<HashMap><database>biostudies-literature</database><scores/><additional><omics_type>Unknown</omics_type><volume>5</volume><submitter>Xu C</submitter><pubmed_abstract>Biological databases are essential for providing curated knowledge, but their rigid data structures and restrictive query formats often limit flexible and exploratory user interactions. In the field of plant phosphorylation, manually curated and reviewed data represent only a small portion of the available knowledge, and users often seek information that goes beyond what is provided in structured databases. While large language models (LLMs) like ChatGPT-4o possess extensive contextual knowledge, integrating this capability into bioinformatics tools remains an open challenge. Here, we present a multimodal question-answering widget that integrates ChatGPT-4o with our Plant Protein Phosphorylation Database (P3DB). This system supports natural language queries and dynamic prompt formulation, </pubmed_abstract><journal>Frontiers in bioinformatics</journal><pagination>1687687</pagination><full_dataset_link>https://www.ebi.ac.uk/biostudies/studies/S-EPMC12568720</full_dataset_link><repository>biostudies-literature</repository><pubmed_title>Multimodal knowledge expansion widget powered by plant protein phosphorylation database and ChatGPT.</pubmed_title><pmcid>PMC12568720</pmcid><pubmed_authors>Khadakkar G</pubmed_authors><pubmed_authors>Xie J</pubmed_authors><pubmed_authors>Xu D</pubmed_authors><pubmed_authors>Xu C</pubmed_authors><pubmed_authors>Yao Q</pubmed_authors><pubmed_authors>Yu Y</pubmed_authors></additional><is_claimable>false</is_claimable><name>Multimodal knowledge expansion widget powered by plant protein phosphorylation database and ChatGPT.</name><description>Biological databases are essential for providing curated knowledge, but their rigid data structures and restrictive query formats often limit flexible and exploratory user interactions. In the field of plant phosphorylation, manually curated and reviewed data represent only a small portion of the available knowledge, and users often seek information that goes beyond what is provided in structured databases. While large language models (LLMs) like ChatGPT-4o possess extensive contextual knowledge, integrating this capability into bioinformatics tools remains an open challenge. Here, we present a multimodal question-answering widget that integrates ChatGPT-4o with our Plant Protein Phosphorylation Database (P3DB). This system supports natural language queries and dynamic prompt formulation, </description><dates><release>2025-01-01T00:00:00Z</release><publication>2025</publication><modification>2026-06-05T07:47:16.82Z</modification><creation>2026-05-14T03:12:48.243Z</creation></dates><accession>S-EPMC12568720</accession><cross_references><pubmed>41169664</pubmed><doi>10.3389/fbinf.2025.1687687</doi></cross_references></HashMap>