Ignition of Small Molecule Inhibitors in Friedreich's Ataxia with Explainable Artificial Intelligence

Authors

  • Kevser Kübra Kırboğa PhD student at the Department of Computational Science and Engineering at Istanbul Technical University, Bilecik Seyh Edebali University, Department of Bioengineering, Bilecik, Turkey
  • Ecir Uğur Küçüksille Suleyman Demirel University, Engineering Faculty, Computer Engineering Department, 32260,Isparta, Turkey,
  • Utku Köse Suleyman Demirel University, Turkey, University of North Dakota, USA

DOI:

https://doi.org/10.18662/brain/14.3/475

Keywords:

Explainable Artificial Intelligence, Friedreich Ataxia, Predictive accuracy, Quantitative structure-activity relationship, Shapley values, QSAR

Abstract

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.

 

Author Biography

Utku Köse, Suleyman Demirel University, Turkey, University of North Dakota, USA

 

 

References

Alper, G. & Narayanan, V. (2003). Friedreich's ataxia. Pediatr Neurol, 28(5), 335-341. https://doi.org/10.1016/s0887-8994(03)00004-3

Aranca, T. V., Jones, T. M., Shaw, J. D., Staffetti, J. S., Ashizawa, T., Kuo, S.-H., Fogel, B. L., Wilmot, G. R., Perlman, S. L., Onyike, C. U., Ying, S. H. & Zesiewicz, T. A. (2016). Emerging therapies in Friedreich's ataxia. Neurodegenerative Disease Management, 6(1), 49-65. https://doi.org/10.2217/nmt.15.73

Bendheim, P. E., Poeggeler, B., Neria, E., Ziv, V., Pappolla, M. A. & Chain, D. G. (2002). Development of indole-3-propionic acid (OXIGON™) for alzheimer's disease. Journal of molecular neuroscience, 19(1), 213-217.

Beutler, E. (2007). Iron storage disease: Facts, fiction and progress. Blood Cells, Molecules, and Diseases, 39(2), 140-147. https://doi.org/10.1016/j.bcmd.2007.03.009

Boddaert, N., Le Quan Sang, K. H., Rötig, A., Leroy-Willig, A., Gallet, S., Brunelle, F., Sidi, D., Thalabard, J.-C., Munnich, A. & Cabantchik, Z. I. (2007). Selective iron chelation in Friedreich ataxia: biologic and clinical implications. Blood, 110(1), 401-408. https://doi.org/10.1182/blood-2006-12-065433

Bulteau, A. L., Dancis, A., Gareil, M., Montagne, J. J., Camadro, J. M. & Lesuisse, E. (2007). Oxidative stress and protease dysfunction in the yeast model of Friedreich ataxia. Free Radic Biol Med, 42(10), 1561-1570. https://doi.org/10.1016/j.freeradbiomed.2007.02.014

Carracedo, P., Blanco, J., Rodriguez-Fernandez, N., Cedrón-Santaeufemia, F., Nóvoa, F., Carballal, A., Maojo, V., Pazos, A. & Fernandez-Lozano, C. (2021). A review on machine learning approaches and trends in drug discovery. Computational and Structural Biotechnology Journal, 19, 4538-4558. https://doi.org/10.1016/j.csbj.2021.08.011

Cherny, R. A., Atwood, C. S., Xilinas, M. E., Gray, D. N., Jones, W. D., Mclean, C. A., Barnham, K. J., Volitakis, I., Fraser, F. W., Kim, Y.-S., Huang, X., Goldstein, L. E., Moir, R. D., Lim, J. T., Beyreuther, K., Zheng, H., Tanzi, R. E., Masters, C. L. & Bush, A. I. (2001). Treatment with a Copper-Zinc chelator markedly and rapidly inhibits β-Amyloid accumulation in Alzheimer's disease transgenic mice. Neuron, 30(3), 665-676. https://doi.org/10.1016/s0896-6273(01)00317-8

Cook, A., & Giunti, P. (2017). Friedreich's ataxia: clinical features, pathogenesis and management. British Medical Bulletin, 124(1), 19-30. https://doi.org/10.1093/bmb/ldx034

Costantini, A., Laureti, T., Pala, M. I., Colangeli, M., Cavalieri, S., Pozzi, E., Brusco, A., Salvarani, S., Serrati, C. & Fancellu, R. (2016). Long-term treatment with thiamine as possible medical therapy for Friedreich ataxia. Journal of neurology, 263(11), 2170-2178.

