TRANSFORMING BIOCHEMISTRY FOR DRUG DISCOVERY: THE RISE OF ARTIFICIAL INTELLIGENCE – A SYSTEMATIC REVIEW
Main Article Content
Keywords
Artificial Intelligence; Biochemistry; Machine Learning; Drug Discovery; Protein Structure Prediction
Abstract
Biochemistry continues to be heavily impacted by the increasing availability of biological data produced by advancements in genomic, proteomic and metabolomic research. The analysis of this large and highly complex data set has created challenges for both experimental and computational approaches in biochemistry. The use of artificial intelligence (AI) as a pattern recognition and learning tool to handle the large amount of available data has provided a means to overcome the limitations imposed by traditional biochemical methodologies.
Objectives: Reviewing the current state-of-the-art in the application of artificial intelligence in biochemical research while highlighting the transformative nature of AI in drug discovery and molecular analysis.
Materials and Methods: A comprehensive review of the literature was performed, utilizing electronic databases, including PubMed, Google Scholar and Scopus to obtain relevant articles regarding the application of various types of artificial intelligence (AI) techniques, including machine learning, deep learning and natural language processing in biochemical research. Articles identified were reviewed and synthesized.
Results: Artificial intelligence has made significant contributions to several areas of biochemistry, including protein structure prediction, enzyme engineering, drug discovery, metabolic pathway analysis and genomics/proteomics data interpretation. AI-based models have provided improved predictive capability, accelerated experimentation and decreased costs associated with experimentation and/or data analysis, allowing researchers to explore complex biological systems that could not have been studied using traditional biochemical methodologies.
Conclusion: Artificial intelligence will continue to transform biochemical research by improving data analysis capabilities, accelerating biochemical research workflows and enabling new avenues of drug discovery and drug development through advanced biochemical analytical methods. Although challenges exist regarding the quality of data being used in AI, the interpretability of AI-based models and ethics of using AI in biochemical research, we anticipate that future inclusion of AI into biochemical research will enable tremendous advancement in the fields of precision medicine, biotechnology and systems biology.
References
2. Senior, A. W., et al. Protein structure prediction using multiple sequence alignments. Nature 2020, 577, 706-710.
3. Collins, F. S., Hamburg, M. A., & Holtzman, D. M. Precision medicine. Science 2013, 341, 756-763.
4. Mitchell, J. B. O. Machine learning in drug discovery. Nat. Rev. Drug Discov. 2014, 13, 547-551.
5. Eran, A., & Ruppin, E. Machine learning in cancer research. Nat. Rev. Cancer 2019, 19, 755-771.
6. Liu, Y. Y., Nietlispach, D., & Sverrisson, F. Machine learning for protein engineering. Trends Biotechnol. 2020, 38, 64-76.
7. Greenshields, H. M., et al. Machine learning for metabolic engineering. Metab. Eng. 2019, 56, 164-181.
8. Libbrecht, M. W., & Noble, W. S. Machine learning applications in genetics and genomics. Nat. Rev. Genet. 2015, 16, 321-332.
9. Pu, Q., et al. Applications of deep learning in proteomics. Nat. Methods 2017, 14, 1087-1094.
10. LeCun, Y., Bengio, Y., & Hinton, G. Deep learning. Nature 2015, 521, 436-444.
Article Sidebar
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
All articles published in JPTCP are licensed under Copyright Creative Commons Attribution-NonCommercial 4.0 International License.
A C Jesudoss Prabhakaran
Professor and Head, Dept of Pharmacology, Sri Venkateswaraa Medical College Hospital,
Redhills, Chennai, India
