ARTIFICAL INTELLIGENCE AND MACHINE LEARNING IN PHARMACEUTICAL ANALYSIS

B. Satya Prasad*, J. N. Suresh Kumar, P. Pavani, B. Bhargavi, S. K. Akram, D. Sasi Kumar, K. Vineela Eswari Devi

ABSTRACT

Artificial Intelligence (AI) & Machine Learning (ML) are two terms that transformed pharmaceutical sciences, including drug discovery, drug development, precision medicine and nanomedicine. Traditional drug discovery is a long, expensive and failure-prone process that may take over 10 years and million of dollars before it produces a therapeutically active compound ready for clinical trials and commercialization. AI-driven computational approaches can tackle numerous challenges of drug discovery and development, including target or lead identification and optimization, virtual screening, predicting drug target interactions, toxicity and personalized treatment options. The concept of artificial intelligence was first introduced in the 1940s when Alan Turing laid the foundations for machine intelligence theory claiming that there is no fundamental difference between human and machine computation (Turing, 1950). The formal idea of artificial intelligence was further proposed by Mc Carthy, Minsky, Rochester and Shannon who proposed the Dartmouth Hypothesis about the possibility for machines to stimulate human intelligence (Mc Carthy et al 1955). In the following decades the concepts machine learning and deep learning were introduced Schmidhuber in 2015. There are three review papers that discuss the role of AI&ML in pharmaceutical sciences and health care. The first study focus on the role of artificial intelligence in drug discovery and discovery and precision nanomedicine (Zhu et al, 2022). Zhu et al. highlight importance of algorithms and nano-enabled therapeutics for precision nanomedicine. The main ideas of the study include finding and selecting the target developing the optimal drug using nano-enabled therapeutics and individualizing treatment based on patients characteristics. The second review paper discuss the role of AI in spatial structure of protein predicting and drug synergism prediction targeting molecular mechanism and protein drug interactions (Lie et al, 2022). The study by Lei et al. high-light the importance of AI in analyzing and prediction the spatial structure of protein to reveal molecular mechanisms and biological functions. The third review paper was discusses the concept of artificial intelligence, machine learning and deep learning elucidates ethical and social implications and high light the public awarness about AI (Garcia & Salichos, 2022). The study by Garcia & Salichosis a detailed analysis about the opportunities and limitations of AI.I would like to address the main ideas of all three reviewed papers and discuss hoe AL&ML can be applied to various stages of drug discovery and development. I will also comment on such terms as machine learning, deep learning, protein spatial structure prediction, virtual screening precision, precision medicine, nanomedicine, drug synergism prediction, explainable AI.

Keywords: Artificial Intelligence; Machine Learning; Deep Learning; Drug Discovery; Pharmaceutical Analysis; Precision Medicine; Nanomedicine; Drug Target Interactions; Drug Synergism; Protein Structure Prediction; Explainable AI.