Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.7
4.6
Journals
Pharmaceuticals
Special Issues
Machine Learning Methods for Medicinal Chemistry
share announcement

Machine Learning Methods for Medicinal Chemistry

A special issue of Pharmaceuticals (ISSN 1424-8247). This special issue belongs to the section "Medicinal Chemistry".

Deadline for manuscript submissions: closed (25 February 2024) | Viewed by 8904

Special Issue Editor

Dr. Krzysztof Marciniec

E-Mail Website
Guest Editor
Department of Organic Chemistry, Medical University of Silesia, Jagiellonska 4, PL-41200 Sosnowiec, Poland
Interests: organic synthesis; molecular docking; molecular dynamics; anticancer activity; antipsychotic activity

Special Issue Information

Dear Colleagues,

The concept of artificial intelligence (AI) is increasingly being used in predictive modeling and optimization of medical chemistry processes in drug discovery. One of the main goals of AI is to create machine learning (ML) platforms that enable gradual improvement in model performance. This Special Issue aims to introduce examples showing how current ML methods are used in various areas of the drug discovery process. The focus will be placed on some achievements using newer machine learning methods in designing tools capable of generating and assessing synthetic structures, as well as ligand binding and ADMET models.

Perspective topics include (but are not limited to):

  • Recent advances in AI/ML algorithms;
  • Applications of ML in structure generation;
  • Prediction of target protein in drug design;
  • Homology modeling/prediction of protein folding;
  • Machine learning approaches to predicting protein–ligand interactions;
  • In silico toxicity and ADMET modeling to optimize molecular properties;
  • ML in drug metabolite and metabolic site prediction;
  • ML-based biomarker discovery;
  • Use of ML in synthesis planning.

Dr. Krzysztof Marciniec
Guest Editor

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. Pharmaceuticals is an international peer-reviewed open access monthly 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 2900 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

  • machine learning
  • drug discovery
  • QSAR
  • ADMET
  • in silico screening
  • molecular docking
  • synthesis planning

Published Papers (6 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

16 pages, 1257 KiB  
Article
Absorption Distribution Metabolism Excretion and Toxicity Property Prediction Utilizing a Pre-Trained Natural Language Processing Model and Its Applications in Early-Stage Drug Development
by Woojin Jung, Sungwoo Goo, Taewook Hwang, Hyunjung Lee, Young-Kuk Kim, Jung-woo Chae, Hwi-yeol Yun and Sangkeun Jung
Pharmaceuticals 2024, 17(3), 382; https://doi.org/10.3390/ph17030382 - 17 Mar 2024
Viewed by 911
Abstract
Machine learning techniques are extensively employed in drug discovery, with a significant focus on developing QSAR models that interpret the structural information of potential drugs. In this study, the pre-trained natural language processing (NLP) model, ChemBERTa, was utilized in the drug discovery process. [...] Read more.
Machine learning techniques are extensively employed in drug discovery, with a significant focus on developing QSAR models that interpret the structural information of potential drugs. In this study, the pre-trained natural language processing (NLP) model, ChemBERTa, was utilized in the drug discovery process. We proposed and evaluated four core model architectures as follows: deep neural network (DNN), encoder, concatenation (concat), and pipe. The DNN model processes physicochemical properties as input, while the encoder model leverages the simplified molecular input line entry system (SMILES) along with NLP techniques. The latter two models, concat and pipe, incorporate both SMILES and physicochemical properties, operating in parallel and with sequential manners, respectively. We collected 5238 entries from DrugBank, including their physicochemical properties and absorption, distribution, metabolism, excretion, and toxicity (ADMET) features. The models’ performance was assessed by the area under the receiver operating characteristic curve (AUROC), with the DNN, encoder, concat, and pipe models achieved 62.4%, 76.0%, 74.9%, and 68.2%, respectively. In a separate test with 84 experimental microsomal stability datasets, the AUROC scores for external data were 78% for DNN, 44% for the encoder, and 50% for concat, indicating that the DNN model had superior predictive capabilities for new data. This suggests that models based on structural information may require further optimization or alternative tokenization strategies. The application of natural language processing techniques to pharmaceutical challenges has demonstrated promising results, highlighting the need for more extensive data to enhance model generalization. Full article
(This article belongs to the Special Issue Machine Learning Methods for Medicinal Chemistry)
►▼ Show Figures

