Artificial Intelligence and Machine Learning Methods to Evaluate Cardiotoxicity following the Adverse Outcome Pathway Frameworks
Cardiovascular disease is a leading global cause of mortality. The potential cardiotoxic effects of chemicals from different classes, such as environmental contaminants, pesticides, and drugs can significantly contribute to effects on health. The same chemical can induce cardiotoxicity in different...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Toxics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2305-6304/12/1/87 |
| _version_ | 1797342486415278080 |
|---|---|
| author | Edoardo Luca Viganò Davide Ballabio Alessandra Roncaglioni |
| author_facet | Edoardo Luca Viganò Davide Ballabio Alessandra Roncaglioni |
| author_sort | Edoardo Luca Viganò |
| collection | DOAJ |
| description | Cardiovascular disease is a leading global cause of mortality. The potential cardiotoxic effects of chemicals from different classes, such as environmental contaminants, pesticides, and drugs can significantly contribute to effects on health. The same chemical can induce cardiotoxicity in different ways, following various Adverse Outcome Pathways (AOPs). In addition, the potential synergistic effects between chemicals further complicate the issue. In silico methods have become essential for tackling the problem from different perspectives, reducing the need for traditional in vivo testing, and saving valuable resources in terms of time and money. Artificial intelligence (AI) and machine learning (ML) are among today’s advanced approaches for evaluating chemical hazards. They can serve, for instance, as a first-tier component of Integrated Approaches to Testing and Assessment (IATA). This study employed ML and AI to assess interactions between chemicals and specific biological targets within the AOP networks for cardiotoxicity, starting with molecular initiating events (MIEs) and progressing through key events (KEs). We explored methods to encode chemical information in a suitable way for ML and AI. We started with commonly used approaches in Quantitative Structure–Activity Relationship (QSAR) methods, such as molecular descriptors and different types of fingerprint. We then increased the complexity of encoders, incorporating graph-based methods, auto-encoders, and character embeddings employed in neural language processing. We also developed a multimodal neural network architecture, capable of considering the complementary nature of different chemical representations simultaneously. The potential of this approach, compared to more conventional architectures designed to handle a single encoder, becomes apparent when the amount of data increases. |
| first_indexed | 2024-03-08T10:33:58Z |
| format | Article |
| id | doaj.art-f7c0eea638e3476781b60b26c5f2769e |
| institution | Directory Open Access Journal |
| issn | 2305-6304 |
| language | English |
| last_indexed | 2024-03-08T10:33:58Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Toxics |
| spelling | doaj.art-f7c0eea638e3476781b60b26c5f2769e2024-01-26T18:41:53ZengMDPI AGToxics2305-63042024-01-011218710.3390/toxics12010087Artificial Intelligence and Machine Learning Methods to Evaluate Cardiotoxicity following the Adverse Outcome Pathway FrameworksEdoardo Luca Viganò0Davide Ballabio1Alessandra Roncaglioni2Laboratory of Environmental Toxicology and Chemistry, Department of Environmental Health Sciences, Istituto di Ricerche Farmacologiche Mario Negri IRCSS, 20156 Milan, ItalyMilano Chemometrics and QSAR Research Group, Department of Earth and Environmental Sciences, University of Milano-Bicocca, 20126 Milan, ItalyLaboratory of Environmental Toxicology and Chemistry, Department of Environmental Health Sciences, Istituto di Ricerche Farmacologiche Mario Negri IRCSS, 20156 Milan, ItalyCardiovascular disease is a leading global cause of mortality. The potential cardiotoxic effects of chemicals from different classes, such as environmental contaminants, pesticides, and drugs can significantly contribute to effects on health. The same chemical can induce cardiotoxicity in different ways, following various Adverse Outcome Pathways (AOPs). In addition, the potential synergistic effects between chemicals further complicate the issue. In silico methods have become essential for tackling the problem from different perspectives, reducing the need for traditional in vivo testing, and saving valuable resources in terms of time and money. Artificial intelligence (AI) and machine learning (ML) are among today’s advanced approaches for evaluating chemical hazards. They can serve, for instance, as a first-tier component of Integrated Approaches to Testing and Assessment (IATA). This study employed ML and AI to assess interactions between chemicals and specific biological targets within the AOP networks for cardiotoxicity, starting with molecular initiating events (MIEs) and progressing through key events (KEs). We explored methods to encode chemical information in a suitable way for ML and AI. We started with commonly used approaches in Quantitative Structure–Activity Relationship (QSAR) methods, such as molecular descriptors and different types of fingerprint. We then increased the complexity of encoders, incorporating graph-based methods, auto-encoders, and character embeddings employed in neural language processing. We also developed a multimodal neural network architecture, capable of considering the complementary nature of different chemical representations simultaneously. The potential of this approach, compared to more conventional architectures designed to handle a single encoder, becomes apparent when the amount of data increases.https://www.mdpi.com/2305-6304/12/1/87in silico modelsartificial intelligencemachine learningnew-approach methodologies (NAMs)toxicological endpointsquantitative structure–activity relationship (QSAR) |
| spellingShingle | Edoardo Luca Viganò Davide Ballabio Alessandra Roncaglioni Artificial Intelligence and Machine Learning Methods to Evaluate Cardiotoxicity following the Adverse Outcome Pathway Frameworks Toxics in silico models artificial intelligence machine learning new-approach methodologies (NAMs) toxicological endpoints quantitative structure–activity relationship (QSAR) |
| title | Artificial Intelligence and Machine Learning Methods to Evaluate Cardiotoxicity following the Adverse Outcome Pathway Frameworks |
| title_full | Artificial Intelligence and Machine Learning Methods to Evaluate Cardiotoxicity following the Adverse Outcome Pathway Frameworks |
| title_fullStr | Artificial Intelligence and Machine Learning Methods to Evaluate Cardiotoxicity following the Adverse Outcome Pathway Frameworks |
| title_full_unstemmed | Artificial Intelligence and Machine Learning Methods to Evaluate Cardiotoxicity following the Adverse Outcome Pathway Frameworks |
| title_short | Artificial Intelligence and Machine Learning Methods to Evaluate Cardiotoxicity following the Adverse Outcome Pathway Frameworks |
| title_sort | artificial intelligence and machine learning methods to evaluate cardiotoxicity following the adverse outcome pathway frameworks |
| topic | in silico models artificial intelligence machine learning new-approach methodologies (NAMs) toxicological endpoints quantitative structure–activity relationship (QSAR) |
| url | https://www.mdpi.com/2305-6304/12/1/87 |
| work_keys_str_mv | AT edoardolucavigano artificialintelligenceandmachinelearningmethodstoevaluatecardiotoxicityfollowingtheadverseoutcomepathwayframeworks AT davideballabio artificialintelligenceandmachinelearningmethodstoevaluatecardiotoxicityfollowingtheadverseoutcomepathwayframeworks AT alessandraroncaglioni artificialintelligenceandmachinelearningmethodstoevaluatecardiotoxicityfollowingtheadverseoutcomepathwayframeworks |