Mazin Saleem Salman¹*, Fatimah Abdulrazzaq Mohammed² and Faten Salim Haanooon²

¹Southern Technical University, Ministry of Higher Education and Scientific Research, Iraq
²Ministry of Education, Iraq

*Corresponding Author: Mazin Saleem Salman, Department of Pharmacy Technologies, Southern Technical University, Ministry of Higher Education and Scientific Research, Iraq.

Received: April 30, 2024; Published: June 18, 2024

Abstract

The high costs and frequent failures have historically hindered the progress of developing medicines, due, to inefficiencies in the drug discovery process. To revolutionize drug development, in the current study we proposed a plan based on the use of artificial intelligence (AI). Our cutting-edge AI algorithms are designed to enhance drug candidates and predict their properties by leveraging machine learning, deep learning, and natural language processing. Our comprehensive approach involves data preparation, AI model creation, virtual screenings, molecule simulations, ADME/toxicity predictions and validation through experiments. We have generated 10,000 molecules, which were then narrowed down to 500 candidates. Showcasing the remarkable capabilities of our AI driven system. With an F1 score of 0.92 for bioactivity prediction an accuracy rate of 0.88, for solubility prediction and a toxicity prediction accuracy of 0.95; our machine learning models have exhibited performance. Our deep learning models have also performed well; for example, our CNN model for solubility prediction had a remarkable mean absolute error of 0.3 log units, while our GCN model for drug-target interactions had an area under the curve of 0.98. Chemicals created by AI with high binding affinities, such -12.5 kcal/mol, have been uncovered using molecular docking simulations. Among our notable accomplishments is the successful synthesis of twenty compounds, all of which have strong bioactivities with IC50 values between ten and two hundred nanometers. Importantly, research conducted in living organisms (mice and rats) has shown substantial therapeutic effectiveness, with outcomes such as a 60% suppression of tumor growth and a 75% decrease in inflammation. Our AI platform has proven time and time again that it can produce new, powerful drug candidates with desirable characteristics, opening the door to a more efficient drug discovery process that can hasten the distribution of revolutionary treatments and enhance patient results.

Keywords: Artificial Intelligence; Drug Discovery; Machine Learning; Deep Learning; Virtual Screening; ADME/T Prediction; Molecular Docking; Molecular Dynamics; Bioactivity Assays; In vivo Studies

References

1. DiMasi JA., et al. “Innovation in the pharmaceutical industry: new estimates of R&D costs”. Journal of Health Economics 47 (2016): 20-33.
2. Mak KK and Pichika MR. “Artificial intelligence in drug development: present status and future prospects”. Drug Discovery Today3 (2019): 773-780.
3. Stokes JM., et al. “A deep learning approach to antibiotic discovery”. Cell4 (2020): 688-702.
4. Chan HS., et al. “Advancing drug discovery via artificial intelligence”. Trends in Pharmacological Sciences8 (2019): 592-604.
5. Hughes JP., et al. “Principles of early drug discovery”. British Journal of Pharmacology6 (2011): 1239-1249.
6. Trott O and Olson AJ. “AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading”. Journal of Computational Chemistry 2 (2010): 455-461.
7. Mahmud M., et al. “Deep learning in mining biological data”. Cognitive Computation1 (2021): 1-33.
8. Wouters OJ., et al. “Estimated research and development investment needed to bring a new medicine to market, 2009-2018”. Jama9 (2020): 844-853.
9. Hosny A., et al. “Artificial intelligence in radiology”. Nature Reviews Cancer8 (2018): 500-510.
10. Cortes-Ciriano I., et al. “Comparing the influence of simulated experimental errors on 12 machine learning algorithms in bioactivity modeling using 12 diverse data sets”. Journal of Chemical Information and Modelling7 (2015): 1413-1425.
11. Vijay U., et al. “Microbial mutagenicity assay: Ames test”. Bio-protocol6 (2018): e2763.
12. Cherkasov A., et al. “QSAR modeling: where have you been? Where are you going to?”. Journal of Medicinal Chemistry 12 (2014): 4977-5010.
13. Kinnings SL., et al. “A machine learning-based method to improve docking scoring functions and its application to drug repurposing”. Journal of Chemical Information and Modelling 2 (2011): 408-419.
14. A Dobchev D., et al. “In silico machine learning methods in drug development”. Current Topics in Medicinal Chemistry 16 (2018): 1913-22.
15. Andrianov AM., et al. “Application of deep learning and molecular modeling to identify small drug-like compounds as potential HIV-1 entry inhibitors”. Journal of Biomolecular Structure and Dynamics16 (2022): 7555-7573.
16. Kim S., et al. “PubChem in 2021: new data content and improved web interfaces”. Nucleic Acids Research D1 (2021): D1388-1395.
17. Timmons PB and Hewage CM. “ENNAVIA is a novel method which employs neural networks for antiviral and anti-coronavirus activity prediction for therapeutic peptides”. Briefings in Bioinformatics6 (2021): bbab258.
18. Zhang Y., et al. “Deep learning driven drug discovery: tackling severe acute respiratory syndrome coronavirus 2”. Frontiers in Microbiology 12 (2021): 739684.

Citation

Citation: Mazin Saleem Salman., et al. “Harnessing Artificial Intelligence for the Design and Development of Novel Effective Medicines". Acta Scientific Microbiology 7.7 (2024): 27-37.

Copyright

Copyright: © 2024 Mazin Saleem Salman., et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.