Back

HieVi: Protein Large Language Model for proteome-based phage clustering

Panigrahi, S.; Ansaldi, M.; Ginet, N.

2024-12-20 genomics
10.1101/2024.12.17.627486 bioRxiv
Show abstract

Viral taxonomy is a challenging task due to the propensity of viruses for recombination. Recent updates from the ICTV and advancements in proteome-based clustering tools highlight the need for a unified framework to organize bacteriophages (phages) across multiscale taxonomic ranks, extending beyond genome-based clustering. Meanwhile, self-supervised large language models, trained on amino acid sequences, have proven effective in capturing the structural, functional, and evolutionary properties of proteins. Building on these advancements, we introduce HieVi, which uses embeddings from a protein language model to define a vector representation of phages and generate a hierarchical tree of phages. Using the INPHARED dataset of 24,362 complete and annotated viral genomes, we show that in HieVi, a multi-scale taxonomic ranking emerges that aligns well with current ICTV taxonomy. We propose that this method, unique in its integration of protein language models for viral taxonomy, can encode phylogenetic relationships, at least up to the family level. It therefore offers a valuable tool for biologists to discover and define new phage families while unraveling novel evolutionary connections.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

1
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 0.1%
14.6%
Similar papers in this journal
2
Virus Evolution
◐ 155 papers in training set
Top 0.2%
11.5%
Similar papers in this journal
3
Viruses
○ 332 papers in training set
Top 0.2%
11.5%
Similar papers in this journal
4
Nucleic Acids Research
◐ 1281 papers in training set
Top 4%
4.7%
Similar papers in this journal
5
Scientific Reports
○ 3612 papers in training set
Top 20%
4.7%
Similar papers in this journal
6
Nature Communications
○ 5641 papers in training set
Top 34%
3.3%
50% of probability mass above
7
Peer Community Journal
● 281 papers in training set
Top 2%
3.1%
8
PLOS Computational Biology
● 1863 papers in training set
Top 10%
3.1%
9
GigaScience
◐ 212 papers in training set
Top 1%
2.7%
10
Scientific Data
○ 209 papers in training set
Top 0.9%
2.6%
11
mSystems
● 394 papers in training set
Top 3%
2.6%
12
BMC Genomics
○ 406 papers in training set
Top 3%
2.4%
13
BMC Biology
○ 265 papers in training set
Top 1%
2.3%
14
Bioinformatics
◐ 1204 papers in training set
Top 6%
2.1%
15
Molecular Biology and Evolution
◐ 542 papers in training set
Top 4%
1.4%
16
Frontiers in Genetics
○ 230 papers in training set
Top 3%
1.3%
17
iScience
○ 1154 papers in training set
Top 24%
1.3%
18
Genome Biology
○ 637 papers in training set
Top 7%
1.3%
19
Frontiers in Microbiology
○ 427 papers in training set
Top 6%
1.3%
20
Briefings in Bioinformatics
◐ 354 papers in training set
Top 5%
1.3%
21
PLOS ONE
● 5266 papers in training set
Top 54%
1.1%
22
Communications Biology
○ 993 papers in training set
Top 26%
1.0%
23
BMC Bioinformatics
○ 457 papers in training set
Top 5%
1.0%
24
Frontiers in Immunology
○ 638 papers in training set
Top 8%
1.0%
25
Microbiome
○ 154 papers in training set
Top 2%
1.0%
26
iMeta
○ 10 papers in training set
Top 0.2%
0.8%
27
Frontiers in Cellular and Infection Microbiology
○ 109 papers in training set
Top 4%
0.8%
28
Microbial Genomics
● 225 papers in training set
Top 3%
0.8%
29
Genomics
○ 64 papers in training set
Top 2%
0.8%
30
ISME Communications
◐ 120 papers in training set
Top 2%
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.