Prediction on drug-target interaction has always been a crucial link for drug discovery and repositioning, which have witnessed tremendous progress in recent years. Despite many efforts made, the existing representation learning or feature generation approaches of both drugs and proteins remain complicated as well as in high dimension. In addition, it is difficult for current methods to extract local important residues from sequence information while remaining focused on global structure. At the same time, massive data is not always easily accessible, which makes model learning from small datasets imminent. As a result, we propose an end-to-end learning model with SUPD and SUDD methods to encode drugs and proteins, which not only leave out the complicated feature extraction process but also greatly reduce the dimension of the embedding matrix. Meanwhile, we use a multi-view strategy with a transformer to extract local important residues of proteins for better representation learning. Finally, we evaluate our model on the BindingDB dataset in comparisons with different state-of-the-art models from comprehensive indicators. In results of 100% BindingDB, our AUC, AUPR, ACC, and F1-score reached 90.9%, 89.8%, 84.2%, and 84.3% respectively, which successively exceed the average values of other models by 2.2%, 2.3%, 2.6%, and 2.6%. Moreover, our model also generally surpasses their performance on 30% and 50% BindingDB datasets.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9138327PMC
http://dx.doi.org/10.3390/biom12050644DOI Listing

Publication Analysis

Top Keywords

drug-target interaction
8
multi-view strategy
8
representation learning
8
drugs proteins
8
extract local
8
local residues
8
multi-transdti transformer
4
transformer drug-target
4
interaction prediction
4
prediction based
4

Similar Publications

Epidermal melanocytes form synaptic-like contacts with cutaneous nerve fibers, but the functional outcome of these connections remains elusive. In this pilot study we used our fully humanized re-innervated skin organ culture model to investigate melanocyte-nerve fiber interactions in UV-B-induced melanogenesis. UV-B-irradiation significantly enhanced melanin content and tyrosinase activity in re-innervated skin compared to non-innervated controls, indicating that neuronal presence is essential for exacerbating pigmentation upon UV-B irradiation in long-term culture.

View Article and Find Full Text PDF

TransferBAN-Syn: a transfer learning-based algorithm for predicting synergistic drug combinations against echinococcosis.

Front Genet

January 2025

Key Laboratory of Intelligent Computing and Signal Processing, School of Artificial Intelligence, Anhui University, Hefei, China.

Echinococcosis is a zoonotic parasitic disease caused by the larvae of echinococcus tapeworms infesting the human body. Drug combination therapy is highly valued for the treatment of echinococcosis because of its potential to overcome resistance and enhance the response to existing drugs. Traditional methods of identifying drug combinations via biological experimentation is costly and time-consuming.

View Article and Find Full Text PDF

Existing chemotherapeutic approaches against refractory cancers are ineffective due to off-target effects, inefficient delivery, and inadequate accumulation of anticancer drugs at the tumor site, which causes limited efficiency of drug treatment and toxicity to neighboring healthy cells. The development of nano-based drug delivery systems (DDSs) with the goal of delivering desired therapeutic doses to the diseased cells and has already proven to be a promising strategy to address these challenges. Our study focuses on achieving an efficient tumor-targeted delivery of a combination of drugs for therapeutic benefits by developing a versatile DDS by following a simple one-step chemical approach.

View Article and Find Full Text PDF

Exosome-based targeted delivery of NF-κB ameliorates age-related neuroinflammation in the aged mouse brain.

Exp Mol Med

January 2025

Department of Physiology, Inflammation-Cancer Microenvironment Research Center, Ewha Womans University College of Medicine, Seoul, 07804, Republic of Korea.

Neuroinflammation, a significant contributor to various neurodegenerative diseases, is strongly associated with the aging process; however, to date, no efficacious treatments for neuroinflammation have been developed. In aged mouse brains, the number of infiltrating immune cells increases, and the key transcription factor associated with increased chemokine levels is nuclear factor kappa B (NF-κB). Exosomes are potent therapeutics or drug delivery vehicles for various materials, including proteins and regulatory genes, to target cells.

View Article and Find Full Text PDF

Pillar[n]arene-Based Supramolecular Nanodrug Delivery Systems for Cancer Therapy.

ChemMedChem

January 2025

School of Chemistry and Chemical Engineering, Guangxi University, Nanning, 530004, Guangxi, P. R. China.

Macrocyclic supramolecular materials play an important role in encapsulating anticancer drugs to improve the anticancer efficiency and reduce the toxicity to normal tissues through host-guest interactions. Among them, pillar[n]arenes, as an emerging class of supramolecular macrocyclic compounds, have attracted increasing attention in drug delivery and drug-controlled release due to their high biocompatibility, excellent host-guest chemistry, and simplicity of modification. In this review, we summarize the research progress of pillar[n]arene-based supramolecular nanodrug delivery systems (SNDs) in recent years in the field of tumor therapy, including drug-controlled release, imaging diagnostics and therapeutic modalities.

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!