1
|
Jia X, Wang T, Zhu H. Advancing Computational Toxicology by Interpretable Machine Learning. ENVIRONMENTAL SCIENCE & TECHNOLOGY 2023; 57:17690-17706. [PMID: 37224004 PMCID: PMC10666545 DOI: 10.1021/acs.est.3c00653] [Citation(s) in RCA: 10] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/25/2023] [Revised: 05/05/2023] [Accepted: 05/05/2023] [Indexed: 05/26/2023]
Abstract
Chemical toxicity evaluations for drugs, consumer products, and environmental chemicals have a critical impact on human health. Traditional animal models to evaluate chemical toxicity are expensive, time-consuming, and often fail to detect toxicants in humans. Computational toxicology is a promising alternative approach that utilizes machine learning (ML) and deep learning (DL) techniques to predict the toxicity potentials of chemicals. Although the applications of ML- and DL-based computational models in chemical toxicity predictions are attractive, many toxicity models are "black boxes" in nature and difficult to interpret by toxicologists, which hampers the chemical risk assessments using these models. The recent progress of interpretable ML (IML) in the computer science field meets this urgent need to unveil the underlying toxicity mechanisms and elucidate the domain knowledge of toxicity models. In this review, we focused on the applications of IML in computational toxicology, including toxicity feature data, model interpretation methods, use of knowledge base frameworks in IML development, and recent applications. The challenges and future directions of IML modeling in toxicology are also discussed. We hope this review can encourage efforts in developing interpretable models with new IML algorithms that can assist new chemical assessments by illustrating toxicity mechanisms in humans.
Collapse
Affiliation(s)
- Xuelian Jia
- Department
of Chemistry and Biochemistry, Rowan University, Glassboro, New Jersey 08028, United States
| | - Tong Wang
- Department
of Chemistry and Biochemistry, Rowan University, Glassboro, New Jersey 08028, United States
| | - Hao Zhu
- Department
of Chemistry and Biochemistry, Rowan University, Glassboro, New Jersey 08028, United States
| |
Collapse
|
2
|
Zangene E, Marashi SA, Montazeri H. SL-scan identifies synthetic lethal interactions in cancer using metabolic networks. Sci Rep 2023; 13:15763. [PMID: 37737478 PMCID: PMC10516981 DOI: 10.1038/s41598-023-42992-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2023] [Accepted: 09/18/2023] [Indexed: 09/23/2023] Open
Abstract
Exploiting synthetic lethality is a promising strategy for developing targeted cancer therapies. However, identifying clinically significant synthetic lethal (SL) interactions among a large number of gene combinations is a challenging computational task. In this study, we developed the SL-scan pipeline based on metabolic network modeling to discover SL interaction. The SL-scan pipeline identifies the association between simulated Flux Balance Analysis knockout scores and mutation data across cancer cell lines and predicts putative SL interactions. We assessed the concordance of the SL pairs predicted by SL-scan with those of obtained from analysis of the CRISPR, shRNA, and PRISM datasets. Our results demonstrate that the SL-scan pipeline outperformed existing SL prediction approaches based on metabolic networks in identifying SL pairs in various cancers. This study emphasizes the importance of integrating multiple data sources, particularly mutation data, when identifying SL pairs for targeted cancer therapies. The findings of this study may lead to the development of novel targeted cancer therapies.
Collapse
Affiliation(s)
- Ehsan Zangene
- Department of Bioinformatics, Institute of Biochemistry and Biophysics, University of Tehran, Tehran, Iran
| | - Sayed-Amir Marashi
- Department of Biotechnology, College of Science, University of Tehran, Tehran, Iran.
| | - Hesam Montazeri
- Department of Bioinformatics, Institute of Biochemistry and Biophysics, University of Tehran, Tehran, Iran.
| |
Collapse
|
3
|
Hao Y, Romano JD, Moore JH. Knowledge graph aids comprehensive explanation of drug and chemical toxicity. CPT Pharmacometrics Syst Pharmacol 2023; 12:1072-1079. [PMID: 37475158 PMCID: PMC10431039 DOI: 10.1002/psp4.12975] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/11/2023] [Revised: 04/04/2023] [Accepted: 04/06/2023] [Indexed: 07/22/2023] Open
Abstract
In computational toxicology, prediction of complex endpoints has always been challenging, as they often involve multiple distinct mechanisms. State-of-the-art models are either limited by low accuracy, or lack of interpretability due to their black-box nature. Here, we introduce AIDTox, an interpretable deep learning model which incorporates curated knowledge of chemical-gene connections, gene-pathway annotations, and pathway hierarchy. AIDTox accurately predicts cytotoxicity outcomes in HepG2 and HEK293 cells. It also provides comprehensive explanations of cytotoxicity covering multiple aspects of drug activity, including target interaction, metabolism, and elimination. In summary, AIDTox provides a computational framework for unveiling cellular mechanisms for complex toxicity endpoints.
