Back

Revisiting microbe-metabolite interactions: doing better than random

Morton, J.; McDonald, D.; Aksenov, A.; Nothias-Scaglia, L.-F.; Foulds, J.; Quinn, R. A.; Badri, M.; Swenson, T.; Van Goethem, M.; Northen, T.; Vazquez-Baeza, Y.; Wang, M.; Bokulich, N.; Watters, A.; Song, S. J.; Bonneau, R.; Dorrestein, P.; Knight, R.

2019-12-16 bioinformatics
10.1101/2019.12.10.871905 bioRxiv
Show abstract

I.Recently, Quinn and Erb et al [1] made the case that when used correctly, correlation and proportionality can outperform MMvec when identifying microbe-metabolite interactions. We revisit this comparison and show that the proposed correlation and proportionality are outperformed by MMvec on real data due to their inability to deal with sparsity commonly observed in microbiome and metabolome datasets.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

1
Bioinformatics
◐ 1204 papers in training set
Top 1%
19.2%
Similar papers in this journal
2
Bioinformatics Advances
◐ 203 papers in training set
Top 0.1%
12.3%
Similar papers in this journal
3
Briefings in Bioinformatics
◐ 354 papers in training set
Top 0.4%
12.3%
Similar papers in this journal
4
Journal of Computational Biology
○ 48 papers in training set
Top 0.1%
7.0%
Similar papers in this journal
50% of probability mass above
5
BMC Bioinformatics
○ 457 papers in training set
Top 2%
5.3%
Similar papers in this journal
6
PLOS Computational Biology
● 1863 papers in training set
Top 9%
3.6%
7
Journal of Medical Internet Research
◐ 87 papers in training set
Top 0.8%
3.3%
8
Patterns
○ 78 papers in training set
Top 0.8%
2.5%
9
Genome Biology
○ 637 papers in training set
Top 4%
2.5%
10
Computational and Structural Biotechnology Journal
● 242 papers in training set
Top 2%
2.2%
11
GigaScience
◐ 212 papers in training set
Top 2%
2.2%
12
IEEE Access
● 35 papers in training set
Top 0.6%
1.8%
13
Scientific Reports
○ 3612 papers in training set
Top 56%
1.6%
14
Frontiers in Genetics
○ 230 papers in training set
Top 3%
1.4%
15
BioData Mining
○ 22 papers in training set
Top 0.3%
1.2%
16
IEEE Transactions on Computational Biology and Bioinformatics
● 20 papers in training set
Top 0.4%
1.2%
17
PLOS ONE
● 5266 papers in training set
Top 51%
1.2%
18
IEEE Journal of Biomedical and Health Informatics
● 37 papers in training set
Top 1.0%
1.0%
19
BMC Genomics
○ 406 papers in training set
Top 7%
0.9%
20
PeerJ
◐ 308 papers in training set
Top 10%
0.9%
21
Frontiers in Bioinformatics
○ 49 papers in training set
Top 1%
0.9%
22
IEEE/ACM Transactions on Computational Biology and Bioinformatics
● 38 papers in training set
Top 1.0%
0.9%
23
mSystems
● 394 papers in training set
Top 6%
0.6%
24
Nature Methods
○ 385 papers in training set
Top 7%
0.6%
25
Frontiers in Microbiology
○ 427 papers in training set
Top 9%
0.5%
26
Nature Biotechnology
○ 172 papers in training set
Top 5%
0.5%
27
Nature Computational Science
○ 55 papers in training set
Top 2%
0.5%
28
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 5%
0.5%

"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.