Back

Unraveling codon usage of Escherichia coli using machine learning

Huang, B.; Hu, Y.; Chen, X.; Lin, S.

2023-02-07 systems biology
10.1101/2023.02.07.527422 bioRxiv
Show abstract

Machine learning is used to investigate the codon usage of protein-encoding genes, which is one of the fundamental questions of molecular biology. The presentation, parameter learning, and decoding of the conditional random field (CRF) model are implemented and then utilized to analyze the codon usage of the genes of Escherichia coli and its phages. Most genes of E. coli use codons conforming to the weights of the model determined by all E. coli genes. Phages use the codons like their host E. coli. Finally, the study evaluates the codon usage of several example genes in the context of the model. These results help to understand the codon usage in E. coli.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

1
Bioinformatics
◐ 1204 papers in training set
Top 2%
11.7%
Similar papers in this journal
2
BMC Bioinformatics
○ 457 papers in training set
Top 0.7%
9.6%
Similar papers in this journal
3
Briefings in Bioinformatics
◐ 354 papers in training set
Top 0.7%
9.5%
Similar papers in this journal
4
PLOS Computational Biology
● 1863 papers in training set
Top 5%
6.6%
Similar papers in this journal
5
Biosystems
○ 31 papers in training set
Top 0.1%
4.8%
Similar papers in this journal
6
PLOS ONE
● 5266 papers in training set
Top 30%
4.8%
7
Scientific Reports
○ 3612 papers in training set
Top 26%
4.0%
50% of probability mass above
8
Frontiers in Genetics
○ 230 papers in training set
Top 1%
3.2%
9
Frontiers in Molecular Biosciences
○ 102 papers in training set
Top 0.2%
3.2%
10
PeerJ
◐ 308 papers in training set
Top 4%
2.4%
11
Computers in Biology and Medicine
○ 128 papers in training set
Top 2%
2.1%
12
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 2%
1.9%
13
Nucleic Acids Research
◐ 1281 papers in training set
Top 8%
1.9%
14
Quantitative Biology
○ 12 papers in training set
Top 0.1%
1.7%
15
Bioinformatics Advances
◐ 203 papers in training set
Top 3%
1.7%
16
IEEE/ACM Transactions on Computational Biology and Bioinformatics
● 38 papers in training set
Top 0.6%
1.7%
17
Computational and Structural Biotechnology Journal
● 242 papers in training set
Top 4%
1.7%
18
iScience
○ 1154 papers in training set
Top 28%
1.1%
19
International Journal of Molecular Sciences
○ 494 papers in training set
Top 12%
1.1%
20
Frontiers in Microbiology
○ 427 papers in training set
Top 7%
1.1%
21
Computational Biology and Chemistry
○ 28 papers in training set
Top 0.7%
1.1%
22
eLife
● 5828 papers in training set
Top 63%
1.0%
23
Frontiers in Systems Biology
○ 10 papers in training set
Top 0.1%
1.0%
24
Biochimica et Biophysica Acta (BBA) - Gene Regulatory Mechanisms
○ 15 papers in training set
Top 0.2%
0.9%
25
Database
◐ 61 papers in training set
Top 0.8%
0.9%
26
Journal of Molecular Biology
○ 232 papers in training set
Top 4%
0.8%
27
Genes to Cells
○ 25 papers in training set
Top 0.5%
0.8%
28
Genomics
○ 64 papers in training set
Top 2%
0.6%
29
BMC Genomics
○ 406 papers in training set
Top 9%
0.6%
30
Entropy
○ 21 papers in training set
Top 0.4%
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.