Deore, A., Dhumane, J., Wagh, R. & Sonawane, R. (2019). The stages of drug discovery and development process. Asian Journal of Pharmaceutical Research and Development, 7, 62-67. https://doi.org/10.22270/ajprd.v7i6.616

Gaulton, A., Hersey, A., Nowotka, M., Bento, A. P., Chambers, J., Mendez, D., Mutowo, P., Atkinson, F., Bellis, L. J., Cibrián-Uhalte, E., Davies, M., Dedman, N., Karlsson, A., Magariños, M. P., Overington, J. P., Papadatos, G., Smit, I. & Leach, A. R. (2017). The ChEMBL database in 2017. Nucleic Acids Research, 45(D1), D945-D954. https://doi.org/10.1093/nar/gkw1074

Goncalves, S., Paupe, V., Dassa, E. P. & Rustin, P. (2008). Deferiprone targets aconitase: Implication for Friedreich's ataxia treatment. BMC Neurology, 8(1), 20. https://doi.org/10.1186/1471-2377-8-20

Gottesfeld, J. M. (2019). Molecular mechanisms and therapeutics for the GAA•TTC expansion disease Friedreich Ataxia. Neurotherapeutics, 16(4), 1032-1049. https://doi.org/10.1007/s13311-019-00764-x

Gramatica, P. & Sangion, A. (2016). A Historical excursus on the statistical validation parameters for QSAR models: A clarification concerning metrics and terminology. Journal of Chemical Information and Modeling, 56(6), 1127-1131. https://doi.org/10.1021/acs.jcim.6b00088

Guidotti, R., Monreale, A., Giannotti, F., Pedreschi, D., Ruggieri, S., & Turini, F. (2019). Factual and counterfactual explanations for black box decision making. IEEE Intelligent Systems, 34(6), 14-23.

Herman, D., Jenssen, K., Burnett, R., Soragni, E., Perlman, S. L., & Gottesfeld, J. M. (2006). Histone deacetylase inhibitors reverse gene silencing in Friedreich's ataxia. Nat Chem Biol, 2(10), 551-558. https://doi.org/10.1038/nchembio815

Hider, Robert C., Ma, Y., Molina-Holgado, F., Gaeta, A. & Roy, S. (2008). Iron chelation as a potential therapy for neurodegenerative disease. Biochemical Society Transactions, 36(6), 1304-1308. https://doi.org/10.1042/bst0361304

Hu, L., Liu, B., Ji, J. & Li, Y. (2020). Tree‐based machine learning to identify and understand major determinants for stroke at the neighborhood level. Journal of the American Heart Association, 9(22). https://doi.org/10.1161/jaha.120.016745

Işık, M., Demir, Y., Kırıcı, M., Demir, R., Şimşek, F. & Beydemir, Ş. (2015). Changes in the antioxidant system in adult epilepsy patients receiving antiepileptic drugs. Archives of physiology and biochemistry, 121(3), 97-102. https://doi.org/10.3109/13813455.2015.1026912

Jiménez-Luna, J., Grisoni, F. & Schneider, G. (2020). Drug discovery with explainable artificial intelligence. Nature Machine Intelligence, 2(10), 573-584. https://doi.org/10.1038/s42256-020-00236-4

Kaur, D., Yantiri, F., Rajagopalan, S., Kumar, J., Mo, J. Q., Boonplueang, R., Viswanath, V., Jacobs, R., Yang, L., Beal, M. F., Dimonte, D., Volitaskis, I., Ellerby, L., Cherny, R. A., Bush, A. I. & Andersen, J. K. (2003). Genetic or pharmacological Iron chelation prevents MPTP-induced neurotoxicity in Vivo. Neuron, 37(6), 899-909. https://doi.org/10.1016/s0896-6273(03)00126-0

Kumar, R., Zakharov, M. N., Khan, S. H., Miki, R., Jang, H., Toraldo, G., Singh, R., Bhasin, S. & Jasuja, R. (2011). The dynamic structure of the estrogen receptor. Journal of Amino Acids, 2011, 812540. https://doi.org/10.4061/2011/812540

Lavecchia, A. (2015). Machine-learning approaches in drug discovery: methods and applications. Drug Discov Today, 20(3), 318-331. https://doi.org/10.1016/j.drudis.2014.10.012

Lew, S.-Y., Yow, Y.-Y., Lim, L.-W. & Wong, K.-H. (2020). Antioxidant-mediated protective role of Hericium erinaceus (Bull.: Fr.) Pers. against oxidative damage in fibroblasts from Friedreich's ataxia patient. Food Science and Technology, 40(suppl 1), 264-272. https://doi.org/10.1590/fst.09919

