Back

kMermaid: Ultrafast functional classification of microbial reads

Lucas, A.; Schaffer, D. E.; Wickramasinghe, J.; Auslander, N.

2023-08-28 microbiology
10.1101/2023.08.28.555149 bioRxiv
Show abstract

Shotgun metagenomic sequencing can determine both taxonomic and functional content of microbiomes. However, current functional classification methods for metagenomic reads require substantial computational resources and yield ambiguous classifications, limiting downstream quantitative analyses. Existing k-mer based methods to classify microbial sequences into species-level groups have immensely improved taxonomic classification, but this concept has not been extended to functional classification. Here we introduce kMermaid, for classifying metagenomic reads into functional clusters of proteins. Using protein k-mers, kMermaid allows for highly accurate and ultrafast functional classification, with a fixed memory usage, and can easily be employed on a typical computer.

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

1
Genome Biology
○ 637 papers in training set
Top 0.1%
37.7%
Similar papers in this journal
2
PLOS Computational Biology
● 1863 papers in training set
Top 5%
7.5%
Similar papers in this journal
3
Microbiome
○ 154 papers in training set
Top 0.5%
6.4%
Similar papers in this journal
50% of probability mass above
4
Nature Communications
○ 5641 papers in training set
Top 28%
5.3%
Similar papers in this journal
5
GigaScience
◐ 212 papers in training set
Top 0.6%
5.2%
Similar papers in this journal
6
Bioinformatics
◐ 1204 papers in training set
Top 5%
3.9%
7
PLOS ONE
● 5266 papers in training set
Top 34%
3.9%
8
Nature Methods
○ 385 papers in training set
Top 3%
3.9%
9
Genome Research
● 468 papers in training set
Top 3%
2.0%
10
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 2%
2.0%
11
Scientific Reports
○ 3612 papers in training set
Top 55%
1.6%
12
iScience
○ 1154 papers in training set
Top 20%
1.6%
13
mSystems
● 394 papers in training set
Top 4%
1.6%
14
Nucleic Acids Research
◐ 1281 papers in training set
Top 12%
1.1%
15
Microbial Genomics
● 225 papers in training set
Top 2%
1.0%
16
Nature Biotechnology
○ 172 papers in training set
Top 4%
1.0%
17
BMC Genomics
○ 406 papers in training set
Top 8%
0.8%
18
mBio
● 833 papers in training set
Top 11%
0.8%
19
PLOS Genetics
● 862 papers in training set
Top 13%
0.8%
20
PLOS Biology
● 486 papers in training set
Top 13%
0.8%
21
BMC Bioinformatics
○ 457 papers in training set
Top 6%
0.8%
22
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 43%
0.8%
23
Cell Systems
○ 201 papers in training set
Top 6%
0.6%
24
Cell Reports Methods
○ 165 papers in training set
Top 5%
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.