Collapse
Affiliation(s)
- Yun Hao
- Genomics and Computational Biology (GCB) Graduate ProgramUniversity of PennsylvaniaPhiladelphiaPennsylvaniaUSA
| | - Joseph D. Romano
- Institute for Biomedical InformaticsUniversity of PennsylvaniaPhiladelphiaPennsylvaniaUSA
- Center of Excellence in Environmental ToxicologyUniversity of PennsylvaniaPhiladelphiaPennsylvaniaUSA
| | - Jason H. Moore
- Department of Computational BiomedicineCedars‐Sinai Medical CenterLos AngelesCaliforniaUSA
| |
Collapse
|
4
|
Weiskittel TM, Cao A, Meng-Lin K, Lehmann Z, Feng B, Correia C, Zhang C, Wisniewski P, Zhu S, Yong Ung C, Li H. Network Biology-Inspired Machine Learning Features Predict Cancer Gene Targets and Reveal Target Coordinating Mechanisms. Pharmaceuticals (Basel) 2023; 16:752. [PMID: 37242535 PMCID: PMC10223789 DOI: 10.3390/ph16050752] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2023] [Revised: 05/08/2023] [Accepted: 05/11/2023] [Indexed: 05/28/2023] Open
Abstract
Anticipating and understanding cancers' need for specific gene activities is key for novel therapeutic development. Here we utilized DepMap, a cancer gene dependency screen, to demonstrate that machine learning combined with network biology can produce robust algorithms that both predict what genes a cancer is dependent on and what network features coordinate such gene dependencies. Using network topology and biological annotations, we constructed four groups of novel engineered machine learning features that produced high accuracies when predicting binary gene dependencies. We found that in all examined cancer types, F1 scores were greater than 0.90, and model accuracy remained robust under multiple hyperparameter tests. We then deconstructed these models to identify tumor type-specific coordinators of gene dependency and identified that in certain cancers, such as thyroid and kidney, tumors' dependencies are highly predicted by gene connectivity. In contrast, other histologies relied on pathway-based features such as lung, where gene dependencies were highly predictive by associations with cell death pathway genes. In sum, we show that biologically informed network features can be a valuable and robust addition to predictive pharmacology models while simultaneously providing mechanistic insights.
Collapse
Affiliation(s)
- Taylor M. Weiskittel
- Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA; (T.M.W.)
- Mayo Clinic Alix School of Medicine, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA
| | - Andrew Cao
- Department of Computer Science, Duke University, Durham, NC 27708, USA
| | - Kevin Meng-Lin
- Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA; (T.M.W.)
| | - Zachary Lehmann
- Department of Chemistry, Biochemistry and Physics, South Dakota State University, Brookings, SD 57006, USA
| | - Benjamin Feng
- Department of Molecular Cell and Developmental Biology, University of California, Los Angeles, CA 90095, USA
| | - Cristina Correia
- Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA; (T.M.W.)
| | - Cheng Zhang
- Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA; (T.M.W.)
| | - Philip Wisniewski
- Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA; (T.M.W.)
| | - Shizhen Zhu
- Department of Biochemistry and Molecular Biology, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA
| | - Choong Yong Ung
- Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA; (T.M.W.)
| | - Hu Li
- Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA; (T.M.W.)
| |
Collapse
|
5
|
Gervits A, Sharan R. Predicting genetic interactions, cell line dependencies and drug sensitivities with variational graph auto-encoder. FRONTIERS IN BIOINFORMATICS 2022; 2:1025783. [DOI: 10.3389/fbinf.2022.1025783] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2022] [Accepted: 11/21/2022] [Indexed: 12/03/2022] Open
Abstract
Large scale cancer genomics data provide crucial information about the disease and reveal points of intervention. However, systematic data have been collected in specific cell lines and their collection is laborious and costly. Hence, there is a need to develop computational models that can predict such data for any genomic context of interest. Here we develop novel models that build on variational graph auto-encoders and can integrate diverse types of data to provide high quality predictions of genetic interactions, cell line dependencies and drug sensitivities, outperforming previous methods. Our models, data and implementation are available at: https://github.com/aijag/drugGraphNet.