Li, H. & Nantasenamat, C. (2019). Toward insights on determining factors for high activity in antimicrobial peptides via machine learning. PeerJ, 7, https://doi.org/10.7717/peerj.8265

Li, R., Shinde, A., Liu, A., Glaser, S., Lyou, Y., Yuh, B., Wong, J. & Amini, A. (2020). Machine learning–based interpretation and visualization of nonlinear interactions in prostate cancer survival. JCO Clinical Cancer Informatics(4), 637-646. https://doi.org/10.1200/cci.20.00002

Lipinski, C. A., Lombardo, F., Dominy, B. W. & Feeney, P. J. (2001). Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings1PII of original article: S0169-409X(96)00423-1. Advanced Drug Delivery Reviews, 46(1), 3-26. https://doi.org/https://doi.org/10.1016/S0169-409X(00)00129-0

Lo, Y. C., Rensi, S. E., Torng, W. & Altman, R. B. (2018). Machine learning in chemoinformatics and drug discovery. Drug Discov Today, 23(8), 1538-1546. https://doi.org/10.1016/j.drudis.2018.05.010

Lundberg, S. & Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions.

Lundberg, S. M., Erion, G. G. & Lee, S.-I. (2019). Consistent individualized feature attribution for tree ensembles.

Lundberg, S. M., Nair, B., Vavilala, M. S., Horibe, M., Eisses, M. J., Adams, T., Liston, D. E., Low, D. K.-W., Newman, S.-F., Kim, J. & Lee, S.-I. (2018). Explainable machine-learning predictions for the prevention of hypoxaemia during surgery. Nature Biomedical Engineering, 2(10), 749-760. https://doi.org/10.1038/s41551-018-0304-0

Malik, A. A., Phanus‐Umporn, C., Schaduangrat, N., Shoombuatong, W., Isarankura‐Na‐Ayudhya, C. & Nantasenamat, C. (2020). HCVpred: A web server for predicting the bioactivity of hepatitis C virus NS5B inhibitors. Journal of Computational Chemistry, 41(20), 1820-1834. https://doi.org/10.1002/jcc.26223

Molina-Holgado, F., Gaeta, A., Francis, P. T., Williams, R. J. & Hider, R. C. (2008). Neuroprotective actions of deferiprone in cultured cortical neurones and SHSY-5Y cells. Journal of Neurochemistry, 105(6), 2466-2476. https://doi.org/10.1111/j.1471-4159.2008.05332.x

Molnar, C. (2020). Interpretable machine learning. Self published. https://christophm.github.io/interpretable-ml-book/

Moncada-Torres, A., Van Maaren, M. C., Hendriks, M. P., Siesling, S. & Geleijnse, G. (2021). Explainable machine learning can outperform Cox regression predictions and provide insights in breast cancer survival. Scientific Reports, 11(1). https://doi.org/10.1038/s41598-021-86327-7

OECD, O. (2007). Environment health and safety publications series on testing and assessment No. 69, Guidance document on the validation of (quantitative) structure-activity relationships [(Q) SAR] models. In: OECD, Paris, France.

Pandolfo, M. (1999). Friedreich's ataxia: clinical aspects and pathogenesis. Semin Neurol, 19(3), 311-321. https://doi.org/10.1055/s-2008-1040847

Pandolfo, M. & Hausmann, L. (2013). Deferiprone for the treatment of Friedreich's ataxia. Journal of Neurochemistry, 126, 142-146. https://doi.org/10.1111/jnc.12300

Reeder, B. J. & Wilson, M. T. (2005). Desferrioxamine inhibits production of cytotoxic heme to protein cross-linked myoglobin: A mechanism to protect against oxidative stress without iron chelation. Chemical Research in Toxicology, 18(6), 1004-1011. https://doi.org/10.1021/tx049660y

Rodríguez-Pérez, R. & Bajorath, J. (2020). Interpretation of machine learning models using shapley values: application to compound potency and multi-target activity predictions. Journal of Computer-Aided Molecular Design, 34(10), 1013-1026. https://doi.org/10.1007/s10822-020-00314-0

Rodríguez, L. R., Lapeña, T., Calap-Quintana, P., Moltó, M. D., Gonzalez-Cabo, P. & Navarro Langa, J. A. (2020). Antioxidant therapies and oxidative stress in Friedreich's Ataxia: The right path or just a diversion? Antioxidants, 9(8), 664. https://doi.org/10.3390/antiox9080664

