Predicting antimicrobial mechanism-of-action from transcriptomes: A generalizable explainable artificial intelligence approach.
To better combat the expansion of antibiotic resistance in pathogens, new compounds, particularly those with novel mechanisms-of-action [MOA], represent a major research priority in biomedical science. However, rediscovery of known antibiotics demonstrates a need for approaches that accurately ident...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2021-03-01
|
| Series: | PLoS Computational Biology |
| Online Access: | https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1008857&type=printable |
| _version_ | 1826554801579622400 |
|---|---|
| author | Josh L Espinoza Chris L Dupont Aubrie O'Rourke Sinem Beyhan Pavel Morales Amy Spoering Kirsten J Meyer Agnes P Chan Yongwook Choi William C Nierman Kim Lewis Karen E Nelson |
| author_facet | Josh L Espinoza Chris L Dupont Aubrie O'Rourke Sinem Beyhan Pavel Morales Amy Spoering Kirsten J Meyer Agnes P Chan Yongwook Choi William C Nierman Kim Lewis Karen E Nelson |
| author_sort | Josh L Espinoza |
| collection | DOAJ |
| description | To better combat the expansion of antibiotic resistance in pathogens, new compounds, particularly those with novel mechanisms-of-action [MOA], represent a major research priority in biomedical science. However, rediscovery of known antibiotics demonstrates a need for approaches that accurately identify potential novelty with higher throughput and reduced labor. Here we describe an explainable artificial intelligence classification methodology that emphasizes prediction performance and human interpretability by using a Hierarchical Ensemble of Classifiers model optimized with a novel feature selection algorithm called Clairvoyance; collectively referred to as a CoHEC model. We evaluated our methods using whole transcriptome responses from Escherichia coli challenged with 41 known antibiotics and 9 crude extracts while depositing 122 transcriptomes unique to this study. Our CoHEC model can properly predict the primary MOA of previously unobserved compounds in both purified forms and crude extracts at an accuracy above 99%, while also correctly identifying darobactin, a newly discovered antibiotic, as having a novel MOA. In addition, we deploy our methods on a recent E. coli transcriptomics dataset from a different strain and a Mycobacterium smegmatis metabolomics timeseries dataset showcasing exceptionally high performance; improving upon the performance metrics of the original publications. We not only provide insight into the biological interpretation of our model but also that the concept of MOA is a non-discrete heuristic with diverse effects for different compounds within the same MOA, suggesting substantial antibiotic diversity awaiting discovery within existing MOA. |
| first_indexed | 2024-12-20T10:31:15Z |
| format | Article |
| id | doaj.art-377ccb11394b4b25b621ebb209e3a5d9 |
| institution | Directory Open Access Journal |
| issn | 1553-734X 1553-7358 |
| language | English |
| last_indexed | 2025-03-14T07:46:41Z |
| publishDate | 2021-03-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Computational Biology |
| spelling | doaj.art-377ccb11394b4b25b621ebb209e3a5d92025-03-03T05:31:33ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582021-03-01173e100885710.1371/journal.pcbi.1008857Predicting antimicrobial mechanism-of-action from transcriptomes: A generalizable explainable artificial intelligence approach.Josh L EspinozaChris L DupontAubrie O'RourkeSinem BeyhanPavel MoralesAmy SpoeringKirsten J MeyerAgnes P ChanYongwook ChoiWilliam C NiermanKim LewisKaren E NelsonTo better combat the expansion of antibiotic resistance in pathogens, new compounds, particularly those with novel mechanisms-of-action [MOA], represent a major research priority in biomedical science. However, rediscovery of known antibiotics demonstrates a need for approaches that accurately identify potential novelty with higher throughput and reduced labor. Here we describe an explainable artificial intelligence classification methodology that emphasizes prediction performance and human interpretability by using a Hierarchical Ensemble of Classifiers model optimized with a novel feature selection algorithm called Clairvoyance; collectively referred to as a CoHEC model. We evaluated our methods using whole transcriptome responses from Escherichia coli challenged with 41 known antibiotics and 9 crude extracts while depositing 122 transcriptomes unique to this study. Our CoHEC model can properly predict the primary MOA of previously unobserved compounds in both purified forms and crude extracts at an accuracy above 99%, while also correctly identifying darobactin, a newly discovered antibiotic, as having a novel MOA. In addition, we deploy our methods on a recent E. coli transcriptomics dataset from a different strain and a Mycobacterium smegmatis metabolomics timeseries dataset showcasing exceptionally high performance; improving upon the performance metrics of the original publications. We not only provide insight into the biological interpretation of our model but also that the concept of MOA is a non-discrete heuristic with diverse effects for different compounds within the same MOA, suggesting substantial antibiotic diversity awaiting discovery within existing MOA.https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1008857&type=printable |
| spellingShingle | Josh L Espinoza Chris L Dupont Aubrie O'Rourke Sinem Beyhan Pavel Morales Amy Spoering Kirsten J Meyer Agnes P Chan Yongwook Choi William C Nierman Kim Lewis Karen E Nelson Predicting antimicrobial mechanism-of-action from transcriptomes: A generalizable explainable artificial intelligence approach. PLoS Computational Biology |
| title | Predicting antimicrobial mechanism-of-action from transcriptomes: A generalizable explainable artificial intelligence approach. |
| title_full | Predicting antimicrobial mechanism-of-action from transcriptomes: A generalizable explainable artificial intelligence approach. |
| title_fullStr | Predicting antimicrobial mechanism-of-action from transcriptomes: A generalizable explainable artificial intelligence approach. |
| title_full_unstemmed | Predicting antimicrobial mechanism-of-action from transcriptomes: A generalizable explainable artificial intelligence approach. |
| title_short | Predicting antimicrobial mechanism-of-action from transcriptomes: A generalizable explainable artificial intelligence approach. |
| title_sort | predicting antimicrobial mechanism of action from transcriptomes a generalizable explainable artificial intelligence approach |
| url | https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1008857&type=printable |
| work_keys_str_mv | AT joshlespinoza predictingantimicrobialmechanismofactionfromtranscriptomesageneralizableexplainableartificialintelligenceapproach AT chrisldupont predictingantimicrobialmechanismofactionfromtranscriptomesageneralizableexplainableartificialintelligenceapproach AT aubrieorourke predictingantimicrobialmechanismofactionfromtranscriptomesageneralizableexplainableartificialintelligenceapproach AT sinembeyhan predictingantimicrobialmechanismofactionfromtranscriptomesageneralizableexplainableartificialintelligenceapproach AT pavelmorales predictingantimicrobialmechanismofactionfromtranscriptomesageneralizableexplainableartificialintelligenceapproach AT amyspoering predictingantimicrobialmechanismofactionfromtranscriptomesageneralizableexplainableartificialintelligenceapproach AT kirstenjmeyer predictingantimicrobialmechanismofactionfromtranscriptomesageneralizableexplainableartificialintelligenceapproach AT agnespchan predictingantimicrobialmechanismofactionfromtranscriptomesageneralizableexplainableartificialintelligenceapproach AT yongwookchoi predictingantimicrobialmechanismofactionfromtranscriptomesageneralizableexplainableartificialintelligenceapproach AT williamcnierman predictingantimicrobialmechanismofactionfromtranscriptomesageneralizableexplainableartificialintelligenceapproach AT kimlewis predictingantimicrobialmechanismofactionfromtranscriptomesageneralizableexplainableartificialintelligenceapproach AT karenenelson predictingantimicrobialmechanismofactionfromtranscriptomesageneralizableexplainableartificialintelligenceapproach |