Figure 1

25 pages, 828 KiB  
Article
Machine Learning Application for Medicinal Chemistry: Colchicine Case, New Structures, and Anticancer Activity Prediction
by Damian Nowak, Adam Huczyński, Rafał Adam Bachorz and Marcin Hoffmann
Pharmaceuticals 2024, 17(2), 173; https://doi.org/10.3390/ph17020173 - 29 Jan 2024
Viewed by 894
Abstract
In the contemporary era, the exploration of machine learning (ML) has gained widespread attention and is being leveraged to augment traditional methodologies in quantitative structure–activity relationship (QSAR) investigations. The principal objective of this research was to assess the anticancer potential of colchicine-based compounds [...] Read more.
In the contemporary era, the exploration of machine learning (ML) has gained widespread attention and is being leveraged to augment traditional methodologies in quantitative structure–activity relationship (QSAR) investigations. The principal objective of this research was to assess the anticancer potential of colchicine-based compounds across five distinct cell lines. This research endeavor ultimately sought to construct ML models proficient in forecasting anticancer activity as quantified by the IC50 value, while concurrently generating innovative colchicine-derived compounds. The resistance index (RI) is computed to evaluate the drug resistance exhibited by LoVo/DX cells relative to LoVo cancer cell lines. Meanwhile, the selectivity index (SI) is computed to determine the potential of a compound to demonstrate superior efficacy against tumor cells compared to its toxicity against normal cells, such as BALB/3T3. We introduce a novel ML system adept at recommending novel chemical structures predicated on known anticancer activity. Our investigation entailed the assessment of inhibitory capabilities across five cell lines, employing predictive models utilizing various algorithms, including random forest, decision tree, support vector machines, k-nearest neighbors, and multiple linear regression. The most proficient model, as determined by quality metrics, was employed to predict the anticancer activity of novel colchicine-based compounds. This methodological approach yielded the establishment of a library encompassing new colchicine-based compounds, each assigned an IC50 value. Additionally, this study resulted in the development of a validated predictive model, capable of reasonably estimating IC50 values based on molecular structure input. Full article
(This article belongs to the Special Issue Machine Learning Methods for Medicinal Chemistry)
►▼ Show Figures

Figure 1

13 pages, 3288 KiB  
Article
Derivation of Highly Predictive 3D-QSAR Models for hERG Channel Blockers Based on the Quantum Artificial Neural Network Algorithm
by Taeho Kim, Kee-Choo Chung and Hwangseo Park
Pharmaceuticals 2023, 16(11), 1509; https://doi.org/10.3390/ph16111509 - 24 Oct 2023
Viewed by 1024
Abstract
The hERG potassium channel serves as an annexed target for drug discovery because the associated off-target inhibitory activity may cause serious cardiotoxicity. Quantitative structure–activity relationship (QSAR) models were developed to predict inhibitory activities against the hERG potassium channel, utilizing the three-dimensional (3D) distribution [...] Read more.
The hERG potassium channel serves as an annexed target for drug discovery because the associated off-target inhibitory activity may cause serious cardiotoxicity. Quantitative structure–activity relationship (QSAR) models were developed to predict inhibitory activities against the hERG potassium channel, utilizing the three-dimensional (3D) distribution of quantum mechanical electrostatic potential (ESP) as the molecular descriptor. To prepare the optimal atomic coordinates of dataset molecules, pairwise 3D structural alignments were carried out in order for the quantum mechanical cross correlation between the template and other molecules to be maximized. This alignment method stands out from the common atom-by-atom matching technique, as it can handle structurally diverse molecules as effectively as chemical derivatives that share an identical scaffold. The alignment problem prevalent in 3D-QSAR methods was ameliorated substantially by dividing the dataset molecules into seven subsets, each of which contained molecules with similar molecular weights. Using an artificial neural network algorithm to find the functional relationship between the quantum mechanical ESP descriptors and the experimental hERG inhibitory activities, highly predictive 3D-QSAR models were derived for all seven molecular subsets to the extent that the squared correlation coefficients exceeded 0.79. Given their simplicity in model development and strong predictability, the 3D-QSAR models developed in this study are expected to function as an effective virtual screening tool for assessing the potential cardiotoxicity of drug candidate molecules. Full article
(This article belongs to the Special Issue Machine Learning Methods for Medicinal Chemistry)
►▼ Show Figures

