Artificial Intelligence in Drug Design: Algorithms, Applications, Challenges and Ethics

Abstract

The discovery paradigm of drugs is rapidly growing due to advances in machine learning (ML) and artificial intelligence (AI). This review covers myriad faces of AI and ML in drug design. There is a plethora of AI algorithms, the most common of which are summarized in this review. In addition, AI is fraught with challenges that are highlighted along with plausible solutions to them. Examples are provided to illustrate the use of AI and ML in drug discovery and in predicting drug properties such as binding affinities and interactions, solubility, toxicology, blood–brain barrier permeability and chemical properties. The review also includes examples depicting the implementation of AI and ML in tackling intractable diseases such as COVID-19, cancer and Alzheimer’s disease. Ethical considerations and future perspectives of AI are also covered in this review.

Quantum and Classical Evaluations of Carboxylic Acid Bioisosteres: From Capped Moieties to a Drug Molecule

“…These similarities are congruent with the similarities observed for other carboxylic acid bioisosteres from previous studies, which include tetrazole, 18 methylsquarate, 17 sulfonamide, 16 isoxazole, tetrazol-5-one, oxadiazole, thiazolidinedione, and oxazolidinedione. 15 To highlight the non-coincidence in this similarity of the bioisosteric or potential bioisosteric groups, the rather leveled-off AED values in these groups are contrasted with (1) the significant difference observed in the AEDs between the non-bioisosteric pair (furan and sulfonamide) and (2) the relatively varying AEDs of the capping groups (as shown in Figure 3 ). The AED difference, on average, between the carboxylic acid (0.0713 a.u.)…”

“…The ESP maps are used as a classical tool to qualitatively visualize molecular properties, while the AED is a quantum tool used to evaluate quantitatively atomic or, subsequently, group properties within a molecule. In the past, the ESP maps had been relied on, almost exclusively, to explain non-classical bioisosterism. , However, in the past decade, the AED tool was developed and referred to as a more robust quantitative tool for measuring the similarity among non-classical bioisosteres. − The AED tool is based on, first, generating the wavefunction of a system, and then, partitioning the molecule into atomic basins according to the Quantum Theory of Atoms in Molecules (QTAIM) theory. The property of a bioisosteric group is then calculated as the sum of the properties of the atoms constituting this group.…”

Analog Programmable‐Photonic Computation

“…There are numerous applications in mathematics, physics, and (bio) engineering that can be efficiently solved by utilizing matrix algorithms, such as artificial intelligence, [ 70 ] deep learning, [ 71 ] tensor decomposition, [ 72 ] astronomical imaging, [ 73 ] robotics, [ 74 ] drug design, [ 75,76 ] autonomous driving, [ 77 ] medical diagnostic imaging, [ 78 ] and genomic analysis. [ 79,80 ] Most of these applications involve pattern recognition , a computational task that can be conducted with quantum computers, e.g., using the single‐qubit model reported in refs.…”

Computational research on flat image design and style based on perceptual feature quantification

“…With the continuous development of technologies such as Internet [1], Internet of Things [2], big data [3] and artificial intelligence [4], design is gradually moving towards digitisation [5], networking [6], intelligence and personalisation -the new form of intelligence [7]. Replacing manual production with computers [8] and using algorithms [9] to help designers complete repetitive design tasks [10] is one of the important contents of the new generation of intelligent design [11] research. Taking the design of graphic images [12] as an example, from the posters that can be seen everywhere in life to the large and small web page advertisements on the Internet, the demand for a large number of low-value and easy-to-consume graphic design has always been a problem [13].…”