Exploring chemical space for lead identification by propagating on chemical similarity network.

Comput Struct Biotechnol J

AIGENDRUG CO., LTD., Gwanak-ro 1, Gwanak-gu, Seoul, 08826, South Korea.

Published: August 2023

Motivation: Lead identification is a fundamental step to prioritize candidate compounds for downstream drug discovery process. Machine learning (ML) and deep learning (DL) approaches are widely used to identify lead compounds using both chemical property and experimental information. However, ML or DL methods rarely consider compound similarity information directly since ML and DL models use abstract representation of molecules for model construction. Alternatively, data mining approaches are also used to explore chemical space with drug candidates by screening undesirable compounds. A major challenge for data mining approaches is to develop efficient data mining methods that search large chemical space for desirable lead compounds with low false positive rate.

Results: In this work, we developed a network propagation (NP) based data mining method for lead identification that performs search on an ensemble of chemical similarity networks. We compiled 14 fingerprint-based similarity networks. Given a target protein of interest, we use a deep learning-based drug target interaction model to narrow down compound candidates and then we use network propagation to prioritize drug candidates that are highly correlated with drug activity score such as IC. In an extensive experiment with BindingDB, we showed that our approach successfully discovered intentionally unlabeled compounds for given targets. To further demonstrate the prediction power of our approach, we identified 24 candidate leads for CLK1. Two out of five synthesizable candidates were experimentally validated in binding assays. In conclusion, our framework can be very useful for lead identification from very large compound databases such as ZINC.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10480321PMC
http://dx.doi.org/10.1016/j.csbj.2023.08.016DOI Listing

Publication Analysis

Top Keywords

lead identification
16
data mining
16
chemical space
12
chemical similarity
8
lead compounds
8
mining approaches
8
drug candidates
8
network propagation
8
similarity networks
8
lead
6

Similar Publications

Outcomes of segmentectomy versus lobectomy in adults with non-cystic fibrosis bronchiectasis.

J Bras Pneumol

January 2025

. Departamento de Cirurgia Torácica, Instituto do Coracao, Hospital das Clínicas HCFMUSP, Faculdade de Medicina, Universidade de São Paulo, São Paulo, SP, BR.

Objective: Surgical resection remains the gold standard treatment for bronchiectasis in patients who present with hemoptysis or suppuration, as well as in those who do not respond to clinical treatment. We sought to investigate the efficacy of sublobar resection (segmentectomy) and compare it with that of lobar resection (lobectomy) in patients with non-cystic fibrosis bronchiectasis.

Methods: Patients undergoing lobectomy or segmentectomy between 2019 and 2023 were included in the study.

View Article and Find Full Text PDF

In contemporary globalised societies, global awareness and identification, as well as local and regional identifications (other than national identity), may all become increasingly important for guiding people's sense of belonging and purpose and in turn their self-concept. As the world has become increasingly interconnected, people increasingly identify with various cultures and worldviews within both local and global contexts. Attempts to reconcile these multiple cultural identities can lead to a sense of cultural dissonance as people struggle to integrate these identities into a coherent sense of self.

View Article and Find Full Text PDF

Iodoform, a halogenated organic compound, has been a cornerstone in surgical practice due to its potent antiseptic and antimicrobial properties. This comprehensive review examines the historical evolution, mechanism of action, clinical applications, and safety profile of iodoform across various surgical disciplines. Historically significant formulations like Whitehead's varnish and bismuth iodoform paraffin paste (BIPP) demonstrated remarkable efficacy in wound healing during the late 19th and early 20th centuries.

View Article and Find Full Text PDF

Expanding the Chemical Space of Reverse Fosmidomycin Analogs.

ACS Med Chem Lett

January 2025

Institute of Pharmaceutical and Medicinal Chemistry, Faculty of Mathematics and Natural Sciences, Heinrich Heine University Düsseldorf, Universitätsstr. 1, 40225 Düsseldorf, Germany.

Multidrug-resistant pathogens pose a major threat to human health, necessitating the identification of new drug targets and lead compounds that are not susceptible to cross-resistance. This study demonstrates that novel reverse thia analogs of the phosphonohydroxamic acid antibiotic fosmidomycin inhibit 1-deoxy-d-xylulose 5-phosphate reductoisomerase (DXR), an essential enzyme for , , and that is absent in humans. Some novel analogs with large α-phenyl substituents exhibited strong inhibition across these three DXR orthologues, surpassing the inhibitory activity of fosmidomycin.

View Article and Find Full Text PDF

Background: Health inequalities can affect access and uptake to pulmonary rehabilitation (PR). An individual's protected characteristics (age, disability, gender reassignment, marriage and civil partnership, pregnancy and maternity, race, religion or belief, sex and sexual orientation) may contribute to health inequalities. Healthcare professionals (HCPs) experiences of the inclusivity and representativeness of PR services and knowledge of protected characteristics are unknown, however are vital for the identification and resolution of health inequalities.

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!