Chemoinformatics Approaches to Structure- and Ligand-Based Drug Design, Volume II

Advances in computer hardware and the availability of high-performance supercomputing platforms and parallel computing, along with artificial intelligence methods are successfully complementing traditional approaches in medicinal chemistry. In particular, machine learning is gaining importance with the growth of the available data collections. One of the critical areas where this methodology can be successfully applied is in the development of new antibacterial agents. The latter is essential because of the high attrition rates in new drug discovery, both in industry and in academic research programs. Scientific involvement in this area is even more urgent as antibacterial drug resistance becomes a public health concern worldwide and pushes us increasingly into the post-antibiotic era. In this review, we focus on the latest machine learning approaches used in the discovery of new antibacterial agents and targets, covering both small molecules and antibacterial peptides. For the benefit of the reader, we summarize all applied machine learning approaches and available databases useful for the design of new antibacterial agents and address the current shortcomings.

9,777 views

39 citations

The representation of docked lead compounds and drug ((A) T6649932, (B) ST088474, (C) T5923555, (D) T5923531, (E) T6763842, and (F) ruxolitinib) present inside the ATP-binding site of JAK1 after molecular docking.

Original Research

21 April 2022

Identification of Potent and Selective JAK1 Lead Compounds Through Ligand-Based Drug Design Approaches

Sathya Babu

, 4 more and

Thirumurthy Madhavan

3,398 views

21 citations

Bar plots showing the distribution of the predicted classes for the different ADMET endpoints. EPA1 corresponds to the (LD50 ≤ 50 mg/kg) the highest toxicity category. EPA2 (moderately toxic) includes chemicals with 50 < LD50 ≤ 500 mg/kg. EPA3 (slightly toxic) includes chemicals with 500 < LD50 ≤ 5,000 mg/kg. Safe chemicals (LD50 > 5,000 mg/kg) are included in EPA4. Here, the color green is used to indicate compounds that are better suited for further study.

Technology and Code

26 April 2022

Drugsniffer: An Open Source Workflow for Virtually Screening Billions of Molecules for Binding Affinity to Protein Targets

Vishwesh Venkatraman

, 6 more and

Amitava Roy

5,774 views

12 citations

Original Research

29 June 2022

Probabilistic Pocket Druggability Prediction via One-Class Learning

Riccardo Aguti

, 3 more and

Andrea Cavalli

4,551 views

8 citations

Original Research

03 May 2022

Structure-Based Design of 2-Aminopurine Derivatives as CDK2 Inhibitors for Triple-Negative Breast Cancer

Hanzhi Liang

, 5 more and

Xuben Hou

3,744 views

4 citations

Original Research

18 March 2022

A Set of Experimentally Validated Decoys for the Human CC Chemokine Receptor 7 (CCR7) Obtained by Virtual Screening

Matic Proj

, 9 more and

Stanislav Gobec

2,932 views

3 citations

Original Research

11 March 2022

Pocket2Drug: An Encoder-Decoder Deep Neural Network for the Target-Based Drug Design

Wentao Shi

, 4 more and

Michal Brylinski

Examples of molecules generated by Pocket2Drug for a binding site in MSK1. (A) The label ligand, AMP-PNP. (B–F) Molecules constructed by Pocket2Drug with maximum common substructures to the label ligand highlighted in cyan. (G) Molecule shown in B (ice blue) docked to the binding site in MSK1 (orange).

Computational modeling is an essential component of modern drug discovery. One of its most important applications is to select promising drug candidates for pharmacologically relevant target proteins. Because of continuing advances in structural biology, putative binding sites for small organic molecules are being discovered in numerous proteins linked to various diseases. These valuable data offer new opportunities to build efficient computational models predicting binding molecules for target sites through the application of data mining and machine learning. In particular, deep neural networks are powerful techniques capable of learning from complex data in order to make informed drug binding predictions. In this communication, we describe Pocket2Drug, a deep graph neural network model to predict binding molecules for a given a ligand binding site. This approach first learns the conditional probability distribution of small molecules from a large dataset of pocket structures with supervised training, followed by the sampling of drug candidates from the trained model. Comprehensive benchmarking simulations show that using Pocket2Drug significantly improves the chances of finding molecules binding to target pockets compared to traditional drug selection procedures. Specifically, known binders are generated for as many as 80.5% of targets present in the testing set consisting of dissimilar data from that used to train the deep graph neural network model. Overall, Pocket2Drug is a promising computational approach to inform the discovery of novel biopharmaceuticals.

6,394 views

15 citations

The user may request the measures between two protein structures or within a list of pairs of proteins. Also, the protein structures can be both experimentally solved (downloaded from Protein Data Bank) or homology models (uploaded by the user).

Original Research

18 March 2022

A New Strategy for Multitarget Drug Discovery/Repositioning Through the Identification of Similar 3D Amino Acid Patterns Among Proteins Structures: The Case of Tafluprost and its Effects on Cardiac Ion Channels

Alejandro Valdés-Jiménez

, 6 more and

Gabriel Núñez-Vivanco

2,628 views

6 citations

Visualization of selected ML algorithms: (A) k-nearest neighbor, (B) decision tree, (C) hyperplane with the highest separation margin constructed within the support vector machines algorithm implementation, (D) data transformation to the space, in which they are linearly separable with the use of the kernel function.

Review

10 March 2022

From Data to Knowledge: Systematic Review of Tools for Automatic Analysis of Molecular Dynamics Output

Hanna Baltrukevich

and

Sabina Podlewska

4,292 views

6 citations

Original Research

10 March 2022

Limits of Prediction for Machine Learning in Drug Discovery

Modest von Korff

and

Thomas Sander

3,013 views

6 citations

Class A GPCRs. The structures of the receptors marked with red dots have already been solved experimentally (Kooistra et al., 2021).

Review

09 March 2022

The Impact of the Secondary Binding Pocket on the Pharmacology of Class A GPCRs

Attila Egyed

, 1 more and

György M. Keserű

8,794 views

20 citations

Technology and Code

21 February 2022

Introduction to the BioChemical Library (BCL): An Application-Based Open-Source Toolkit for Integrated Cheminformatics and Machine Learning in Computer-Aided Drug Discovery

Benjamin P. Brown

, 8 more and

Jens Meiler

The BioChemical Library (BCL) cheminformatics toolkit is an application-based academic open-source software package designed to integrate traditional small molecule cheminformatics tools with machine learning-based quantitative structure-activity/property relationship (QSAR/QSPR) modeling. In this pedagogical article we provide a detailed introduction to core BCL cheminformatics functionality, showing how traditional tasks (e.g., computing chemical properties, estimating druglikeness) can be readily combined with machine learning. In addition, we have included multiple examples covering areas of advanced use, such as reaction-based library design. We anticipate that this manuscript will be a valuable resource for researchers in computer-aided drug discovery looking to integrate modular cheminformatics and machine learning tools into their pipelines.

8,526 views

17 citations