Back

Illuminating the functional landscape of the dark proteome across the Animal Tree of Life through natural language processing models

Martinez-Redondo, G. I.; Barrios-Nunez, I.; Vazquez-Valls, M.; Rojas, A. M.; Fernandez, R.

2024-02-29 evolutionary biology Community evaluation
10.1101/2024.02.28.582465 bioRxiv
Show abstract

Functional annotation is crucial in biology, but many protein-coding genes remain uncharacterized, especially in non-model organisms. FANTASIA (Functional ANnoTAtion based on embedding space SImilArity) integrates protein language models for large-scale functional annotation. Applied to [~]1,000 animal proteomes, it predicts functions to virtually all proteins, revealing previously uncharacterized functions that enhance our understanding of molecular evolution. FANTASIA is available on GitHub at https://github.com/CBBIO/FANTASIA.

Matching journals

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

1
Nature Communications
○ 5641 papers in training set
Top 13%
14.3%
Similar papers in this journal
2
Genome Biology
○ 637 papers in training set
Top 1%
9.3%
Similar papers in this journal
3
Bioinformatics
◐ 1204 papers in training set
Top 3%
8.5%
Similar papers in this journal
4
Scientific Reports
○ 3612 papers in training set
Top 13%
6.0%
Similar papers in this journal
5
Nature Methods
○ 385 papers in training set
Top 2%
5.3%
Similar papers in this journal
6
Protein Science
○ 246 papers in training set
Top 0.8%
5.3%
7
Communications Biology
○ 993 papers in training set
Top 2%
5.3%
50% of probability mass above
8
PLOS Computational Biology
● 1863 papers in training set
Top 8%
4.1%
9
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 1%
3.4%
10
GigaScience
◐ 212 papers in training set
Top 1%
3.3%
11
Scientific Data
○ 209 papers in training set
Top 0.8%
3.1%
12
Nucleic Acids Research
◐ 1281 papers in training set
Top 6%
3.1%
13
Journal of Proteome Research
● 234 papers in training set
Top 0.8%
3.1%
14
eLife
● 5828 papers in training set
Top 40%
2.7%
15
Briefings in Bioinformatics
◐ 354 papers in training set
Top 3%
2.5%
16
Nature Computational Science
○ 55 papers in training set
Top 0.6%
1.8%
17
Peer Community Journal
● 281 papers in training set
Top 3%
1.7%
18
Molecular Biology and Evolution
◐ 542 papers in training set
Top 3%
1.7%
19
iScience
○ 1154 papers in training set
Top 22%
1.4%
20
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 33%
1.3%
21
BMC Genomics
○ 406 papers in training set
Top 6%
1.1%
22
Bioinformatics Advances
◐ 203 papers in training set
Top 4%
1.0%
23
Molecular Systems Biology
○ 162 papers in training set
Top 3%
0.9%
24
Genome Research
● 468 papers in training set
Top 6%
0.9%
25
BMC Bioinformatics
○ 457 papers in training set
Top 6%
0.8%
26
Nature Ecology & Evolution
131 papers in training set
Top 3%
0.6%
27
BMC Biology
○ 265 papers in training set
Top 8%
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.