Predicting the Pathway Involvement of All Pathway and Associated Compound Entries Defined in the Kyoto Encyclopedia of Genes and Genomes
<b>Background/Objectives</b>: Predicting the biochemical pathway involvement of a compound could facilitate the interpretation of biological and biomedical research. Prior prediction approaches have largely focused on metabolism, training machine learning models to solely predict based o...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | Metabolites |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-1989/14/11/582 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846153043098206208 |
|---|---|
| author | Erik D. Huckvale Hunter N. B. Moseley |
| author_facet | Erik D. Huckvale Hunter N. B. Moseley |
| author_sort | Erik D. Huckvale |
| collection | DOAJ |
| description | <b>Background/Objectives</b>: Predicting the biochemical pathway involvement of a compound could facilitate the interpretation of biological and biomedical research. Prior prediction approaches have largely focused on metabolism, training machine learning models to solely predict based on metabolic pathways. However, there are many other types of pathways in cells and organisms that are of interest to biologists. <b>Methods</b>: While several publications have made use of the metabolites and metabolic pathways available in the Kyoto Encyclopedia of Genes and Genomes (KEGG), we downloaded all the compound entries with pathway annotations available in the KEGG. From these data, we constructed a dataset where each entry contained features representing compounds combined with features representing pathways, followed by a binary label indicating whether the given compound is associated with the given pathway. We trained multi-layer perceptron binary classifiers on variations of this dataset. <b>Results</b>: The models trained on 6485 KEGG compounds and 502 pathways scored an overall mean Matthews correlation coefficient (MCC) performance of 0.847, a median MCC of 0.848, and a standard deviation of 0.0098. <b>Conclusions</b>: This performance on all 502 KEGG pathways represents a roughly 6% improvement over the performance of models trained on only the 184 KEGG metabolic pathways, which had a mean MCC of 0.800 and a standard deviation of 0.021. These results demonstrate the capability to effectively predict biochemical pathways in general, in addition to those specifically related to metabolism. Moreover, the improvement in the performance demonstrates additional transfer learning with the inclusion of non-metabolic pathways. |
| format | Article |
| id | doaj-art-f4b152c4f2b143d19f150fbdc8f10c3b |
| institution | Kabale University |
| issn | 2218-1989 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Metabolites |
| spelling | doaj-art-f4b152c4f2b143d19f150fbdc8f10c3b2024-11-26T18:13:03ZengMDPI AGMetabolites2218-19892024-10-01141158210.3390/metabo14110582Predicting the Pathway Involvement of All Pathway and Associated Compound Entries Defined in the Kyoto Encyclopedia of Genes and GenomesErik D. Huckvale0Hunter N. B. Moseley1Markey Cancer Center, University of Kentucky, Lexington, KY 40536, USAMarkey Cancer Center, University of Kentucky, Lexington, KY 40536, USA<b>Background/Objectives</b>: Predicting the biochemical pathway involvement of a compound could facilitate the interpretation of biological and biomedical research. Prior prediction approaches have largely focused on metabolism, training machine learning models to solely predict based on metabolic pathways. However, there are many other types of pathways in cells and organisms that are of interest to biologists. <b>Methods</b>: While several publications have made use of the metabolites and metabolic pathways available in the Kyoto Encyclopedia of Genes and Genomes (KEGG), we downloaded all the compound entries with pathway annotations available in the KEGG. From these data, we constructed a dataset where each entry contained features representing compounds combined with features representing pathways, followed by a binary label indicating whether the given compound is associated with the given pathway. We trained multi-layer perceptron binary classifiers on variations of this dataset. <b>Results</b>: The models trained on 6485 KEGG compounds and 502 pathways scored an overall mean Matthews correlation coefficient (MCC) performance of 0.847, a median MCC of 0.848, and a standard deviation of 0.0098. <b>Conclusions</b>: This performance on all 502 KEGG pathways represents a roughly 6% improvement over the performance of models trained on only the 184 KEGG metabolic pathways, which had a mean MCC of 0.800 and a standard deviation of 0.021. These results demonstrate the capability to effectively predict biochemical pathways in general, in addition to those specifically related to metabolism. Moreover, the improvement in the performance demonstrates additional transfer learning with the inclusion of non-metabolic pathways.https://www.mdpi.com/2218-1989/14/11/582pathway predictionMatthews correlation coefficientmachine learningmulti-layer perceptrontransfer learningKEGG |
| spellingShingle | Erik D. Huckvale Hunter N. B. Moseley Predicting the Pathway Involvement of All Pathway and Associated Compound Entries Defined in the Kyoto Encyclopedia of Genes and Genomes Metabolites pathway prediction Matthews correlation coefficient machine learning multi-layer perceptron transfer learning KEGG |
| title | Predicting the Pathway Involvement of All Pathway and Associated Compound Entries Defined in the Kyoto Encyclopedia of Genes and Genomes |
| title_full | Predicting the Pathway Involvement of All Pathway and Associated Compound Entries Defined in the Kyoto Encyclopedia of Genes and Genomes |
| title_fullStr | Predicting the Pathway Involvement of All Pathway and Associated Compound Entries Defined in the Kyoto Encyclopedia of Genes and Genomes |
| title_full_unstemmed | Predicting the Pathway Involvement of All Pathway and Associated Compound Entries Defined in the Kyoto Encyclopedia of Genes and Genomes |
| title_short | Predicting the Pathway Involvement of All Pathway and Associated Compound Entries Defined in the Kyoto Encyclopedia of Genes and Genomes |
| title_sort | predicting the pathway involvement of all pathway and associated compound entries defined in the kyoto encyclopedia of genes and genomes |
| topic | pathway prediction Matthews correlation coefficient machine learning multi-layer perceptron transfer learning KEGG |
| url | https://www.mdpi.com/2218-1989/14/11/582 |
| work_keys_str_mv | AT erikdhuckvale predictingthepathwayinvolvementofallpathwayandassociatedcompoundentriesdefinedinthekyotoencyclopediaofgenesandgenomes AT hunternbmoseley predictingthepathwayinvolvementofallpathwayandassociatedcompoundentriesdefinedinthekyotoencyclopediaofgenesandgenomes |