Background: Identification of drug-target interactions is an indispensable part of drug discovery. While conventional shallow machine learning and recent deep learning methods based on chemogenomic properties of drugs and target proteins have pushed this prediction performance improvement to a new level, these methods are still difficult to adapt to novel structures. Alternatively, large-scale biological and pharmacological data provide new ways to accelerate drug-target interaction prediction.

Methods: Here, we propose DrugMAN, a deep learning model for predicting drug-target interaction by integrating multiplex heterogeneous functional networks with a mutual attention network (MAN). DrugMAN uses a graph attention network-based integration algorithm to learn network-specific low-dimensional features for drugs and target proteins by integrating four drug networks and seven gene/protein networks collected by a certain screening conditions, respectively. DrugMAN then captures interaction information between drug and target representations by a mutual attention network to improve drug-target prediction.

Results: DrugMAN achieved the best performance compared with cheminformation-based methods SVM, RF, DeepPurpose and network-based deep learing methods DTINet and NeoDT in four different scenarios, especially in real-world scenarios. Compared with SVM, RF, deepurpose, DTINet, and NeoDT, DrugMAN showed the smallest decrease in AUROC, AUPRC, and F1-Score from warm-start to Both-cold scenarios. This result is attributed to DrugMAN's learning from heterogeneous data and indicates that DrugMAN has a good generalization ability. Taking together, DrugMAN spotlights heterogeneous information to mine drug-target interactions and can be a powerful tool for drug discovery and drug repurposing.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11577831PMC
http://dx.doi.org/10.1186/s12859-024-05976-3DOI Listing

Publication Analysis

Top Keywords

drug-target interaction
12
mutual attention
12
attention network
12
drug-target interactions
8
drug discovery
8
deep learning
8
drugs target
8
target proteins
8
dtinet neodt
8
drugman
7

Similar Publications

As a chronic gynecological disease, endometriosis is defined as the implantation of endometrial glands as well as stroma outside the uterine cavity. Proliferation is a major pathophysiology in endometriosis. Previous studies demonstrated a hormone named melatonin, which is mainly produced by the pineal gland, exerts a therapeutic impact on endometriosis.

View Article and Find Full Text PDF

Molecular insights into kinetic stabilization of amorphous solid dispersion of pharmaceuticals.

Phys Chem Chem Phys

December 2024

Department of Physical Chemistry, University of Chemistry and Technology Prague, Technická 5, CZ-166 28 Prague 6, Praha, Czech Republic.

Poor aqueous solubility of crystalline active pharmaceutical ingredients (APIs) restricts their bioavailability. Amorphous solid dispersions with biocompatible polymer excipients offer a solution to overcome this problem, potentially enabling a broader use of many drug candidate molecules. This work addresses various aspects of the design of a suitable combination of an API and a polymer to form such a binary solid dispersion.

View Article and Find Full Text PDF

Personalized Multi-Epitope Nanovaccine Unlocks B Cell-Mediated Multiple Pathways of Antitumor Immunity.

Adv Mater

December 2024

State Key Laboratory of Drug Research & Center of Pharmaceutics, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, Shanghai, 201203, China.

B lymphocytes have emerged as an important immune-regulating target. Inoculation with tumor cell membrane-derived vaccines is a promising strategy to activate B cells, yet their efficiency is limited due to lack of costimulatory molecules. To amplify B cell responses against tumor, herein, a spatiotemporally-synchronized antigen-adjuvant integrated nanovaccine, termed as CM-CpG-aCD40, is constructed by conjugating the immune stimulative CpG oligonucleotide and the anti-CD40 antibody (aCD40) onto the membrane vesicles derived from triple negative breast cancer cells.

View Article and Find Full Text PDF

Supramolecular nanotherapeutics based on cucurbiturils.

J Nanobiotechnology

December 2024

Department of Toxicology and Sanitary Chemistry, School of Public Health, Capital Medical University, Beijing, 100069, People's Republic of China.

Polymeric biomaterials have important applications in aiding clinical disease treatment, including drug delivery, bioimaging, and tissue engineering. Currently, conventional tumor chemotherapy faces obstacles such as poor solubility/stability, inability to target, and uncontrolled drug release in clinical trials, for which the emergence of supramolecular material therapeutics combining non-covalent interactions with conventional therapies is a very promising candidate. Due to their molecular recognition abilities with a range of biomolecules, cucurbit[n]uril (CB[n]), a type of macrocyclic receptors with robust backbones, hydrophobic cavities, and carbonyl-binding channels, have garnered a lot of attention.

View Article and Find Full Text PDF

Nanomaterials have been shown to promote crop growth, yield and stress resistance. Carbon nanosol (CNS), a type of nanomaterial, is used to regulate tobacco shoot and root growth. However, information about the application of CNS to crop plants, especially tobacco, is still limited.

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!