Figure 1

13 pages, 5770 KiB  
Article
Identification of Potential JNK3 Inhibitors: A Combined Approach Using Molecular Docking and Deep Learning-Based Virtual Screening
by Chenpeng Yao, Zheyuan Shen, Liteng Shen, Kailibinuer Kadier, Jingyi Zhao, Yu Guo, Lei Xu, Ji Cao, Xiaowu Dong and Bo Yang
Pharmaceuticals 2023, 16(10), 1459; https://doi.org/10.3390/ph16101459 - 13 Oct 2023
Cited by 1 | Viewed by 1578
Abstract
JNK3, a member of the MAPK family, plays a pivotal role in mediating cellular responses to stress signals, with its activation implicated in a myriad of inflammatory conditions. While JNK3 holds promise as a therapeutic target for neurodegenerative disorders such as Huntington’s, Parkinson’s, [...] Read more.
JNK3, a member of the MAPK family, plays a pivotal role in mediating cellular responses to stress signals, with its activation implicated in a myriad of inflammatory conditions. While JNK3 holds promise as a therapeutic target for neurodegenerative disorders such as Huntington’s, Parkinson’s, and Alzheimer’s diseases, there remains a gap in the market for effective JNK3 inhibitors. Despite some pan-JNK inhibitors reaching clinical trials, no JNK-targeted therapies have achieved market approval. To bridge this gap, our study introduces a sophisticated virtual screening approach. We begin with an energy-based screening, subsequently integrating a variety of rescoring techniques. These encompass glide docking scores, MM/GBSA, and artificial scoring mechanisms such as DeepDock and advanced Graph Neural Networks. This virtual screening workflow is designed to evaluate and identify potential small-molecule inhibitors with high binding affinity. We have implemented a virtual screening workflow to identify potential candidate molecules. This process has resulted in the selection of ten molecules. Subsequently, these ten molecules have undergone biological activity evaluation to assess their potential efficacy. Impressively, molecule compound 6 surfaced as the most promising, exhibiting a potent kinase inhibitory activity marked by an IC50 of 130.1 nM and a notable reduction in TNF-α release within macrophages. This suggests that compound 6 could potentially serve as an effective inhibitor for the treatment of neuroinflammation and neurodegenerative diseases. The prospect of further medicinal modifications to optimize compound 6 presents a promising avenue for future research and development in this field. Utilizing binding pose metadynamics coupled with molecular dynamics simulations, we delved into the explicit binding mode of compound 6 to JNK3. Such insights pave the way for refined drug development strategies. Collectively, our results underscore the efficacy of the hybrid virtual screening workflow in the identification of robust JNK3 inhibitors, holding promise for innovative treatments against neuroinflammation and neurodegenerative disorders. Full article
(This article belongs to the Special Issue Machine Learning Methods for Medicinal Chemistry)
►▼ Show Figures

Graphical abstract

11 pages, 1855 KiB  
Article
Large-Scale Predictions of Compound Potency with Original and Modified Activity Classes Reveal General Prediction Characteristics and Intrinsic Limitations of Conventional Benchmarking Calculations
by Tiago Janela and Jürgen Bajorath
Pharmaceuticals 2023, 16(4), 530; https://doi.org/10.3390/ph16040530 - 2 Apr 2023
Cited by 3 | Viewed by 1576
Abstract
Predicting compound potency is a major task in computational medicinal chemistry, for which machine learning is often applied. This study systematically predicted compound potency values for 367 target-based compound activity classes from medicinal chemistry using a preferred machine learning approach and simple control [...] Read more.
Predicting compound potency is a major task in computational medicinal chemistry, for which machine learning is often applied. This study systematically predicted compound potency values for 367 target-based compound activity classes from medicinal chemistry using a preferred machine learning approach and simple control methods. The predictions produced unexpectedly similar results for different classes and comparably high accuracy for machine learning and simple control models. Based on these findings, the influence of different data set modifications on relative prediction accuracies was explored, including potency range balancing, removal of nearest neighbors, and analog series-based compound partitioning. The predictions were surprisingly resistant to these modifications, leading to only small error margin increases. These findings also show that conventional benchmark settings are unsuitable for directly comparing potency prediction methods. Full article
(This article belongs to the Special Issue Machine Learning Methods for Medicinal Chemistry)
►▼ Show Figures

Figure 1

23 pages, 8340 KiB  
Article
Identification of Novel Arachidonic Acid 15-Lipoxygenase Inhibitors Based on the Bayesian Classifier Model and Computer-Aided High-Throughput Virtual Screening
by Yinglin Liao, Peng Cao and Lianxiang Luo
Pharmaceuticals 2022, 15(11), 1440; https://doi.org/10.3390/ph15111440 - 20 Nov 2022
Cited by 4 | Viewed by 2131
Abstract
Ferroptosis is an iron-dependent lipid peroxidative form of cell death that is distinct from apoptosis and necrosis. ALOX15, also known as arachidonic acid 15-lipoxygenase, promotes ferroptosis by converting intracellular unsaturated lipids into oxidized lipid intermediates and is an important ferroptosis target. In this [...] Read more.
Ferroptosis is an iron-dependent lipid peroxidative form of cell death that is distinct from apoptosis and necrosis. ALOX15, also known as arachidonic acid 15-lipoxygenase, promotes ferroptosis by converting intracellular unsaturated lipids into oxidized lipid intermediates and is an important ferroptosis target. In this study, a naive Bayesian machine learning classifier with a structure-based, high-throughput screening approach and a molecular docking program were combined to screen for three compounds with excellent target-binding potential. In the absorption, distribution, metabolism, excretion, and toxicity characterization, three candidate molecules were predicted to exhibit drug-like properties. The subsequent molecular dynamics simulations confirmed their stable binding to the targets. The findings indicated that the compounds exhibited excellent potential ALOX15 inhibitor capacity, thereby providing novel candidates for the treatment of inflammatory ischemia-related diseases caused by ferroptosis. Full article
(This article belongs to the Special Issue Machine Learning Methods for Medicinal Chemistry)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-6
Back to TopTop