<HashMap><database>biostudies-literature</database><scores/><additional><submitter>Guo X</submitter><funding>National Natural Science Foundation of China (National Science Foundation of China)</funding><pagination>183</pagination><full_dataset_link>https://www.ebi.ac.uk/biostudies/studies/S-EPMC11228022</full_dataset_link><repository>biostudies-literature</repository><omics_type>Unknown</omics_type><volume>9(1)</volume><pubmed_abstract>Helicobacter pylori (H. pylori) is currently recognized as the primary carcinogenic pathogen associated with gastric tumorigenesis, and its high prevalence and resistance make it difficult to tackle. A graph neural network-based deep learning model, employing different training sets of 13,638 molecules for pre-training and fine-tuning, was aided in predicting and exploring novel molecules against H. pylori. A positively predicted novel berberine derivative 8 with 3,13-disubstituted alkene exhibited a potency against all tested drug-susceptible and resistant H. pylori strains with minimum inhibitory concentrations (MICs) of 0.25-0.5 μg/mL. Pharmacokinetic studies demonstrated an ideal gastric retention of 8, with the stomach concentration significantly higher than its MIC at 24 h post dose.</pubmed_abstract><journal>Signal transduction and targeted therapy</journal><pubmed_title>A deep learning-driven discovery of berberine derivatives as novel antibacterial against multidrug-resistant Helicobacter pylori.</pubmed_title><pmcid>PMC11228022</pmcid><funding_grant_id>32141003</funding_grant_id><funding_grant_id>82003575</funding_grant_id><funding_grant_id>61972384</funding_grant_id><pubmed_authors>Jiang J</pubmed_authors><pubmed_authors>Zeng Q</pubmed_authors><pubmed_authors>Xu M</pubmed_authors><pubmed_authors>Lu X</pubmed_authors><pubmed_authors>Guo X</pubmed_authors><pubmed_authors>Song D</pubmed_authors><pubmed_authors>Chen F</pubmed_authors><pubmed_authors>Wei W</pubmed_authors><pubmed_authors>You X</pubmed_authors><pubmed_authors>Zhao X</pubmed_authors><pubmed_authors>Fan T</pubmed_authors><pubmed_authors>Zhao L</pubmed_authors><pubmed_authors>Zhang Z</pubmed_authors><pubmed_authors>Zhang X</pubmed_authors><pubmed_authors>Pang J</pubmed_authors><pubmed_authors>Wang Y</pubmed_authors><pubmed_authors>Feng S</pubmed_authors></additional><is_claimable>false</is_claimable><name>A deep learning-driven discovery of berberine derivatives as novel antibacterial against multidrug-resistant Helicobacter pylori.</name><description>Helicobacter pylori (H. pylori) is currently recognized as the primary carcinogenic pathogen associated with gastric tumorigenesis, and its high prevalence and resistance make it difficult to tackle. A graph neural network-based deep learning model, employing different training sets of 13,638 molecules for pre-training and fine-tuning, was aided in predicting and exploring novel molecules against H. pylori. A positively predicted novel berberine derivative 8 with 3,13-disubstituted alkene exhibited a potency against all tested drug-susceptible and resistant H. pylori strains with minimum inhibitory concentrations (MICs) of 0.25-0.5 μg/mL. Pharmacokinetic studies demonstrated an ideal gastric retention of 8, with the stomach concentration significantly higher than its MIC at 24 h post dose.</description><dates><release>2024-01-01T00:00:00Z</release><publication>2024 Jul</publication><modification>2026-06-01T07:37:35.54Z</modification><creation>2025-04-04T11:25:14.621Z</creation></dates><accession>S-EPMC11228022</accession><cross_references><pubmed>38972904</pubmed><doi>10.1038/s41392-024-01895-0</doi></cross_references></HashMap>