Back

Case Study of Using AI as Co-Pilot in Biotech Research: Functional Network Analysis of Invasive Cancer

Sinitskiy, A.

2025-05-17 bioinformatics
10.1101/2025.05.14.654152 bioRxiv
Show abstract

This study presents a case analysis of using AI systems as co-pilots in biological research, focusing on functional protein networks in invasive colorectal cancer. We used public proteomic data alongside ChatGPT, GitHub Copilot, and PaperQA to automate parts of the workflow, including literature review, code generation, and network analysis. While AI tools improved efficiency, they required expert guidance for tasks involving complex metadata, domain-specific parsing, and reproducibility. Our analysis identified cytoskeleton- and signaling-related networks in invasive cancer, aligning with known biology, but attempts to distinguish invasive from non-invasive cases produced inconclusive results. An attempt to conduct fully automated research using Agent Laboratory failed due to hallucinated data, misinterpretation of research goals, and instability as the complexity of the underlying LLM increased. These findings show that current AI can assist but not replace human researchers in complex biotech studies.

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

1
Journal of Proteome Research
● 234 papers in training set
Top 0.2%
18.4%
Similar papers in this journal
2
PROTEOMICS
○ 43 papers in training set
Top 0.1%
6.7%
Similar papers in this journal
3
PLOS Computational Biology
● 1863 papers in training set
Top 7%
5.5%
Similar papers in this journal
4
Computational and Structural Biotechnology Journal
● 242 papers in training set
Top 0.6%
5.5%
Similar papers in this journal
5
Scientific Reports
○ 3612 papers in training set
Top 22%
4.3%
Similar papers in this journal
6
Analytical Chemistry
● 218 papers in training set
Top 0.8%
4.3%
7
GigaScience
◐ 212 papers in training set
Top 0.9%
4.0%
8
Bioinformatics
◐ 1204 papers in training set
Top 5%
3.2%
50% of probability mass above
9
Briefings in Bioinformatics
◐ 354 papers in training set
Top 3%
3.2%
10
PLOS ONE
● 5266 papers in training set
Top 36%
3.2%
11
Frontiers in Bioinformatics
○ 49 papers in training set
Top 0.2%
3.1%
12
Cell Systems
○ 201 papers in training set
Top 2%
2.6%
13
Nature Communications
○ 5641 papers in training set
Top 38%
2.6%
14
Bioinformatics Advances
◐ 203 papers in training set
Top 2%
2.4%
15
Protein Science
○ 246 papers in training set
Top 2%
2.1%
16
Molecular Systems Biology
○ 162 papers in training set
Top 1%
2.1%
17
Nature Methods
○ 385 papers in training set
Top 4%
1.7%
18
Patterns
○ 78 papers in training set
Top 1%
1.7%
19
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 2%
1.7%
20
iScience
○ 1154 papers in training set
Top 21%
1.5%
21
Molecular & Cellular Proteomics
183 papers in training set
Top 1%
1.3%
22
Biology
○ 45 papers in training set
Top 0.4%
1.1%
23
BMC Bioinformatics
○ 457 papers in training set
Top 5%
1.1%
24
Scientific Data
○ 209 papers in training set
Top 3%
0.8%
25
Genome Biology
○ 637 papers in training set
Top 10%
0.6%
26
Cell Reports Methods
○ 165 papers in training set
Top 4%
0.6%
27
PeerJ
◐ 308 papers in training set
Top 12%
0.6%
28
Journal of the American Society for Mass Spectrometry
● 37 papers in training set
Top 0.6%
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.