A Brief Review of Machine Learning-Based Bioactive Compound Research

Abstract

Bioactive compounds are often used as initial substances for many therapeutic agents. In recent years, both theoretical and practical innovations in hardware-assisted and fast-evolving machine learning (ML) have made it possible to identify desired bioactive compounds in chemical spaces, such as those in natural products (NPs). This review introduces how machine learning approaches can be used for the identification and evaluation of bioactive compounds. It also provides an overview of recent research trends in machine learning-based prediction and the evaluation of bioactive compounds by listing real-world examples along with various input data. In addition, several ML-based approaches to identify specific bioactive compounds for cardiovascular and metabolic diseases are described. Overall, these approaches are important for the discovery of novel bioactive compounds and provide new insights into the machine learning basis for various traditional applications of bioactive compound-related research.

Bioactive Compounds of Verbascum sinuatum L.: Health Benefits and Potential as New Ingredients for Industrial Applications

“…Bioactive compounds are minor chemical compounds present in plants or animals with beneficial health properties with many potential industrial applications [ 20 ]. The aerial part of V. sinuatum used in traditional medicine have been analyzed by some authors, who have reported that the main bioactive compounds are polyphenols and iridoids ( Table 2 ).…”

“…For this reason, the extraction and characterization of the different classes of the phenolic compounds from natural plants may lead to the development of new ingredients for industrial applications. Concerning these compounds, three different classes have been identified in V. sinuatum [ 6 , 20 , 21 , 22 , 23 ]: (1) flavonoids, such as apigenin, luteolin, naringin, rutin, naringenin, plantagonine, rhamnetin, myricetin, hesperetin, cynaroside, apigetrin, hyperoside, chrysin, and quercetin; (2) phenolic acids, such as caffeic acid, caffeic acid hexoxide, ρ -Coumaric acid, quinic acid, ursolic acid, chlorogenic acid, cinnamic acid, and gallic acid; and (3) phenylethanoid glycosides, such as p -coumaroyl-6- O -rhamnosyl aucubin isomer I and p -coumaroyl-6- O -rhamnosyl aucubin isomer II.…”

Identification of Drug Compound Bio-Activities Through Artificial Intelligence

“…Different public Repositories like Drug Bank, PubChem, CheMBL are present (Reboredo, P.C., et al, 2021). Park, J. et al, (2022) and the team elaborated on utilization of machine learning in detecting the bioactivity of compounds, Bioactive compounds are those chemical compounds that are used to cure different diseases. It is used as a curing agent after predicting using ML approaches.…”

“…Experimentally verified bioactivity of natural products is insufficient to build an ML model. To process the lead optimization task more efficiently, many machine learning approaches have been studied recently: (i) atom modification reinforcement learning models that add or delete atoms or bonds, (ii) generative reinforcement learning which generates similar but modified structures, (iii) generative machine learning with controlled chemical properties that also generates similar modified structure with preserved predictive properties, and (iv) a 3D structure-based ligand design model that uses a 3D crystal structure of protein and ligand to generate novel molecules (Park, J., et al, 2022). Gupta, R.et al,(2021) and the team stated that AI and deep learning algorithms have been applied in an alternate piece of medication revelation processes like peptide, synthesis, structure-based virtual screening, ligand-based virtual screening, harmfulness forecast, drug checking, and quantitative design action relationship.…”

Drug–Target Interaction Deep Learning-Based Model Identifies the Flavonoid Troxerutin as a Candidate TRPV1 Antagonist

“…2023, 13, 5617 2 of 12 that can be trained with known datasets to predict new outputs based on trained weights. In drug discovery, ML techniques can be used to predict the physicochemical properties, bioactivity, and toxicity of small-molecule bioactive compounds and are more cost-effective and rapid than conventional methods [8][9][10][11]. Using ML, the present study aimed to identify natural compounds or derivatives that could act as transient receptor potential vanilloid 1 (TRPV1) antagonists.…”