Back

Bioinformatics Illustrations Decoded by ChatGPT: The Good, The Bad, and The Ugly

Wang, J.; Ye, Q.; Liu, L.; Guo, N. L.; Hu, G.

2023-10-17 bioinformatics
10.1101/2023.10.15.562423 bioRxiv
Show abstract

Emerging studies underscore the promising capabilities of large language model-based chatbots in conducting fundamental bioinformatics data analyses. The recent feature of accepting image-inputs by ChatGPT motivated us to explore its efficacy in deciphering bioinformatics illustrations. Our evaluation with examples in cancer research, including sequencing data analysis, multimodal network-based drug repositioning, and tumor clonal evolution, revealed that ChatGPT can proficiently explain different plot types and apply biological knowledge to enrich interpretations. However, it struggled to provide accurate interpretations when quantitative analysis of visual elements was involved. Furthermore, while the chatbot can draft figure legends and summarize findings from the figures, stringent proofreading is imperative to ensure the accuracy and reliability of the content.

Matching journals

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

1
Computational and Structural Biotechnology Journal
● 242 papers in training set
Top 0.1%
23.0%
Similar papers in this journal
2
Briefings in Bioinformatics
◐ 354 papers in training set
Top 0.8%
8.1%
Similar papers in this journal
3
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 0.6%
5.7%
Similar papers in this journal
4
BMC Bioinformatics
○ 457 papers in training set
Top 2%
4.2%
Similar papers in this journal
5
Scientific Reports
○ 3612 papers in training set
Top 24%
4.2%
Similar papers in this journal
6
Nucleic Acids Research
◐ 1281 papers in training set
Top 5%
3.6%
7
iScience
○ 1154 papers in training set
Top 8%
2.8%
50% of probability mass above
8
Frontiers in Bioinformatics
○ 49 papers in training set
Top 0.3%
2.2%
9
Nature Communications
○ 5641 papers in training set
Top 41%
2.2%
10
Computers in Biology and Medicine
○ 128 papers in training set
Top 2%
2.0%
11
PLOS Computational Biology
● 1863 papers in training set
Top 14%
1.8%
12
Life Science Alliance
● 285 papers in training set
Top 3%
1.8%
13
Bioinformatics Advances
◐ 203 papers in training set
Top 3%
1.7%
14
BMC Methods
○ 15 papers in training set
Top 0.1%
1.7%
15
Life
○ 29 papers in training set
Top 0.3%
1.5%
16
PLOS ONE
● 5266 papers in training set
Top 48%
1.5%
17
JCO Clinical Cancer Informatics
● 22 papers in training set
Top 0.4%
1.5%
18
Cell Reports Methods
○ 165 papers in training set
Top 2%
1.5%
19
Bioinformatics
◐ 1204 papers in training set
Top 7%
1.4%
20
npj Systems Biology and Applications
○ 125 papers in training set
Top 1%
1.4%
21
Communications Biology
○ 993 papers in training set
Top 20%
1.2%
22
Genome Biology
○ 637 papers in training set
Top 7%
1.2%
23
PeerJ
◐ 308 papers in training set
Top 7%
1.2%
24
BMC Genomics
○ 406 papers in training set
Top 6%
1.1%
25
Scientific Data
○ 209 papers in training set
Top 2%
1.1%
26
Genomics, Proteomics & Bioinformatics
188 papers in training set
Top 2%
0.9%
27
Cancer Research Communications
● 51 papers in training set
Top 2%
0.9%
28
Genome Medicine
○ 183 papers in training set
Top 5%
0.9%
29
Patterns
○ 78 papers in training set
Top 2%
0.9%
30
NAR Cancer
◐ 37 papers in training set
Top 0.7%
0.9%

"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.