molecules-logo

Journal Browser

Journal Browser

AI in Drug Design

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

Deadline for manuscript submissions: closed (30 April 2020) | Viewed by 20671

Special Issue Editor


E-Mail Website1 Website2
Guest Editor
San Diego Supercomputer Center, Moores Cancer Center, Dept. of Neurosciences: UC San Diego, La Jolla, CA, USA
Interests: structural biology; bioinformatics; personalized drug treatment; artificial intelligence; machine learning (ML); deep learning (DL)

Special Issue Information

Dear Colleagues,

Using AI tools in computational drug design has become very popular. Among the reasons for this are the incredible improved computational power and the achievements in the AI technology. Currently, almost all pharmaceutical companies use AI tools for drug design. In the previous era, when AI was not available, the main time-consuming phase of the drug design process consisted in carrying out numerical experiments exploring all possible substitutions in drug-lead candidates. This is why the exploration of the possible variants of drug compounds was limited. The most promising compounds were identified for further study, but this often led to multimillion losses when the selected drugs failed to produce therapeutic effects in high-level clinical trials. I think that the AI approach does not exclude the experimental validation of possible drug candidates. On the opposite, it makes such validation much more valuable, because an AI system can categorize a large set of possible drug-candidate compounds in several classes and suggest a small number of representative drug candidates from these classes for experimental testing. This Special Issue aims to provide a forum for the most interesting findings in the area of AI application to drug design.

Dr. Igor Tsigenly
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. 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

  • structural biology
  • bioinformatics
  • computational drug design
  • personalized drug treatment
  • artificial intelligence
  • machine learning (ML)
  • deep learning (DL)

Published Papers (5 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

26 pages, 6416 KiB  
Article
Prediction of Premature Termination Codon Suppressing Compounds for Treatment of Duchenne Muscular Dystrophy Using Machine Learning
by Kate Wang, Eden L. Romm, Valentina L. Kouznetsova and Igor F. Tsigelny
Molecules 2020, 25(17), 3886; https://doi.org/10.3390/molecules25173886 - 26 Aug 2020
Cited by 1 | Viewed by 2340
Abstract
A significant percentage of Duchenne muscular dystrophy (DMD) cases are caused by premature termination codon (PTC) mutations in the dystrophin gene, leading to the production of a truncated, non-functional dystrophin polypeptide. PTC-suppressing compounds (PTCSC) have been developed in order to restore protein translation [...] Read more.
A significant percentage of Duchenne muscular dystrophy (DMD) cases are caused by premature termination codon (PTC) mutations in the dystrophin gene, leading to the production of a truncated, non-functional dystrophin polypeptide. PTC-suppressing compounds (PTCSC) have been developed in order to restore protein translation by allowing the incorporation of an amino acid in place of a stop codon. However, limitations exist in terms of efficacy and toxicity. To identify new compounds that have PTC-suppressing ability, we selected and clustered existing PTCSC, allowing for the construction of a common pharmacophore model. Machine learning (ML) and deep learning (DL) models were developed for prediction of new PTCSC based on known compounds. We conducted a search of the NCI compounds database using the pharmacophore-based model and a search of the DrugBank database using pharmacophore-based, ML and DL models. Sixteen drug compounds were selected as a consensus of pharmacophore-based, ML, and DL searches. Our results suggest notable correspondence of the pharmacophore-based, ML, and DL models in prediction of new PTC-suppressing compounds. Full article
(This article belongs to the Special Issue AI in Drug Design)
Show Figures

Figure 1

11 pages, 1601 KiB  
Article
A Pilot Study of Multi-Input Recurrent Neural Networks for Drug-Kinase Binding Prediction
by Kristy Carpenter, Alexander Pilozzi and Xudong Huang
Molecules 2020, 25(15), 3372; https://doi.org/10.3390/molecules25153372 - 24 Jul 2020
Cited by 4 | Viewed by 2226
Abstract
The use of virtual drug screening can be beneficial to research teams, enabling them to narrow down potentially useful compounds for further study. A variety of virtual screening methods have been developed, typically with machine learning classifiers at the center of their design. [...] Read more.
The use of virtual drug screening can be beneficial to research teams, enabling them to narrow down potentially useful compounds for further study. A variety of virtual screening methods have been developed, typically with machine learning classifiers at the center of their design. In the present study, we created a virtual screener for protein kinase inhibitors. Experimental compound–target interaction data were obtained from the IDG-DREAM Drug-Kinase Binding Prediction Challenge. These data were converted and fed as inputs into two multi-input recurrent neural networks (RNNs). The first network utilized data encoded in one-hot representation, while the other incorporated embedding layers. The models were developed in Python, and were designed to output the IC50 of the target compounds. The performance of the models was assessed primarily through analysis of the Q2 values produced from runs of differing sample and epoch size; recorded loss values were also reported and graphed. The performance of the models was limited, though multiple changes are proposed for potential improvement of a multi-input recurrent neural network-based screening tool. Full article
(This article belongs to the Special Issue AI in Drug Design)
Show Figures

