Ignition of Small Molecule Inhibitors in Friedreich's Ataxia with Explainable Artificial Intelligence
Iron (Fe) chelating medicines and Histone deacetylase (HDAC) inhibitors are two therapy options for hereditary Friedreich's Ataxia that have been shown to improve clinical results (FA). Fe chelation molecules can minimize the quantity of stored Fe, and HDAC inhibitors can boost the expression o...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EduSoft publishing
2023-10-01
|
| Series: | Brain: Broad Research in Artificial Intelligence and Neuroscience |
| Subjects: | |
| Online Access: | https://www.edusoft.ro/brain/index.php/brain/article/view/1427 |
| _version_ | 1797335679160549376 |
|---|---|
| author | Kevser Kübra Kirboğa Ecir Uğur Küçüksille Utku Kose |
| author_facet | Kevser Kübra Kirboğa Ecir Uğur Küçüksille Utku Kose |
| author_sort | Kevser Kübra Kirboğa |
| collection | DOAJ |
| description | Iron (Fe) chelating medicines and Histone deacetylase (HDAC) inhibitors are two therapy options for hereditary Friedreich's Ataxia that have been shown to improve clinical results (FA). Fe chelation molecules can minimize the quantity of stored Fe, and HDAC inhibitors can boost the expression of the Frataxin (FXN) gene in enhancing FA. A complete quantitative structure-activity relationship (QSAR) search of inhibitors from the ChEMBL database is reported in this paper, which includes 437 compounds for Fe chelation and 1,354 compounds for HDAC inhibitors. For further investigation, the IC50 was chosen as the unit of bioactivity, and following data refinement, a final dataset of 436 and 1,163 compounds for Fe chelation and HDAC inhibition, respectively, was produced. The Random Forest (RF) technique was used to generate models (train R2 score, 0.701 and 0.892; test R2 score 0.572 and 0.460, for Fe and HDAC, respectively). The models created using the PubChem fingerprint were the strongest of the 12 fingerprint kinds; hence that feature was chosen for interpretation. The results showed the importance of properties related to nitrogen-containing functional groups (SHAP value of PubchemFP656 is -0.29) and aromatic rings (SHAP value of PubchemFP12 is -0.16). As a result, we explained the effect of the molecular fingerprints on the models and the impact on possible drugs that can be developed for FA with artificial intelligence (XAI), which can be explained through SHAP (Shapley Additive Explanations) values. Model scripts and fingerprinting methods are also available at https://github.com/tissueandcells/XAI. |
| first_indexed | 2024-03-08T08:41:50Z |
| format | Article |
| id | doaj.art-e58b864259f54e91905fe29fbe7a9b76 |
| institution | Directory Open Access Journal |
| issn | 2067-3957 |
| language | English |
| last_indexed | 2024-03-08T08:41:50Z |
| publishDate | 2023-10-01 |
| publisher | EduSoft publishing |
| record_format | Article |
| series | Brain: Broad Research in Artificial Intelligence and Neuroscience |
| spelling | doaj.art-e58b864259f54e91905fe29fbe7a9b762024-02-01T18:00:44ZengEduSoft publishingBrain: Broad Research in Artificial Intelligence and Neuroscience2067-39572023-10-011432873131230Ignition of Small Molecule Inhibitors in Friedreich's Ataxia with Explainable Artificial IntelligenceKevser Kübra Kirboğa0Ecir Uğur Küçüksille1Utku Kose2PhD student at the Department of Computational Science and Engineering at Istanbul Technical University, BilecikSeyhEdebali University, Department of Bioengineering, Bilecik, Turkey, ORCID ID:0000-0002-2917-8860Suleyman Demirel University, EngineeringFaculty, ComputerEngineeringDepartment, 32260,Isparta, Turkey, ORCID ID:0000-0002-3293-9878Suleyman Demirel University, Turkey, University of North Dakota, USA, ORCID ID: https://orcid.org/0000-0002-9652-6415 , utkukose@gmail.com, utkukose@sdu.edu.tr, utku.kose@und.eduIron (Fe) chelating medicines and Histone deacetylase (HDAC) inhibitors are two therapy options for hereditary Friedreich's Ataxia that have been shown to improve clinical results (FA). Fe chelation molecules can minimize the quantity of stored Fe, and HDAC inhibitors can boost the expression of the Frataxin (FXN) gene in enhancing FA. A complete quantitative structure-activity relationship (QSAR) search of inhibitors from the ChEMBL database is reported in this paper, which includes 437 compounds for Fe chelation and 1,354 compounds for HDAC inhibitors. For further investigation, the IC50 was chosen as the unit of bioactivity, and following data refinement, a final dataset of 436 and 1,163 compounds for Fe chelation and HDAC inhibition, respectively, was produced. The Random Forest (RF) technique was used to generate models (train R2 score, 0.701 and 0.892; test R2 score 0.572 and 0.460, for Fe and HDAC, respectively). The models created using the PubChem fingerprint were the strongest of the 12 fingerprint kinds; hence that feature was chosen for interpretation. The results showed the importance of properties related to nitrogen-containing functional groups (SHAP value of PubchemFP656 is -0.29) and aromatic rings (SHAP value of PubchemFP12 is -0.16). As a result, we explained the effect of the molecular fingerprints on the models and the impact on possible drugs that can be developed for FA with artificial intelligence (XAI), which can be explained through SHAP (Shapley Additive Explanations) values. Model scripts and fingerprinting methods are also available at https://github.com/tissueandcells/XAI.https://www.edusoft.ro/brain/index.php/brain/article/view/1427explainable artificial intelligence, friedreich ataxia, predictive accuracy, quantitative structure-activity relationship, qsar, shapley values. |
| spellingShingle | Kevser Kübra Kirboğa Ecir Uğur Küçüksille Utku Kose Ignition of Small Molecule Inhibitors in Friedreich's Ataxia with Explainable Artificial Intelligence Brain: Broad Research in Artificial Intelligence and Neuroscience explainable artificial intelligence, friedreich ataxia, predictive accuracy, quantitative structure-activity relationship, qsar, shapley values. |
| title | Ignition of Small Molecule Inhibitors in Friedreich's Ataxia with Explainable Artificial Intelligence |
| title_full | Ignition of Small Molecule Inhibitors in Friedreich's Ataxia with Explainable Artificial Intelligence |
| title_fullStr | Ignition of Small Molecule Inhibitors in Friedreich's Ataxia with Explainable Artificial Intelligence |
| title_full_unstemmed | Ignition of Small Molecule Inhibitors in Friedreich's Ataxia with Explainable Artificial Intelligence |
| title_short | Ignition of Small Molecule Inhibitors in Friedreich's Ataxia with Explainable Artificial Intelligence |
| title_sort | ignition of small molecule inhibitors in friedreich s ataxia with explainable artificial intelligence |
| topic | explainable artificial intelligence, friedreich ataxia, predictive accuracy, quantitative structure-activity relationship, qsar, shapley values. |
| url | https://www.edusoft.ro/brain/index.php/brain/article/view/1427 |
| work_keys_str_mv | AT kevserkubrakirboga ignitionofsmallmoleculeinhibitorsinfriedreichsataxiawithexplainableartificialintelligence AT ecirugurkucuksille ignitionofsmallmoleculeinhibitorsinfriedreichsataxiawithexplainableartificialintelligence AT utkukose ignitionofsmallmoleculeinhibitorsinfriedreichsataxiawithexplainableartificialintelligence |