Collapse
|
6
|
Samal BR, Loers JU, Vermeirssen V, De Preter K. Opportunities and challenges in interpretable deep learning for drug sensitivity prediction of cancer cells. FRONTIERS IN BIOINFORMATICS 2022; 2:1036963. [PMID: 36466148 PMCID: PMC9714662 DOI: 10.3389/fbinf.2022.1036963] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2022] [Accepted: 11/03/2022] [Indexed: 01/02/2024] Open
Abstract
In precision oncology, therapy stratification is done based on the patients' tumor molecular profile. Modeling and prediction of the drug response for a given tumor molecular type will further improve therapeutic decision-making for cancer patients. Indeed, deep learning methods hold great potential for drug sensitivity prediction, but a major problem is that these models are black box algorithms and do not clarify the mechanisms of action. This puts a limitation on their clinical implementation. To address this concern, many recent studies attempt to overcome these issues by developing interpretable deep learning methods that facilitate the understanding of the logic behind the drug response prediction. In this review, we discuss strengths and limitations of recent approaches, and suggest future directions that could guide further improvement of interpretable deep learning in drug sensitivity prediction in cancer research.
Collapse
Affiliation(s)
- Bikash Ranjan Samal
- Department of Biomolecular Medicine, Ghent University, Ghent, Belgium
- Center for Medical Genetics Ghent (CMGG), Ghent University, Ghent, Belgium
- Cancer Research Institute Ghent (CRIG), Ghent, Belgium
| | - Jens Uwe Loers
- Department of Biomolecular Medicine, Ghent University, Ghent, Belgium
- Center for Medical Genetics Ghent (CMGG), Ghent University, Ghent, Belgium
- Cancer Research Institute Ghent (CRIG), Ghent, Belgium
- Department of Biomedical Molecular Biology, Ghent University, Ghent, Belgium
| | - Vanessa Vermeirssen
- Department of Biomolecular Medicine, Ghent University, Ghent, Belgium
- Center for Medical Genetics Ghent (CMGG), Ghent University, Ghent, Belgium
- Cancer Research Institute Ghent (CRIG), Ghent, Belgium
- Department of Biomedical Molecular Biology, Ghent University, Ghent, Belgium
| | - Katleen De Preter
- Department of Biomolecular Medicine, Ghent University, Ghent, Belgium
- Center for Medical Genetics Ghent (CMGG), Ghent University, Ghent, Belgium
- Cancer Research Institute Ghent (CRIG), Ghent, Belgium
| |
Collapse
|
7
|
Hao Y, Romano JD, Moore JH. Knowledge-guided deep learning models of drug toxicity improve interpretation. PATTERNS (NEW YORK, N.Y.) 2022; 3:100565. [PMID: 36124309 PMCID: PMC9481960 DOI: 10.1016/j.patter.2022.100565] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/11/2022] [Revised: 05/16/2022] [Accepted: 07/12/2022] [Indexed: 12/04/2022]
Abstract
In drug development, a major reason for attrition is the lack of understanding of cellular mechanisms governing drug toxicity. The black-box nature of conventional classification models has limited their utility in identifying toxicity pathways. Here we developed DTox (deep learning for toxicology), an interpretation framework for knowledge-guided neural networks, which can predict compound response to toxicity assays and infer toxicity pathways of individual compounds. We demonstrate that DTox can achieve the same level of predictive performance as conventional models with a significant improvement in interpretability. Using DTox, we were able to rediscover mechanisms of transcription activation by three nuclear receptors, recapitulate cellular activities induced by aromatase inhibitors and pregnane X receptor (PXR) agonists, and differentiate distinctive mechanisms leading to HepG2 cytotoxicity. Virtual screening by DTox revealed that compounds with predicted cytotoxicity are at higher risk for clinical hepatic phenotypes. In summary, DTox provides a framework for deciphering cellular mechanisms of toxicity in silico.
Collapse
Affiliation(s)
- Yun Hao
- Genomics and Computational Biology (GCB) Graduate Program, University of Pennsylvania, Philadelphia, PA, USA
| | - Joseph D. Romano
- Institute for Biomedical Informatics, University of Pennsylvania, Philadelphia, PA, USA
- Center of Excellence in Environmental Toxicology, University of Pennsylvania, Philadelphia, PA, USA
| | - Jason H. Moore
- Department of Computational Biomedicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA
| |
Collapse
|