A PHP Error was encountered

Severity: Warning

Message: fopen(/var/lib/php/sessions/ci_sessionr2d50kr5tvruhf12h6j81lpt5nr17i74): Failed to open stream: No space left on device

Filename: drivers/Session_files_driver.php

Line Number: 177

Backtrace:

File: /var/www/html/index.php
Line: 316
Function: require_once

A PHP Error was encountered

Severity: Warning

Message: session_start(): Failed to read session data: user (path: /var/lib/php/sessions)

Filename: Session/Session.php

Line Number: 137

Backtrace:

File: /var/www/html/index.php
Line: 316
Function: require_once

Deep Generative Models in Drug Molecule Generation. | LitMetric

Deep Generative Models in Drug Molecule Generation.

J Chem Inf Model

School of Software, Shandong University, Jinan 250100, China.

Published: April 2024

AI Article Synopsis

  • New drug discovery methods are crucial for improving human health, but traditional approaches are often time-consuming and costly.
  • Recent advancements in artificial intelligence, particularly deep generative models, show great promise in efficiently generating drug-like molecules with desirable properties.
  • This study reviews progress in molecule generation, highlights current challenges in the field, and suggests future research directions to enhance drug discovery efforts.

Article Abstract

The discovery of new drugs has important implications for human health. Traditional methods for drug discovery rely on experiments to optimize the structure of lead molecules, which are time-consuming and high-cost. Recently, artificial intelligence has exhibited promising and efficient performance for drug-like molecule generation. In particular, deep generative models achieve great success in generation of drug-like molecules with desired properties, showing massive potential for novel drug discovery. In this study, we review the recent progress of molecule generation using deep generative models, mainly focusing on molecule representations, public databases, data processing tools, and advanced artificial intelligence based molecule generation frameworks. In particular, we present a comprehensive comparison of state-of-the-art deep generative models for molecule generation and a summary of commonly used molecular design strategies. We identify research gaps and challenges of molecule generation such as the need for better databases, missing 3D information in molecular representation, and the lack of high-precision evaluation metrics. We suggest future directions for molecular generation and drug discovery.

Download full-text PDF

Source
http://dx.doi.org/10.1021/acs.jcim.3c01496DOI Listing

Publication Analysis

Top Keywords

molecule generation
24
deep generative
16
generative models
16
drug discovery
12
generation
8
artificial intelligence
8
generation deep
8
molecule
7
deep
4
models
4

Similar Publications

Assembly and Functionality of 2D Protein Arrays.

Adv Sci (Weinh)

March 2025

CAS Key Laboratory of Nano-Bio Interface, Division of Nanobiomedicine and i-Lab, Suzhou Institute of Nano-Tech and Nano-Bionics, Chinese Academy of Sciences, Suzhou, 215123, China.

Among the unique classes of 2D nanomaterials, 2D protein arrays garner increasing attention due to their remarkable structural stability, exceptional physiochemical properties, and tunable electronic and mechanical attributes. The interest in mimicking and surpassing the precise architecture and advanced functionality of natural protein systems drives the field of 2D protein assembly toward the development of sophisticated functional materials. Recent advancements deepen the understanding of the fundamental principles governing 2D protein self-assembly, accelerating the creation of novel functional biomaterials.

View Article and Find Full Text PDF

The growing demand for sustainable and eco-friendly alternatives in bioprocessing, healthcare, and manufacturing has stimulated significant interest in Bacillus subtilis surface display technology. This innovative platform, leveraging both spore and vegetative cell forms, provides exceptional versatility for a wide spectrum of applications, spanning from green technologies to advanced biomedical innovations. The robustness of spores and the metabolic activity of vegetative cells enable efficient enzyme immobilization, biocatalysis, and biosensor development, facilitating bioremediation, pollutant degradation, and renewable energy generation.

View Article and Find Full Text PDF

CKMT1 deficiency contributes to mitochondrial dysfunction and promotes intestinal epithelial cell apoptosis via reverse electron transfer-derived ROS in colitis.

Cell Death Dis

March 2025

National Clinical Research Center for Digestive Diseases, Department of Gastroenterology, Changhai Hospital, Naval Medical University, Shanghai, China.

Mitochondrial dysfunction contributes to the pathogenesis of ulcerative colitis (UC). As a mitochondrial isozyme of creatine kinases, which control energy metabolism, CKMT1 is thought to be a critical molecule in biological processes. However, the specific role of CKMT1 in intestinal inflammation remains largely unknown.

View Article and Find Full Text PDF

Artificial gut Simulator. A scheme to predict intestinal and plasma concentration-time profiles of a weakly basic BCS-II drug, dipyridamole.

Eur J Pharm Biopharm

March 2025

Department of Pharmaceutics, University of Minnesota, Minneapolis, MN 55455, USA; Department of Biomedical Engineering, University of Minnesota, Minneapolis, MN 55455, USA. Electronic address:

The objective of this study was to develop a scheme to predict intestinal and plasma concentration-time profiles of the weakly basic BCS-II drug, Dipyridamole (DPD), using an Artificial Gut Simulator (AGS) integrated with a compartment-based disposition model. In vivo data for this study was obtained from previously published literature. A 3-compartment disposition model was developed using the plasma concentration-time profile of DPD following an intravenous bolus dose.

View Article and Find Full Text PDF

Dual targeting of the mitochondrial Lon peptidase 1 and the chymotrypsin-like proteasome activity as a potential therapeutic strategy in malignant astrocytoma models.

Pharmacol Res

March 2025

Department of Experimental Pathology & Laboratory Medicine, University of California Irvine, Irvine, CA, USA; Department of Neurology, University of California Irvine, Irvine, CA, USA; Chao Family Comprehensive Cancer Center, University of California Irvine, Irvine, CA, USA. Electronic address:

Malignant astrocytomas are aggressive primary brain tumors characterized by extensive hypoxia-induced, mitochondria-dependent changes such as altered respiration, increased chymotrypsin-like (CT-L) proteasome activity, decreased apoptosis, drug resistance, stemness, and increased invasiveness. Mitochondrial Lon Peptidase 1 (LonP1) overexpression and increased CT-L proteasome activity are biomarkers of an aggressive high-grade phenotype and found to be associated with recurrence and poor patient survival. In preclinical models, small molecule agents targeting either LonP1 or the proteasome CT-L activity have anti-astrocytoma activity.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!