Back

Teasing out Missing Reactions in Genome-scale Metabolic Networks through Deep Learning

Chen, C.; Liao, C.; Liu, Y.-Y.

2022-06-29 bioinformatics
10.1101/2022.06.27.497720 bioRxiv
Show abstract

GEnome-scale Metabolic models (GEMs) are powerful tools to predict cellular metabolism and physiological states in living organisms. However, due to our imperfect knowledge of metabolic processes, even highly curated GEMs have knowledge gaps (e.g., missing reactions). Existing gap-filling methods typically require phenotypic data as input to tease out missing reactions. We still lack a computational method for rapid and accurate gap-filling of metabolic networks before experimental data is available. Here we present a deep learning-based method -- CHEbyshev Spectral HyperlInk pREdictor (CHESHIRE) -- to predict missing reactions in GEMs purely from metabolic network topology. We demonstrate that CHESHIRE outperforms other topology-based methods in predicting artificially removed reactions over 926 high- and intermediate-quality GEMs. Furthermore, CHESHIRE is able to improve the phenotypic predictions of 49 draft GEMs for fermentation products and amino acids secretions. Both types of validation suggest that CHESHIRE is a powerful tool for GEM curation to reveal unknown links between reactions and observed metabolic phenotypes.

Matching journals

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

1
Nature Communications
○ 5641 papers in training set
Top 0.8%
39.4%
Similar papers in this journal
2
Nature Methods
○ 385 papers in training set
Top 2%
4.8%
Similar papers in this journal
3
Nature Machine Intelligence
○ 70 papers in training set
Top 0.6%
4.3%
Similar papers in this journal
4
Bioinformatics
◐ 1204 papers in training set
Top 5%
3.2%
Similar papers in this journal
50% of probability mass above
5
Genome Biology
○ 637 papers in training set
Top 4%
3.2%
Similar papers in this journal
6
Cell Systems
○ 201 papers in training set
Top 2%
2.8%
7
Nature Biotechnology
○ 172 papers in training set
Top 2%
2.6%
8
Briefings in Bioinformatics
◐ 354 papers in training set
Top 3%
2.4%
9
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 21%
2.4%
10
Advanced Science
○ 286 papers in training set
Top 4%
2.1%
11
PLOS Computational Biology
● 1863 papers in training set
Top 13%
2.1%
12
iScience
○ 1154 papers in training set
Top 13%
2.1%
13
Communications Biology
○ 993 papers in training set
Top 12%
1.9%
14
Cell Reports Methods
○ 165 papers in training set
Top 2%
1.7%
15
Nucleic Acids Research
◐ 1281 papers in training set
Top 9%
1.5%
16
Nature Computational Science
○ 55 papers in training set
Top 0.8%
1.4%
17
Science Advances
● 1243 papers in training set
Top 25%
1.1%
18
Scientific Reports
○ 3612 papers in training set
Top 63%
1.1%
19
Nature Chemical Biology
○ 119 papers in training set
Top 2%
1.1%
20
Nature
○ 645 papers in training set
Top 8%
1.1%
21
Nature Microbiology
○ 155 papers in training set
Top 3%
1.0%
22
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 4%
1.0%
23
eLife
● 5828 papers in training set
Top 67%
0.8%
24
Genome Research
● 468 papers in training set
Top 6%
0.8%
25
Nature Plants
○ 94 papers in training set
Top 2%
0.8%
26
iMeta
○ 10 papers in training set
Top 0.2%
0.8%
27
Cell Genomics
○ 172 papers in training set
Top 4%
0.8%

"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.