Exploring the Synergistic Potential of Artificial Intelligence and Machine Learning in Chemistry
Open Access
- 30 December 2024
- journal article
- Published by University of Sri Jayewardenepura in Vidyodaya Journal of Science
- Vol. 27 (02)
Abstract
Machine learning (ML) and artificial intelligence (AI) have become specialists in different areas of chemistry. These technologies help to change the standard approaches to data analysis and molecular design along with the properties forecast. This review describes the interesting applications and increasing potential of AI and ML, specifically in drug discovery, chemical synthesis, material science, and computational chemistry. Computationally, the focus was on the application of AI algorithms to quantum chemistry simulations to predict properties of elements within a molecule, or possible reactions of molecules at a rate that would not have been possible manually. Moreover, AI-driven robotic synthesis platforms and experimental techniques have become less labor-intensive. The methods used for the identification of new chemical structures have improved in terms of speed. The benefits and the limitations of integrating AI, as well as the opportunities, are discussed in detail. In this review, it is also reiterated that there are risks that come with the integration of ML in chemistry and how interdisciplinary collaboration and data sharing are crucial to advancing in this field. In a single summary, this review demonstrates how the use of AI and ML can and will expand the horizons of chemical science and discovery.Keywords: Artificial Intelligence, Machine Learning, Drug Discovery, Chemical Synthesis, Materials Science, Computational Chemistry.Keywords
This publication has 42 references indexed in Scilit:
- Experimental design optimization of the ODS of DBT using vanadium oxide supported on mesoporous Ga-SBA-15Catalysis Today, 2020
- Graph Networks as a Universal Machine Learning Framework for Molecules and CrystalsChemistry of Materials, 2019
- Dual-therapy strategy for modification of adiponectin receptor signaling in aging-associated chronic diseasesDrug Discovery Today, 2018
- Synthesis and Evaluation of Ideal Core/Shell Quantum Dots with Precisely Controlled Shell Growth: Nonblinking, Single Photoluminescence Decay Channel, and Suppressed FRETChemistry of Materials, 2018
- Machine Learning in Computer-Aided Synthesis PlanningAccounts of Chemical Research, 2018
- PySCF: the Python‐based simulations of chemistry frameworkWIREs Computational Molecular Science, 2017
- Deep learning for computational chemistryJournal of Computational Chemistry, 2017
- Neural‐Symbolic Machine Learning for Retrosynthesis and Reaction PredictionChemistry – A European Journal, 2017
- Applied Predictive Modeling2013
- AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreadingJournal of Computational Chemistry, 2009