Back

GeneKnow: AI-powered literature synthesis for gene-context analysis

Zhang, H.; Zang, C.

2026-06-01 bioinformatics
10.64898/2026.05.28.728511 bioRxiv
Show abstract

Interpreting gene function in specific biological contexts is essential for biomedical research, yet manual literature review is labor-intensive. We developed GeneKnow, a source-grounded framework that uses generative AI models within a controlled hybrid workflow to produce reliable, traceable literature synthesis supported by authentic citations. Through systematic benchmarking, we showed that GeneKnow outperforms mainstream web-interface AI tools in generating trustworthy context-specific gene function syntheses without fabricated citations and minimizing hallucinations.

Matching journals

The top 9 journals account for 50% of the predicted probability mass.

1
Bioinformatics
◐ 1061 papers in training set
Top 2%
12.3%
2
Nucleic Acids Research
◐ 1128 papers in training set
Top 2%
10.1%
3
Nature Methods
○ 336 papers in training set
Top 2%
4.8%
4
Nature Communications
○ 4913 papers in training set
Top 33%
4.8%
5
Genome Biology
○ 555 papers in training set
Top 1%
4.8%
6
PLOS ONE
● 4510 papers in training set
Top 36%
3.9%
7
Genome Medicine
○ 154 papers in training set
Top 2%
3.6%
8
Bioinformatics Advances
◐ 184 papers in training set
Top 2%
3.1%
9
Cell Systems
○ 167 papers in training set
Top 5%
3.1%
50% of probability mass above
10
BMC Bioinformatics
○ 383 papers in training set
Top 3%
2.7%
11
GigaScience
◐ 172 papers in training set
Top 0.8%
2.4%
12
NAR Genomics and Bioinformatics
◐ 214 papers in training set
Top 1%
2.4%
13
Database
◐ 51 papers in training set
Top 0.3%
2.4%
14
Scientific Reports
○ 3102 papers in training set
Top 50%
2.1%
15
PLOS Computational Biology
● 1633 papers in training set
Top 15%
1.9%
16
PLOS Biology
● 408 papers in training set
Top 9%
1.8%
17
Briefings in Bioinformatics
◐ 326 papers in training set
Top 4%
1.7%
18
Advanced Science
○ 249 papers in training set
Top 11%
1.7%
19
Proceedings of the National Academy of Sciences
● 2130 papers in training set
Top 35%
1.5%
20
Computational and Structural Biotechnology Journal
● 216 papers in training set
Top 5%
1.5%
21
Journal of the American Medical Informatics Association
◐ 61 papers in training set
Top 2%
1.2%
22
Science
● 429 papers in training set
Top 17%
1.2%
23
Nature Biotechnology
○ 147 papers in training set
Top 6%
0.9%
24
Molecular Systems Biology
○ 142 papers in training set
Top 1%
0.9%
25
iScience
○ 1063 papers in training set
Top 24%
0.9%
26
Genomics, Proteomics & Bioinformatics
◐ 171 papers in training set
Top 5%
0.9%
27
Nature
○ 575 papers in training set
Top 14%
0.9%
28
Nature Machine Intelligence
○ 61 papers in training set
Top 4%
0.7%
29
BMC Biology
○ 248 papers in training set
Top 4%
0.7%
30
npj Digital Medicine
○ 97 papers in training set
Top 4%
0.7%