Back

Constructing early diagnosis model of colorectal cancer based on expression profile

wang, s.; wang, y.; wang, s.

2020-01-06 genetics
10.1101/2020.01.06.895730 bioRxiv
Show abstract

purposeIn order to break through the restrictive factors such as the fecal occult blood test (FOBT) in the routine detection of bowel cancer, which is susceptible to diet and drugs, and the high cost and inconvenience of microscopy, Seeking a possible FOBT alternative. MethodsAn error back propagation neural network (BPNN) algorithm was used to construct a CRC diagnosis model based on expression profiles. ResultsThe accuracy of the model on the training and test sets is 0.943 and 0.935, respectively. AUC all reached above 0.95. ConclusionThe CRC molecular detection model based on expression profiles provides a possible alternative to FOBT. It provides a new approach and method for the clinical diagnosis of bowel cancer.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

1
PLOS ONE
● 5266 papers in training set
Top 7%
22.4%
Similar papers in this journal
2
BioMed Research International
○ 28 papers in training set
Top 0.1%
12.2%
Similar papers in this journal
3
Scientific Reports
○ 3612 papers in training set
Top 9%
6.9%
Similar papers in this journal
4
Frontiers in Genetics
○ 230 papers in training set
Top 0.5%
5.0%
Similar papers in this journal
5
PeerJ
◐ 308 papers in training set
Top 1%
4.4%
Similar papers in this journal
50% of probability mass above
6
Bioscience Reports
● 27 papers in training set
Top 0.2%
3.3%
7
Biochemistry and Biophysics Reports
○ 30 papers in training set
Top 0.1%
3.3%
8
Biology
○ 45 papers in training set
Top 0.1%
2.5%
9
Heliyon
○ 152 papers in training set
Top 2%
2.4%
10
Frontiers in Medicine
○ 120 papers in training set
Top 1%
2.2%
11
Genes
○ 144 papers in training set
Top 1%
1.9%
12
Molecular Biology Reports
○ 21 papers in training set
Top 0.3%
1.8%
13
eLife
● 5828 papers in training set
Top 49%
1.8%
14
Genomics
○ 64 papers in training set
Top 0.9%
1.5%
15
Gene
○ 46 papers in training set
Top 0.9%
1.4%
16
Medicine
○ 31 papers in training set
Top 1%
1.4%
17
Frontiers in Oncology
○ 103 papers in training set
Top 2%
1.2%
18
Cancers
○ 213 papers in training set
Top 4%
1.2%
19
PLOS Computational Biology
● 1863 papers in training set
Top 16%
1.2%
20
Genes to Cells
○ 25 papers in training set
Top 0.3%
1.2%
21
Applied Sciences
○ 25 papers in training set
Top 0.6%
1.1%
22
Briefings in Bioinformatics
◐ 354 papers in training set
Top 6%
1.0%
23
International Journal of Biological Macromolecules
○ 76 papers in training set
Top 2%
0.9%
24
Mathematical Biosciences and Engineering
● 23 papers in training set
Top 0.8%
0.9%
25
Journal of Clinical Medicine
○ 97 papers in training set
Top 4%
0.9%
26
Cell Death & Disease
147 papers in training set
Top 3%
0.9%
27
Journal of Medical Virology
○ 140 papers in training set
Top 3%
0.9%
28
International Journal of Molecular Sciences
○ 494 papers in training set
Top 14%
0.9%
29
Genomics, Proteomics & Bioinformatics
188 papers in training set
Top 2%
0.7%
30
Synthetic and Systems Biotechnology
○ 11 papers in training set
Top 0.2%
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.