Back

Harnessing the Power of Large Language Models (LLMs) to Unravel the Influence of Genes and Medication on Biological Processes of Wound Healing

Jui, J. H.; Hauskrecht, M.

2024-03-29 bioinformatics
10.1101/2024.03.26.586862 bioRxiv
Show abstract

Recent advancements in Large Language Models (LLMs) have ushered in a new era for knowledge extraction in the domains of biological and clinical natural language processing (NLP). In this research, we present a novel approach to understanding the regulatory effects of genes and medications on biological processes central to wound healing. Utilizing the capabilities of Generative Pre-trained Transformer (GPT) models by OpenAI, specifically GPT-3.5 and GPT-4, we developed a comprehensive pipeline for the identification and grounding of biological processes and the extraction of such regulatory relations. The performances of both GPTs were rigorously evaluated against a manually annotated corpus of 104 PubMed titles, focusing on their ability to accurately identify and ground biological process concepts and extract relevant regulatory relationships from the text. Our findings demonstrate that GPT-4, in particular, exhibits superior performance in all the tasks, showcasing its potential to facilitate significant advancements in biomedical research without requiring model fine-tuning.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

1
Bioinformatics Advances
◐ 203 papers in training set
Top 0.1%
12.8%
Similar papers in this journal
2
Bioinformatics
◐ 1204 papers in training set
Top 2%
10.9%
Similar papers in this journal
3
BioData Mining
○ 22 papers in training set
Top 0.1%
6.7%
Similar papers in this journal
4
BMC Bioinformatics
○ 457 papers in training set
Top 1%
6.2%
Similar papers in this journal
5
GigaScience
◐ 212 papers in training set
Top 0.7%
4.8%
6
Journal of Biomedical Informatics
○ 47 papers in training set
Top 0.4%
4.8%
Similar papers in this journal
7
Computational and Structural Biotechnology Journal
● 242 papers in training set
Top 0.7%
4.8%
50% of probability mass above
8
Scientific Reports
○ 3612 papers in training set
Top 26%
4.0%
9
Database
◐ 61 papers in training set
Top 0.2%
3.2%
10
Artificial Intelligence in Medicine
○ 17 papers in training set
Top 0.2%
2.8%
11
Nucleic Acids Research
◐ 1281 papers in training set
Top 6%
2.6%
12
Frontiers in Bioinformatics
○ 49 papers in training set
Top 0.3%
2.4%
13
Computers in Biology and Medicine
○ 128 papers in training set
Top 2%
2.4%
14
PLOS ONE
● 5266 papers in training set
Top 41%
2.4%
15
BMC Medical Informatics and Decision Making
○ 43 papers in training set
Top 1%
1.7%
16
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 2%
1.7%
17
iScience
○ 1154 papers in training set
Top 18%
1.7%
18
IEEE/ACM Transactions on Computational Biology and Bioinformatics
● 38 papers in training set
Top 0.6%
1.7%
19
Briefings in Bioinformatics
◐ 354 papers in training set
Top 5%
1.7%
20
Patterns
○ 78 papers in training set
Top 2%
1.4%
21
JAMIA Open
◐ 42 papers in training set
Top 1%
1.1%
22
Journal of the American Medical Informatics Association
◐ 71 papers in training set
Top 2%
1.1%
23
Journal of Computational Biology
○ 48 papers in training set
Top 0.8%
1.1%
24
PLOS Computational Biology
● 1863 papers in training set
Top 18%
1.1%
25
Frontiers in Genetics
○ 230 papers in training set
Top 4%
1.0%
26
IEEE Transactions on Computational Biology and Bioinformatics
● 20 papers in training set
Top 0.6%
0.8%
27
Scientific Data
○ 209 papers in training set
Top 3%
0.8%
28
Genome Biology
○ 637 papers in training set
Top 9%
0.8%
29
PLOS Digital Health
● 106 papers in training set
Top 5%
0.6%
30
Biology Methods and Protocols
◐ 61 papers in training set
Top 3%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.