Explaining Accurate Predictions of Multitarget Compounds with Machine Learning Models Derived for Individual Targets
In drug discovery, compounds with well-defined activity against multiple targets (multitarget compounds, MT-CPDs) provide the basis for polypharmacology and are thus of high interest. Typically, MT-CPDs for polypharmacology have been discovered serendipitously. Therefore, over the past decade, compu...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Molecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1420-3049/28/2/825 |
| _version_ | 1797438256133963776 |
|---|---|
| author | Alec Lamens Jürgen Bajorath |
| author_facet | Alec Lamens Jürgen Bajorath |
| author_sort | Alec Lamens |
| collection | DOAJ |
| description | In drug discovery, compounds with well-defined activity against multiple targets (multitarget compounds, MT-CPDs) provide the basis for polypharmacology and are thus of high interest. Typically, MT-CPDs for polypharmacology have been discovered serendipitously. Therefore, over the past decade, computational approaches have also been adapted for the design of MT-CPDs or their identification via computational screening. Such approaches continue to be under development and are far from being routine. Recently, different machine learning (ML) models have been derived to distinguish between MT-CPDs and corresponding compounds with activity against the individual targets (single-target compounds, ST-CPDs). When evaluating alternative models for predicting MT-CPDs, we discovered that MT-CPDs could also be accurately predicted with models derived for corresponding ST-CPDs; this was an unexpected finding that we further investigated using explainable ML. The analysis revealed that accurate predictions of ST-CPDs were determined by subsets of structural features of MT-CPDs required for their prediction. These findings provided a chemically intuitive rationale for the successful prediction of MT-CPDs using different ML models and uncovered general-feature subset relationships between MT- and ST-CPDs with activities against different targets. |
| first_indexed | 2024-03-09T11:35:02Z |
| format | Article |
| id | doaj.art-7f561d82bdb54a769d5e7730c7649b2b |
| institution | Directory Open Access Journal |
| issn | 1420-3049 |
| language | English |
| last_indexed | 2024-03-09T11:35:02Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Molecules |
| spelling | doaj.art-7f561d82bdb54a769d5e7730c7649b2b2023-11-30T23:45:28ZengMDPI AGMolecules1420-30492023-01-0128282510.3390/molecules28020825Explaining Accurate Predictions of Multitarget Compounds with Machine Learning Models Derived for Individual TargetsAlec Lamens0Jürgen Bajorath1Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universität, Friedrich-Hirzebruch-Allee 5/6, D-53115 Bonn, GermanyDepartment of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universität, Friedrich-Hirzebruch-Allee 5/6, D-53115 Bonn, GermanyIn drug discovery, compounds with well-defined activity against multiple targets (multitarget compounds, MT-CPDs) provide the basis for polypharmacology and are thus of high interest. Typically, MT-CPDs for polypharmacology have been discovered serendipitously. Therefore, over the past decade, computational approaches have also been adapted for the design of MT-CPDs or their identification via computational screening. Such approaches continue to be under development and are far from being routine. Recently, different machine learning (ML) models have been derived to distinguish between MT-CPDs and corresponding compounds with activity against the individual targets (single-target compounds, ST-CPDs). When evaluating alternative models for predicting MT-CPDs, we discovered that MT-CPDs could also be accurately predicted with models derived for corresponding ST-CPDs; this was an unexpected finding that we further investigated using explainable ML. The analysis revealed that accurate predictions of ST-CPDs were determined by subsets of structural features of MT-CPDs required for their prediction. These findings provided a chemically intuitive rationale for the successful prediction of MT-CPDs using different ML models and uncovered general-feature subset relationships between MT- and ST-CPDs with activities against different targets.https://www.mdpi.com/1420-3049/28/2/825multitarget compoundssingle-target compoundsmachine learningactivity predictionmodel explanationfeature analysis |
| spellingShingle | Alec Lamens Jürgen Bajorath Explaining Accurate Predictions of Multitarget Compounds with Machine Learning Models Derived for Individual Targets Molecules multitarget compounds single-target compounds machine learning activity prediction model explanation feature analysis |
| title | Explaining Accurate Predictions of Multitarget Compounds with Machine Learning Models Derived for Individual Targets |
| title_full | Explaining Accurate Predictions of Multitarget Compounds with Machine Learning Models Derived for Individual Targets |
| title_fullStr | Explaining Accurate Predictions of Multitarget Compounds with Machine Learning Models Derived for Individual Targets |
| title_full_unstemmed | Explaining Accurate Predictions of Multitarget Compounds with Machine Learning Models Derived for Individual Targets |
| title_short | Explaining Accurate Predictions of Multitarget Compounds with Machine Learning Models Derived for Individual Targets |
| title_sort | explaining accurate predictions of multitarget compounds with machine learning models derived for individual targets |
| topic | multitarget compounds single-target compounds machine learning activity prediction model explanation feature analysis |
| url | https://www.mdpi.com/1420-3049/28/2/825 |
| work_keys_str_mv | AT aleclamens explainingaccuratepredictionsofmultitargetcompoundswithmachinelearningmodelsderivedforindividualtargets AT jurgenbajorath explainingaccuratepredictionsofmultitargetcompoundswithmachinelearningmodelsderivedforindividualtargets |