Submit to Molecules Review for Molecules Propose a Special Issue

Journal Menu

Journal Browser

Artificial Intelligence and Data Science in the Drug Discovery

Special Issue Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

A special issue of Molecules (ISSN 1420-3049). This special issue belongs to the section "Computational and Theoretical Chemistry".

Deadline for manuscript submissions: closed (31 May 2023) | Viewed by 12656

Share This Special Issue

Special Issue Editors

Dr. Khang Wen Goh

E-Mail Website
Guest Editor

Faculty of Data Science and Information Technology, INTI International University, Nilai 71800, Malaysia
Interests: swarm intelligence; mathematical modelling; fintech; pharmaceutical information technology; healthcare data analysis; precision farming optimization

Dr. Mohammad Khanfar

E-Mail Website
Guest Editor

School of Pharmacy, University of Jordan, Khanfar, Jordan
Interests: drug design; medicinal chemistry

Dr. Siok Yee Chan

E-Mail Website
Guest Editor

School of Pharmaceutical Sciences, Universiti Sains Malaysia, Minden, Malaysia
Interests: pharmaceutics; pharmaceutical technology; dosage form design; formulation sciences

Special Issue Information

Dear Colleagues,

Nowadays, researchers have unprecedented access to a wide variety of databases on chemical molecules and their activities against biological assays. With technological advancements, a new scientific field, data science, is formalized to signify the branch of research that analyses complicated sets of data, including huge datasets from various scientific angles, using sophisticated computer modeling and mathematics. Similarly, artificial intelligence (AI), which evolved from computer science, covers various approaches intended to improve the ability of modern technologies to make data-driven decisions and accurate predictions of events.

This Special Issue serves as a literature platform for effective applications of or theoretical advances in artificial intelligence and data science as well as computational mathematics in drug discovery and the design of drug molecules. Effective clinical examples for utilizing reliable and tested machine learning techniques, modern applications for reinforcement learning and deep learning, the influence of machine learning models, and upcoming solutions/difficulties for machine-learning-based projects in the field of drug development of small molecules, peptides, and antibodies are also welcome.

Dr. Khang Wen Goh
Dr. Mohammad Khanfar
Dr. Siok Yee Chan
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Molecules is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

artificial intelligence
drug discovery
cheminformatics
machine learning
molecular docking
computational drug design
data visualization
swarm intelligence

Benefits of Publishing in a Special Issue

Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (4 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

15 pages, 1886 KiB

Open AccessArticle

Deep Learning for Identifying Promising Drug Candidates in Drug–Phospholipid Complexes

by Soyoung Yoo, Hanbyul Lee and Junghyun Kim

Molecules 2023, 28(12), 4821; https://doi.org/10.3390/molecules28124821 - 16 Jun 2023

Viewed by 1794

Abstract

Drug–phospholipid complexing is a promising formulation technology for improving the low bioavailability of active pharmaceutical ingredients (APIs). However, identifying whether phospholipid and candidate drug can form a complex through in vitro tests can be costly and time-consuming due to the physicochemical properties and experimental environment. In a previous study, the authors developed seven machine learning models to predict drug–phospholipid complex formation, and the lightGBM model demonstrated the best performance. However, the previous study was unable to sufficiently address the degradation of test performance caused by the small size of the training data with class imbalance, and it had the limitation of considering only machine learning techniques. To overcome these limitations, we propose a new deep learning-based prediction model that employs variational autoencoder (VAE) and principal component analysis (PCA) techniques to improve prediction performance. The model uses a multi-layer one-dimensional convolutional neural network (CNN) with a skip connection to effectively capture the complex relationship between drugs and lipid molecules. The computer simulation results demonstrate that our proposed model performs better than the previous model in all performance metrics. Full article

(This article belongs to the Special Issue Artificial Intelligence and Data Science in the Drug Discovery)

► Show Figures

Graphical abstract

27 pages, 7335 KiB

Open AccessArticle

In Silico Drug Design of Anti-Breast Cancer Agents

by Kalirajan Rajagopal, Anandarajagopal Kalusalingam, Anubhav Raj Bharathidasan, Aadarsh Sivaprakash, Krutheesh Shanmugam, Monall Sundaramoorthy and Gowramma Byran

Molecules 2023, 28(10), 4175; https://doi.org/10.3390/molecules28104175 - 18 May 2023

Cited by 4 | Viewed by 4321

Abstract

Cancer is a condition marked by abnormal cell proliferation that has the potential to invade or indicate other health issues. Human beings are affected by more than 100 different types of cancer. Some cancer promotes rapid cell proliferation, whereas others cause cells to divide and develop more slowly. Some cancers, such as leukemia, produce visible tumors, while others, such as breast cancer, do not. In this work, in silico investigations were carried out to investigate the binding mechanisms of four major analogs, which are marine sesquiterpene, sesquiterpene lactone, heteroaromatic chalcones, and benzothiophene against the target estrogen receptor-α for targeting breast cancer using Schrödinger suite 2021-4. The Glide module handled the molecular docking experiments, the QikProp module handled the ADMET screening, and the Prime MM-GB/SA module determined the binding energy of the ligands. The benzothiophene analog BT_ER_15f (G-score −15.922 Kcal/mol) showed the best binding activity against the target protein estrogen receptor-α when compared with the standard drug tamoxifen which has a docking score of −13.560 Kcal/mol. TRP383 (tryptophan) has the highest interaction time with the ligand, and hence it could act for a long time. Based on in silico investigations, the benzothiophene analog BT_ER_15f significantly binds with the active site of the target protein estrogen receptor-α. Similar to the outcomes of molecular docking, the target and ligand complex interaction motif established a high affinity of lead candidates in a dynamic system. This study shows that estrogen receptor-α targets inhibitors with better potential and low toxicity when compared to the existing market drugs, which can be made from a benzothiophene derivative. It may result in considerable activity and be applied to more research on breast cancer. Full article