Graphical abstract

18 pages, 3195 KiB  
Article
Repurposing Zileuton as a Depression Drug Using an AI and In Vitro Approach
by Norwin Kubick, Marta Pajares, Ioana Enache, Gina Manda and Michel-Edwar Mickael
Molecules 2020, 25(9), 2155; https://doi.org/10.3390/molecules25092155 - 5 May 2020
Cited by 9 | Viewed by 4378
Abstract
Repurposing drugs to target M1 macrophages inflammatory response in depression constitutes a bright alternative for commonly used antidepressants. Depression is a significant type of mood disorder, where patients suffer from pathological disturbances associated with a proinflammatory M1 macrophage phenotype. Presently, the most commonly [...] Read more.
Repurposing drugs to target M1 macrophages inflammatory response in depression constitutes a bright alternative for commonly used antidepressants. Depression is a significant type of mood disorder, where patients suffer from pathological disturbances associated with a proinflammatory M1 macrophage phenotype. Presently, the most commonly used antidepressants such as Zoloft and Citalopram can reduce inflammation, but suffer from dangerous side effects without offering specificity toward macrophages. We employed a new strategy for drug repurposing based on the integration of RNA-seq analysis and text mining using deep neural networks. Our system employs a Google semantic AI universal encoder to compute sentences embedding. Sentences similarity is calculated using a sorting function to identify drug compounds. Then sentence relevance is computed using a custom-built convolution differential network. Our system highlighted the NRF2 pathway as a critical drug target to reprogram M1 macrophage response toward an anti-inflammatory profile (M2). Using our approach, we were also able to predict that lipoxygenase inhibitor drug zileuton could modulate NRF2 pathway in vitro. Taken together, our results indicate that reorienting zileuton usage to modulate M1 macrophages could be a novel and safer therapeutic option for treating depression. Full article
(This article belongs to the Special Issue AI in Drug Design)
Show Figures

Figure 1

18 pages, 8709 KiB  
Article
How Sure Can We Be about ML Methods-Based Evaluation of Compound Activity: Incorporation of Information about Prediction Uncertainty Using Deep Learning Techniques
by Igor Sieradzki, Damian Leśniak and Sabina Podlewska
Molecules 2020, 25(6), 1452; https://doi.org/10.3390/molecules25061452 - 23 Mar 2020
Cited by 3 | Viewed by 2747
Abstract
A great variety of computational approaches support drug design processes, helping in selection of new potentially active compounds, and optimization of their physicochemical and ADMET properties. Machine learning is a group of methods that are able to evaluate in relatively short time enormous [...] Read more.
A great variety of computational approaches support drug design processes, helping in selection of new potentially active compounds, and optimization of their physicochemical and ADMET properties. Machine learning is a group of methods that are able to evaluate in relatively short time enormous amounts of data. However, the quality of machine-learning-based prediction depends on the data supplied for model training. In this study, we used deep neural networks for the task of compound activity prediction and developed dropout-based approaches for estimating prediction uncertainty. Several types of analyses were performed: the relationships between the prediction error, similarity to the training set, prediction uncertainty, number and standard deviation of activity values were examined. It was tested whether incorporation of information about prediction uncertainty influences compounds ranking based on predicted activity and prediction uncertainty was used to search for the potential errors in the ChEMBL database. The obtained outcome indicates that incorporation of information about uncertainty of compound activity prediction can be of great help during virtual screening experiments. Full article
(This article belongs to the Special Issue AI in Drug Design)
Show Figures

Figure 1

Review

Jump to: Research

25 pages, 2268 KiB  
Review
Relevant Applications of Generative Adversarial Networks in Drug Design and Discovery: Molecular De Novo Design, Dimensionality Reduction, and De Novo Peptide and Protein Design
by Eugene Lin, Chieh-Hsin Lin and Hsien-Yuan Lane
Molecules 2020, 25(14), 3250; https://doi.org/10.3390/molecules25143250 - 16 Jul 2020
Cited by 42 | Viewed by 8155
Abstract
A growing body of evidence now suggests that artificial intelligence and machine learning techniques can serve as an indispensable foundation for the process of drug design and discovery. In light of latest advancements in computing technologies, deep learning algorithms are being created during [...] Read more.
A growing body of evidence now suggests that artificial intelligence and machine learning techniques can serve as an indispensable foundation for the process of drug design and discovery. In light of latest advancements in computing technologies, deep learning algorithms are being created during the development of clinically useful drugs for treatment of a number of diseases. In this review, we focus on the latest developments for three particular arenas in drug design and discovery research using deep learning approaches, such as generative adversarial network (GAN) frameworks. Firstly, we review drug design and discovery studies that leverage various GAN techniques to assess one main application such as molecular de novo design in drug design and discovery. In addition, we describe various GAN models to fulfill the dimension reduction task of single-cell data in the preclinical stage of the drug development pipeline. Furthermore, we depict several studies in de novo peptide and protein design using GAN frameworks. Moreover, we outline the limitations in regard to the previous drug design and discovery studies using GAN models. Finally, we present a discussion of directions and challenges for future research. Full article
(This article belongs to the Special Issue AI in Drug Design)
Show Figures

Figure 1

Back to TopTop