China
Africa
Explore chapters and articles related to this topic
Role of AI in the Advancement of Drug Discovery and Development
Published in Utpal Chakraborty, Amit Banerjee, Jayanta Kumar Saha, Niloy Sarkar, Chinmay Chakraborty, Artificial Intelligence and the Fourth Industrial Revolution, 2022
Shantanu K. Yadav, Poonam Jindal, Rakesh K. Sindhu
There are presently some established drugs that have used AI methods, but it is possible that it will take another two to three years for more drugs to be established on the basis of advances in technology (AI). Experts believe strongly that AI will forever change the drug industry, including how medicines are found. Nevertheless, the person must know how to train algorithms, needing domain expertise, to be effective in biopharmaceuticals utilizing AI. An acceptable environment will be when AI and medicinal chemists work closely, as the former can help analyze huge data sets and the latter can train machines. Specifically, the DL method is able to handle complicated tasks with massive, high-dimensional data sets without any physical intervention, which has proved valuable in works and business applications. The only way to fully incorporate several large platform data repositories would be to combine ML, particularly DL, with experience and human expertise. AI technology’s powerful data mining capability has given a new energy to software-aided drug design, accelerating and encouraging the drug development process. It is expected that AI software will infiltrate many fields of drug development, and new-drug research will thus become a machine-aided form of drug discovery. Combined with the sequential control of automation and smart synthesis software, a smart drug development system may emerge that combines analytics—the AI prediction model—and automated synthesis. Besides, the present situation of the long cycle of drug development, high price, and high failure rate is expected to change.
Computer-Aided Drug Design for the Identification of Multi-Target Directed Ligands (MTDLs) in Complex Diseases: An Overview
Published in Peter Grunwald, Pharmaceutical Biocatalysis, 2019
Computational or in silico studies play an important role in the drug discovery and drug design paradigm by providing guidance towards the lead identification, lead optimization, prioritization of chemicals before initiating the synthetic or experimental analysis and designing superior analogues. Notably, in silico techniques complement the 3Rs approach, i.e., replacement, refinement, and reduction of animals in research as well as these are cost-effective and time saving. There are several available in silico techniques that can be divided into two major application areas, i.e., structure-based drug design and ligand-based drug design (Huang et al., 2010). Structure-based drug design relies on three-dimensional (3D) structural knowledge of the target protein (enzyme or receptor) and its binding sites to investigate vital inter-molecular interactions as well as their corresponding binding energy. On the other hand, ligand-based drug design relies on knowledge of ligands with known binding information with the target of interest. Notably, both type of techniques together become a powerful in silico tool to design potential ligands against one or multiple targets.
Applications of Machine Learning in Industrial Sectors
Published in Pedro Larrañaga, David Atienza, Javier Diaz-Rozo, Alberto Ogbechie, Carlos Puerto-Santana, Concha Bielza, Industrial Applications of Machine Learning, 2019
Pedro Larrañaga, David Atienza, Javier Diaz-Rozo, Alberto Ogbechie, Carlos Puerto-Santana, Concha Bielza
The aim in drug design is to identify lead compounds with significant activity against a selected biological target. The drug target is a protein whose activity is modulated by its interaction with a chemical compound and may thus control a disease. Lead compounds are identified at the drug discovery stage. They are then optimized in the drug development phase, resulting in a small number of chemicals that are evaluated in human clinical trials. Machine learning has been used at the drug discovery stage to build functions that rank the probability that a chemical will have activity against a known target and to predict ligand-receptor affinity, target structure and the side-effects of new drugs, as well as for target screening on cells and even in drug delivery systems (Bernick, 2015). The review by Lima et al. (2016) mentions random forests, decision trees, artificial neural networks and support vector machines as the main techniques in new drug discovery, whereas Lavecchia (2015) adds k-nearest neighbors, and naive Bayes. Another important use of machine learning is to predict the pharmacokinetic and toxicological profile of compounds, i.e., the so-called ADME-Tox (absorption, distribution, metabolism, excretion and toxicity) (Maltarollo et al., 2015).
Synthesis of Schiff base ligands from salicylaldehyde as potential antibacterial agents: DFT and molecular docking studies
Published in Molecular Physics, 2023
Md. Idrish Ali, Sabrina Helen, Mukta Das, Masud Rana Juwel, Muhammad Abul Kashem Liton
In present times, the development of potential drugs to treat diseases has progressively more relied on computer-aided drug design (CADD). Drug development by means of CADD might reduce the expenses and labour, as well as expedite the development cycle in comparison to conventional methods [19]. CADD comprises several methods, such as pharmacophore modelling, virtual screening, molecular docking and dynamic simulation. These methods are frequently employed to design, generate and examine drugs or other physiologically active compounds [20]. During the past few decades, the recognition of CADD is being well set in the creation of therapeutically important compounds [21]. Molecular docking is the most frequently applied technique for constructing biological and molecular mechanisms to predict and simulate complex structures at the molecular or even atomic level [22]. This technique starts with congregation of various ligand conformations at the active site of the receptor, and then ranking the ligands according to the energies of each specific binding conformation [23].
Genetic functional algorithm model, docking studies and in silico design of novel proposed compounds against Mycobacterium tuberculosis
Published in Egyptian Journal of Basic and Applied Sciences, 2020
The first stage for the design and synthesis of novel hypothetical compounds with enhanced anti-tubercular activity and less toxicity/side effect as to with the approaches and methods that will consider the rate of experimental runs and time factor. Reference to the design of novel drug candidate, computer-aided drug design has demonstrated a crucial part for the discovery of new molecules in pharmaceutical design, drug metabolism, and medicinal chemistry [13]. This approach had facilitated the improvement in the course of optimization of chemical structures with well-defined purposes [14]. Quantitative structure-activity relationship study (QSAR) and molecular docking are one of the computer-aided drug design approaches which had been broadly utilized in the design, improvement and synthesis of first-hand drug [2]. QSAR investigation had shown to be an expedient technique for forecasting biological/inhibition activities, properties of any chemical compound by making use of an experimental data and molecular descriptors. This idea is based on the correlation between the information derived from any chemical space or structural molecule illustrated by the descriptor and well-defined experimental data provided. Meanwhile, molecular docking technique help to foresee the binding location and affinity of the existing interaction between the molecule (ligand) and the target. Thereby providing an idea to design prospective drug with better activity against the target [2]. Therefore, the study aimed to build a Genetic Functional Algorithm model, carry out molecular docking studies and in silico design of novel proposed compounds against Mycobacterium tuberculosis