7 |
| work_keys_str_mv | AT canchen teasingoutmissingreactionsingenomescalemetabolicnetworksthroughhypergraphlearning AT chenliao teasingoutmissingreactionsingenomescalemetabolicnetworksthroughhypergraphlearning AT yangyuliu teasingoutmissingreactionsingenomescalemetabolicnetworksthroughhypergraphlearning |