reguloGPT : Harnessing GPT for Knowledge Graph Construction of Molecular Regulatory Pathways
Motivation: Molecular Regulatory Pathways (MRPs) are crucial for understanding biological functions. Knowledge Graphs (KGs) have become vital in organizing and analyzing MRPs, providing structured representations of complex biological interactions. Current tools for mining KGs from biomedical literature are inadequate in capturing complex, hierarchical relationships and contextual information about MRPs. Large Language Models (LLMs) like GPT-4 offer a promising solution, with advanced capabilities to decipher the intricate nuances of language. However, their potential for end-to-end KG construction, particularly for MRPs, remains largely unexplored.
Results: We present reguloGPT, a novel GPT-4 based in-context learning prompt, designed for the end-to-end joint name entity recognition, N-ary relationship extraction, and context predictions from a sentence that describes regulatory interactions with MRPs. Our reguloGPT approach introduces a context-aware relational graph that effectively embodies the hierarchical structure of MRPs and resolves semantic inconsistencies by embedding context directly within relational edges. We created a benchmark dataset including 400 annotated PubMed titles on N6-methyladenosine (m6A) regulations. Rigorous evaluation of reguloGPT on the benchmark dataset demonstrated marked improvement over existing algorithms. We further developed a novel G-Eval scheme, leveraging GPT-4 for annotation-free performance evaluation and demonstrated its agreement with traditional annotation-based evaluations. Utilizing reguloGPT predictions on m6A-related titles, we constructed the m6A-KG and demonstrated its utility in elucidating m6A's regulatory mechanisms in cancer phenotypes across various cancers. These results underscore reguloGPT's transformative potential for extracting biological knowledge from the literature.
Availability and implementation: The source code of reguloGPT, the m6A title and benchmark datasets, and m6A-KG are available at: https://github.com/Huang-AI4Medicine-Lab/reguloGPT.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - year:2024 |
|---|---|
| Enthalten in: |
bioRxiv : the preprint server for biology - (2024) vom: 30. Jan. |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Wu, Xidong [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
GPT |
|---|
| Anmerkungen: |
Date Revised 12.02.2024 published: Electronic Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1101/2024.01.27.577521 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM368024709 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM368024709 | ||
| 003 | DE-627 | ||
| 005 | 20240212232111.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240205s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1101/2024.01.27.577521 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1289.xml |
| 035 | |a (DE-627)NLM368024709 | ||
| 035 | |a (NLM)38313267 | ||
| 035 | |a (PII)2024.01.27.577521 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Wu, Xidong |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a reguloGPT |b Harnessing GPT for Knowledge Graph Construction of Molecular Regulatory Pathways |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 12.02.2024 | ||
| 500 | |a published: Electronic | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a Motivation: Molecular Regulatory Pathways (MRPs) are crucial for understanding biological functions. Knowledge Graphs (KGs) have become vital in organizing and analyzing MRPs, providing structured representations of complex biological interactions. Current tools for mining KGs from biomedical literature are inadequate in capturing complex, hierarchical relationships and contextual information about MRPs. Large Language Models (LLMs) like GPT-4 offer a promising solution, with advanced capabilities to decipher the intricate nuances of language. However, their potential for end-to-end KG construction, particularly for MRPs, remains largely unexplored | ||
| 520 | |a Results: We present reguloGPT, a novel GPT-4 based in-context learning prompt, designed for the end-to-end joint name entity recognition, N-ary relationship extraction, and context predictions from a sentence that describes regulatory interactions with MRPs. Our reguloGPT approach introduces a context-aware relational graph that effectively embodies the hierarchical structure of MRPs and resolves semantic inconsistencies by embedding context directly within relational edges. We created a benchmark dataset including 400 annotated PubMed titles on N6-methyladenosine (m6A) regulations. Rigorous evaluation of reguloGPT on the benchmark dataset demonstrated marked improvement over existing algorithms. We further developed a novel G-Eval scheme, leveraging GPT-4 for annotation-free performance evaluation and demonstrated its agreement with traditional annotation-based evaluations. Utilizing reguloGPT predictions on m6A-related titles, we constructed the m6A-KG and demonstrated its utility in elucidating m6A's regulatory mechanisms in cancer phenotypes across various cancers. These results underscore reguloGPT's transformative potential for extracting biological knowledge from the literature | ||
| 520 | |a Availability and implementation: The source code of reguloGPT, the m6A title and benchmark datasets, and m6A-KG are available at: https://github.com/Huang-AI4Medicine-Lab/reguloGPT | ||
| 650 | 4 | |a Preprint | |
| 650 | 4 | |a GPT | |
| 650 | 4 | |a In Context Learning | |
| 650 | 4 | |a Knowledge Graph | |
| 650 | 4 | |a Molecular Regulatory Pathways | |
| 650 | 4 | |a m6A mRNA Methylation | |
| 700 | 1 | |a Zeng, Yiming |e verfasserin |4 aut | |
| 700 | 1 | |a Das, Arun |e verfasserin |4 aut | |
| 700 | 1 | |a Jo, Sumin |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Tinghe |e verfasserin |4 aut | |
| 700 | 1 | |a Patel, Parth |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Jianqiu |e verfasserin |4 aut | |
| 700 | 1 | |a Gao, Shou-Jiang |e verfasserin |4 aut | |
| 700 | 1 | |a Pratt, Dexter |e verfasserin |4 aut | |
| 700 | 1 | |a Chiu, Yu-Chiao |e verfasserin |4 aut | |
| 700 | 1 | |a Huang, Yufei |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t bioRxiv : the preprint server for biology |d 2020 |g (2024) vom: 30. Jan. |w (DE-627)NLM31090014X |7 nnns |
| 773 | 1 | 8 | |g year:2024 |g day:30 |g month:01 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1101/2024.01.27.577521 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |j 2024 |b 30 |c 01 | ||