Table 8_Multimodal knowledge expansion widget powered by plant protein phosphorylation database and ChatGPT.xlsx
<p>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...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , , , |
| منشور في: |
2025
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1852015783085867008 |
|---|---|
| author | Chunhui Xu (139181) |
| author2 | Yang Yu (4292) Govardhan Khadakkar (22434757) Jiacheng Xie (14364468) Dong Xu (21616) Qiuming Yao (5815991) |
| author2_role | author author author author author |
| author_facet | Chunhui Xu (139181) Yang Yu (4292) Govardhan Khadakkar (22434757) Jiacheng Xie (14364468) Dong Xu (21616) Qiuming Yao (5815991) |
| author_role | author |
| dc.creator.none.fl_str_mv | Chunhui Xu (139181) Yang Yu (4292) Govardhan Khadakkar (22434757) Jiacheng Xie (14364468) Dong Xu (21616) Qiuming Yao (5815991) |
| dc.date.none.fl_str_mv | 2025-10-15T05:24:57Z |
| dc.identifier.none.fl_str_mv | 10.3389/fbinf.2025.1687687.s010 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/dataset/Table_8_Multimodal_knowledge_expansion_widget_powered_by_plant_protein_phosphorylation_database_and_ChatGPT_xlsx/30361864 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Bioinformatics multimodality large language mode plant protein phosphorylation information retrieva pathway identification |
| dc.title.none.fl_str_mv | Table 8_Multimodal knowledge expansion widget powered by plant protein phosphorylation database and ChatGPT.xlsx |
| dc.type.none.fl_str_mv | Dataset info:eu-repo/semantics/publishedVersion dataset |
| description | <p>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, enabling users to explore phosphorylation events, kinase-substrate relationships, and protein-protein interactions through a global entry. In another application, the widget leverages ChatGPT’s image interpretation functionality to extract regulatory pathways and phosphorylation markers from complex scientific figures. To build this widget effectively, we have explored multiple prompt strategies, including one-step, two-step, few-shot, and image-cropping techniques, demonstrating their impact on output accuracy and consistency. In addition, recent multimodal LLMs such as ChatGPT-5 and Gemini 1.5 have demonstrated comparable capabilities and adaptability when applied to our test cases and the developed widgets. Together, our application widget and results highlight the development of the ChatGPT-P3DB integration as a system that enhances user accessibility, enables visual extraction, and extends the current utility of biological knowledgebases through a flexible and adaptive framework. Our “ChatGPT-P3DB” is open-source and can be accessed on GitHub (https://github.com/yao-laboratory/p3db-chat). The frontend interface, “P3DB askAI” web module, can be accessed freely through https://www.p3db.org/ask-ai.</p> |
| eu_rights_str_mv | openAccess |
| id | Manara_ea930fc4cd78bced91e022f18c377daa |
| identifier_str_mv | 10.3389/fbinf.2025.1687687.s010 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/30361864 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Table 8_Multimodal knowledge expansion widget powered by plant protein phosphorylation database and ChatGPT.xlsxChunhui Xu (139181)Yang Yu (4292)Govardhan Khadakkar (22434757)Jiacheng Xie (14364468)Dong Xu (21616)Qiuming Yao (5815991)Bioinformaticsmultimodalitylarge language modeplant protein phosphorylationinformation retrievapathway identification<p>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, enabling users to explore phosphorylation events, kinase-substrate relationships, and protein-protein interactions through a global entry. In another application, the widget leverages ChatGPT’s image interpretation functionality to extract regulatory pathways and phosphorylation markers from complex scientific figures. To build this widget effectively, we have explored multiple prompt strategies, including one-step, two-step, few-shot, and image-cropping techniques, demonstrating their impact on output accuracy and consistency. In addition, recent multimodal LLMs such as ChatGPT-5 and Gemini 1.5 have demonstrated comparable capabilities and adaptability when applied to our test cases and the developed widgets. Together, our application widget and results highlight the development of the ChatGPT-P3DB integration as a system that enhances user accessibility, enables visual extraction, and extends the current utility of biological knowledgebases through a flexible and adaptive framework. Our “ChatGPT-P3DB” is open-source and can be accessed on GitHub (https://github.com/yao-laboratory/p3db-chat). The frontend interface, “P3DB askAI” web module, can be accessed freely through https://www.p3db.org/ask-ai.</p>2025-10-15T05:24:57ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.3389/fbinf.2025.1687687.s010https://figshare.com/articles/dataset/Table_8_Multimodal_knowledge_expansion_widget_powered_by_plant_protein_phosphorylation_database_and_ChatGPT_xlsx/30361864CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/303618642025-10-15T05:24:57Z |
| spellingShingle | Table 8_Multimodal knowledge expansion widget powered by plant protein phosphorylation database and ChatGPT.xlsx Chunhui Xu (139181) Bioinformatics multimodality large language mode plant protein phosphorylation information retrieva pathway identification |
| status_str | publishedVersion |
| title | Table 8_Multimodal knowledge expansion widget powered by plant protein phosphorylation database and ChatGPT.xlsx |
| title_full | Table 8_Multimodal knowledge expansion widget powered by plant protein phosphorylation database and ChatGPT.xlsx |
| title_fullStr | Table 8_Multimodal knowledge expansion widget powered by plant protein phosphorylation database and ChatGPT.xlsx |
| title_full_unstemmed | Table 8_Multimodal knowledge expansion widget powered by plant protein phosphorylation database and ChatGPT.xlsx |
| title_short | Table 8_Multimodal knowledge expansion widget powered by plant protein phosphorylation database and ChatGPT.xlsx |
| title_sort | Table 8_Multimodal knowledge expansion widget powered by plant protein phosphorylation database and ChatGPT.xlsx |
| topic | Bioinformatics multimodality large language mode plant protein phosphorylation information retrieva pathway identification |