Back

Sensitive clustering of protein sequences at tree-of-life scale using DIAMOND DeepClust

Buchfink, B.; Ashkenazy, H.; Reuter, K.; Kennedy, J. A.; Drost, H.-G.

2023-01-25 genomics Community evaluation
10.1101/2023.01.24.525373 bioRxiv
Show abstract

The biosphere genomics era is transforming life science research, but existing methods struggle to efficiently reduce the vast dimensionality of the protein universe. We present DIAMOND DeepClust, an ultra-fast cascaded clustering method optimized to cluster the 19 billion protein sequences currently defining the protein biosphere. As a result, we detect 1.7 billion clusters of which 32% hold more than one sequence. This means that 544 million clusters represent 94% of all known proteins, illustrating that clustering across the tree of life can significantly accelerate comparative studies in the Earth BioGenome era.

Matching journals

The top 1 journal accounts for 50% of the predicted probability mass.

1
Nature Methods
○ 385 papers in training set
Top 0.1%
58.3%
50% of probability mass above
2
Nature Biotechnology
○ 172 papers in training set
Top 0.1%
12.4%
3
Nature Communications
○ 5641 papers in training set
Top 23%
7.1%
4
Nature
○ 645 papers in training set
Top 4%
3.2%
5
Nature Computational Science
○ 55 papers in training set
Top 0.2%
3.2%
6
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 25%
2.1%
7
Cell Reports Methods
○ 165 papers in training set
Top 2%
1.5%
8
Communications Biology
○ 993 papers in training set
Top 23%
1.1%
9
Cell Genomics
○ 172 papers in training set
Top 3%
1.1%
10
Genome Biology
○ 637 papers in training set
Top 8%
1.0%
11
Nature Machine Intelligence
○ 70 papers in training set
Top 3%
0.8%
12
Genome Research
● 468 papers in training set
Top 6%
0.8%
13
Science
● 477 papers in training set
Top 9%
0.8%
14
Molecular Biology and Evolution
◐ 542 papers in training set
Top 5%
0.8%
15
Nature Genetics
○ 286 papers in training set
Top 6%
0.6%
16
Bioinformatics
◐ 1204 papers in training set
Top 10%
0.6%