Saeys, Y., Inza, I. & Larranaga, P. (2007). A review of feature selection techniques in bioinformatics. Bioinformatics, 23(19), 2507-2517. https://doi.org/10.1093/bioinformatics/btm344

Schaduangrat, N., Malik, A. A. & Nantasenamat, C. (2021). ERpred: a web server for the prediction of subtype-specific estrogen receptor antagonists. PeerJ, 9, https://doi.org/10.7717/peerj.11716

Seznec, H., Simon, D., Bouton, C., Reutenauer, L., Hertzog, A., Golik, P., Procaccio, V., Patel, M., Drapier, J. C., Koenig, M. & Puccio, H. (2005). Friedreich ataxia: the oxidative stress paradox. Hum Mol Genet, 14(4), 463-474. https://doi.org/10.1093/hmg/ddi042

Shapley, L. (1953). A Value for n-Person Games. Princeton University Press, Princeton, 307-317. https://doi.org/https://doi.org/10.1515/9781400881970-018

Shapley, L. S. (2016). 17. A value for n-person games. Contributions to the Theory of Games (AM-28), II, 307-318. Princeton University Press. https://doi.org/doi:10.1515/9781400881970-018

Shobana, G. & Priya, D. N. (2021). Cancer drug classification using artificial neural network with feature selection. 2021 Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV),

Soragni, E., Xu, C., Cooper, A., Plasterer, H. L., Rusche, J. R. & Gottesfeld, J. M. (2011). Evaluation of histone deacetylase inhibitors as therapeutics for neurodegenerative diseases. Methods in molecular biology, 793, 495-508.

Soriano, S., Llorens, J. V., Blanco-Sobero, L., Gutiérrez, L., Calap-Quintana, P., Morales, M. P., Moltó, M. D. & Martínez-Sebastián, M. J. (2013). Deferiprone and idebenone rescue frataxin depletion phenotypes in a Drosophila model of Friedreich's ataxia. Gene, 521(2), 274-281. https://doi.org/10.1016/j.gene.2013.02.049

Staszak, M., Staszak, K., Wieszczycka, K., Bajek, A., Roszkowski, K. & Tylkowski, B. (2021). Machine learning in drug design: Use of artificial intelligence to explore the chemical structure–biological activity relationship. Wiley Interdisciplinary Reviews: Computational Molecular Science. https://doi.org/10.1002/wcms.1568

Stefanidou-Voziki, P., Cardoner-Valbuena, D., Villafafila-Robles, R. & Dominguez-Garcia, J. L. (2021). Feature selection and optimization of a ML fault location algorithm for low voltage grids. 2021 IEEE International Conference on Environment and Electrical Engineering and 2021 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe),

Vamathevan, J., Clark, D., Czodrowski, P., Dunham, I., Ferran, E., Lee, G., Li, B., Madabhushi, A., Shah, P., Spitzer, M. & Zhao, S. (2019). Applications of machine learning in drug discovery and development. Nat Rev Drug Discov, 18(6), 463-477. https://doi.org/10.1038/s41573-019-0024-5

Waskom, M., Botvinnik, Olga, Kane, Drew, Hobson, Paul, Lukauskas, Saulius, Gemperline, David C, Qalieh, Adel. (2017). mwaskom/seaborn: v0.8.1. Zenodo. https://doi.org/https://doi.org/10.5281/zenodo.883859

Wilson, R. B. (2006). Iron dysregulation in Friedreich ataxia. Semin Pediatr Neurol, 13(3), 166-175. https://doi.org/10.1016/j.spen.2006.08.005

Xue, L. & Bajorath, J. (2000). Molecular descriptors in chemoinformatics, computational combinatorial chemistry, and virtual screening. Comb Chem High Throughput Screen, 3(5), 363-372. https://doi.org/10.2174/1386207003331454

Yap, C. W. (2011). PaDEL-descriptor: An open source software to calculate molecular descriptors and fingerprints. Journal of Computational Chemistry, 32(7), 1466-1474. https://doi.org/10.1002/jcc.21707

Downloads

Published

2023-10-06

How to Cite

Kırboğa, K. K., Küçüksille, E. U., & Köse, U. (2023). Ignition of Small Molecule Inhibitors in Friedreich’s Ataxia with Explainable Artificial Intelligence. BRAIN. Broad Research in Artificial Intelligence and Neuroscience, 14(3), 287-313. https://doi.org/10.18662/brain/14.3/475

Most read articles by the same author(s)


Publish your work at the Scientific Publishing House LUMEN

It easy with us: publish now your work, novel, research, proceeding at Lumen Scientific Publishing House

Send your manuscript right now