Back

Self-supervised deep learning for pan-cancer mutation prediction from histopathology

Saldanha, O. L.; Loeffler, C. M. L.; Niehues, J. M.; van Treeck, M.; Seraphin, T. P.; Hewitt, K. J.; Cifci, D.; Veldhuizen, G. P.; Ramesh, S.; Pearson, A. T.; Kather, J. N.

2022-09-16 cancer biology
10.1101/2022.09.15.507455 bioRxiv
Show abstract

The histopathological phenotype of tumors reflects the underlying genetic makeup. Deep learning can predict genetic alterations from tissue morphology, but it is unclear how well these predictions generalize to external datasets. Here, we present a deep learning pipeline based on self-supervised feature extraction which achieves a robust predictability of genetic alterations in two large multicentric datasets of seven tumor types.

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

1
Nature Communications
○ 5641 papers in training set
Top 9%
18.4%
2
Nature Cancer
○ 39 papers in training set
Top 0.1%
18.4%
3
npj Precision Oncology
○ 53 papers in training set
Top 0.1%
15.0%
50% of probability mass above
4
Nature Methods
○ 385 papers in training set
Top 3%
3.5%
5
Nature
○ 645 papers in training set
Top 4%
3.2%
6
Cancer Discovery
● 66 papers in training set
Top 0.8%
3.1%
7
Cancer Cell
○ 42 papers in training set
Top 0.5%
2.4%
8
Cell Reports Medicine
○ 153 papers in training set
Top 1%
2.4%
9
Cancer Research
● 130 papers in training set
Top 1%
2.4%
10
Nature Genetics
○ 286 papers in training set
Top 3%
1.7%
11
npj Digital Medicine
○ 118 papers in training set
Top 2%
1.7%
12
Patterns
○ 78 papers in training set
Top 1%
1.7%
13
Genome Medicine
○ 183 papers in training set
Top 3%
1.5%
14
Nature Medicine
○ 125 papers in training set
Top 2%
1.5%
15
eBioMedicine
○ 183 papers in training set
Top 3%
1.4%
16
Molecular Systems Biology
○ 162 papers in training set
Top 2%
1.3%
17
Communications Medicine
○ 113 papers in training set
Top 3%
1.3%
18
Science Advances
● 1243 papers in training set
Top 25%
1.1%
19
Cell Genomics
○ 172 papers in training set
Top 3%
1.1%
20
Scientific Reports
○ 3612 papers in training set
Top 74%
0.8%
21
Cell Reports Methods
○ 165 papers in training set
Top 4%
0.8%
22
Communications Biology
○ 993 papers in training set
Top 35%
0.6%
23
iScience
○ 1154 papers in training set
Top 40%
0.6%
24
EMBO Molecular Medicine
○ 95 papers in training set
Top 3%
0.6%
25
Nature Biotechnology
○ 172 papers in training set
Top 5%
0.6%