ARTIFICIAL INTELIGENCE IN DRUG DISCOVERY

Dr. Sandip Prasad Tiwari

Faculty of Pharmacy

In the recent years use of Artificial Intelligence (AI) has been widely explored in the field of pharmaceutical research. AI is a software that can learn from data like a human being, gain experience methodically, and ultimately provide a solution or diagnostic even faster than people [1]. AI is a fundamental path in modern medicine. With advantages including mistake reduction, improved accuracy, quick processing, and improved diagnosis, AI has evolved into a medical assistant with the goal of effectively assisting clinicians [2]. From a clinical standpoint, AI is now used to assist doctors in decision-making due to faster pattern recognition from the medical data, which is also registered more precisely in computers than in humans; additionally, AI has the ability to manage and monitor the patients’ data and creating a customised medical plan for future treatments [3]. At several levels, including telemedicine illness diagnosis, decision-making assistance, and medication discovery and development, AI has been shown to be useful in the medical industry [4].

Deep learning (DL) and machine learning have many applications in the healthcare industry, such as clinical decision support systems (CDS) that use massive datasets or human knowledge to make clinical recommendations [5]. Analysis of extensive history data is another use that can be used to forecast a patient’s future instances by identifying patterns. We will discuss the most significant deep learning developments and applications in medical imaging in this paper. The most significant advances in several scientific fields, such as computer vision, natural language processing (NLP), and chemical structure, have been made using deep learning, which is the current use of AI in medical imaging [6]. Deep learning has recently generated a lot of attention in the field of medical imaging due to its resilience while handling images, and it has a bright future for this industry. The key argument in favour of DL is that medical data are huge and come in a variety of forms, including pictures, signals, and patient monitoring records for body felt data [7]. The primary area where DL technique surpassed humans was in the analysis of these data, especially historical data, by learning extremely complex mathematical models and extracting relevant information. In other words, while DL framework won’t take the job of doctors, it will help them make decisions and improve the precision of the final diagnosis analysis [8].

References:

1. Kolluri S, Lin J, Liu R, Zhang Y, Zhang W. Machine learning and artificial intelligence in pharmaceutical research and development: a review. The AAPS Journal. 2022 Feb;24:1-0.
2. Thakur A, Mishra AP, Panda B, Rodríguez D, Gaurav I, Majhi B. Application of artificial intelligence in pharmaceutical and biomedical studies. Current pharmaceutical design. 2020 Aug 1;26(29):3569-78.
3. Mitchell JB. Artificial intelligence in pharmaceutical research and development. Future Medicinal Chemistry. 2018 Jul;10(13):1529-31.
4. Henstock PV. Artificial intelligence for pharma: time for internal investment. Trends in pharmacological sciences. 2019 Aug 1;40(8):543-6.
5. Gupta R, Srivastava D, Sahu M, Tiwari S, Ambasta RK, Kumar P. Artificial intelligence to deep learning: machine intelligence approach for drug discovery. Molecular diversity. 2021 Aug;25:1315-60.
6. Garg A, Mago V. Role of machine learning in medical research: A survey. Computer science review. 2021 May 1;40:100370.
7. Rifaioglu AS, Atas H, Martin MJ, Cetin-Atalay R, Atalay V, Doğan T. Recent applications of deep learning and machine intelligence on in silico drug discovery: methods, tools and databases. Briefings in bioinformatics. 2019 Sep;20(5):1878-912.
8. Currie G, Hawk KE, Rohren E, Vial A, Klein R. Machine learning and deep learning in medical imaging: intelligent imaging. Journal of medical imaging and radiation sciences. 2019 Dec 1;50(4):477-87.