(This article belongs to the Special Issue Artificial Intelligence and Data Science in the Drug Discovery)

► Show Figures

Figure 1

19 pages, 6410 KiB

Open AccessArticle

Coumarin-Based Sulfonamide Derivatives as Potential DPP-IV Inhibitors: Pre-ADME Analysis, Toxicity Profile, Computational Analysis, and In Vitro Enzyme Assay

by Pallavi Kishor Vawhal, Shailaja B. Jadhav, Sumit Kaushik, Kahnu Charan Panigrahi, Chandan Nayak, Humaira Urmee, Sharuk L. Khan, Falak A. Siddiqui, Fahadul Islam, Aziz Eftekhari, Abdullah R. Alzahrani, Mohd Fahami Nur Azlina, Md. Moklesur Rahman Sarker and Ibrahim Abdel Aziz Ibrahim

Molecules 2023, 28(3), 1004; https://doi.org/10.3390/molecules28031004 - 19 Jan 2023

Cited by 6 | Viewed by 3206

Abstract

Recent research on dipeptidyl peptidase-IV (DPP-IV) inhibitors has made it feasible to treat type 2 diabetes mellitus (T2DM) with minimal side effects. Therefore, in the present investigation, we aimed to discover and develop some coumarin-based sulphonamides as potential DPP-IV inhibitors in light of the fact that molecular hybridization of many bioactive pharmacophores frequently results in synergistic activity. Each of the proposed derivatives was subjected to an in silico virtual screening, and those that met all of the criteria and had a higher binding affinity with the DPP-IV enzyme were then subjected to wet lab synthesis, followed by an in vitro biological evaluation. The results of the pre-ADME and pre-tox predictions indicated that compounds 6e, 6f, 6h, and 6m to 6q were inferior and violated the most drug-like criteria. It was observed that 6a, 6b, 6c, 6d, 6i, 6j, 6r, 6s, and 6t displayed less binding free energy (PDB ID: 5Y7H) than the reference inhibitor and demonstrated drug-likeness properties, hence being selected for wet lab synthesis and the structures being confirmed by spectral analysis. In the in vitro enzyme assay, the standard drug Sitagliptin had an IC₅₀ of 0.018 µM in the experiment which is the most potent. All the tested compounds also displayed significant inhibition of the DPP-IV enzyme, but 6i and 6j demonstrated 10.98 and 10.14 µM IC₅₀ values, respectively, i.e., the most potent among the synthesized compounds. Based on our findings, we concluded that coumarin-based sulphonamide derivatives have significant DPP-IV binding ability and exhibit optimal enzyme inhibition in an in vitro enzyme assay. Full article

(This article belongs to the Special Issue Artificial Intelligence and Data Science in the Drug Discovery)

► Show Figures

Figure 1

24 pages, 6410 KiB

Open AccessArticle

Virtual Screening, Synthesis, and Biological Evaluation of Some Carbohydrazide Derivatives as Potential DPP-IV Inhibitors

by Prerana B. Jadhav, Shailaja B. Jadhav, Mehrukh Zehravi, Mohammad S. Mubarak, Fahadul Islam, Philippe Jeandet, Sharuk L. Khan, Nazmul Hossain, Salma Rashid, Long Chiau Ming, Md. Moklesur Rahman Sarker and Mohd Fahami Nur Azlina

Molecules 2023, 28(1), 149; https://doi.org/10.3390/molecules28010149 - 24 Dec 2022

Cited by 7 | Viewed by 2329

Abstract

Dipeptidyl peptidase-4 (DPP-IV) inhibitors are known as safe and well-tolerated antidiabetic medicine. Therefore, the aim of the present work was to synthesize some carbohydrazide derivatives (1a–5d) as DPP-IV inhibitors. In addition, this work involves simulations using molecular docking, ADMET analysis, and Lipinski and Veber’s guidelines. Wet-lab synthesis was used to make derivatives that met all requirements, and then FTIR, NMR, and mass spectrometry were used to confirm the structures and perform biological assays. In this context, in vitro enzymatic and in vivo antidiabetic activity evaluations were carried out. None of the molecules had broken the majority of the drug-likeness rules. Furthermore, these molecules were put through additional screening using molecular docking. In molecular docking experiments (PDB ID: 2P8S), many molecules displayed more potent interactions than native ligands, exhibiting more hydrogen bonds, especially those with chloro- or fluoro substitutions. Our findings indicated that compounds 5b and 4c have IC₅₀ values of 28.13 and 34.94 µM, respectively, under in vitro enzymatic assays. On the 21st day of administration to animals, compound 5b exhibited a significant reduction in serum blood glucose level (157.33 ± 5.75 mg/dL) compared with the diabetic control (Sitagliptin), which showed 280.00 ± 13.29 mg/dL. The antihyperglycemic activity showed that the synthesized compounds have good hypoglycemic potential in fasting blood glucose in the type 2 diabetes animal model (T2DM). Taken all together, our findings indicate that the synthesized compounds exhibit excellent hypoglycemic potential and could be used as leads in developing novel antidiabetic agents. Full article

(This article belongs to the Special Issue Artificial Intelligence and Data Science in the Drug Discovery)

► Show Figures

Journal Menu

Journal Browser

Artificial Intelligence and Data Science in the Drug Discovery

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (4 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI