CoChat
Sign Up
Cited by 122Cancer Genomics and DiagnosticsGenomics and Rare DiseasesBioinformatics and Genomic Networks

The DOI matches its Crossref record; 55 of the 55 references it cites were found in a registry or an index.

deepDriver: Predicting Cancer Driver Genes Based on Somatic Mutations Using Deep Convolutional Neural Networks

Open access
Luo, Ping, Ding, Yulian, Lei, Xiujuan, Wu, Fang-Xiang·2019·Frontiers in Genetics
DOI 10.3389/fgene.2019.00013PMC PMC6361806
Open this paper in CoChat — free accountOpen PDF

Abstract

With the advances in high-throughput technologies, millions of somatic mutations have been reported in the past decade. Identifying driver genes with oncogenic mutations from these data is a critical and challenging problem. Many computational methods have been proposed to predict driver genes. Among them, machine learning-based methods usually train a classifier with representations that concatenate various types of features extracted from different kinds of data. Although successful, simply concatenating different types of features may not be the best way to fuse these data. We notice that a few types of data characterize the similarities of genes, to better integrate them with other data and improve the accuracy of driver gene prediction, in this study, a deep learning-based method (deepDriver) is proposed by performing convolution on mutation-based features of genes and their neighbors in the similarity networks. The method allows the convolutional neural network to learn information within mutation data and similarity networks simultaneously, which enhances the prediction of driver genes. deepDriver achieves AUC scores of 0.984 and 0.976 on breast cancer and colorectal cancer, which are superior to the competing algorithms. Further evaluations of the top 10 predictions also demonstrate that deepDriver is valuable for predicting new driver genes.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3389/fgene.2019.00013

Cites

55 of 55 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Schematic 1-D CNN. In this study, each CONV layer is followed by a pooling layer and the CONV-POOL pattern is repeated for several times. The final structure of the model is determined by grid search.
Figure 1 Schematic 1-D CNN. In this study, each CONV layer is followed by a pooling layer and the CONV-POOL pattern is repeated for several times. The final structure of the model is determined by grid search.CC BY · PubMed Central
Figure 2 Construction of ϕi. Given the feature vectors of gi and its k nearest neighbors gs1, gs2, …, gsk, a feature matrix ϕi is constructed by arranging the 2k vectors into a 2k × nf matrix, which is then used in the convolution.
Figure 2 Construction of ϕi. Given the feature vectors of gi and its k nearest neighbors gs1, gs2, …, gsk, a feature matrix ϕi is constructed by arranging the 2k vectors into a 2k × nf matrix, which is then used in the convolution.CC BY · PubMed Central
Figure 3 ROC curves of the three algorithms obtained on the dataset of BRCA. The red, green, and magenta lines depict the ROC curves of deepDriver, 20/20+ and SVM, respectively. The AUC value of deepDriver is 0.984, which is at least 15.1% higher than that of the other two algorithms.
Figure 3 ROC curves of the three algorithms obtained on the dataset of BRCA. The red, green, and magenta lines depict the ROC curves of deepDriver, 20/20+ and SVM, respectively. The AUC value of deepDriver is 0.984, which is at least 15.1% higher than that of the other two algorithms.CC BY · PubMed Central
Figure 4 ROC curves of the three algorithms obtained on the dataset of COAD. The red, green, and magenta lines depict the ROC curves of deepDriver, 20/20+ and SVM, respectively. The AUC value of deepDriver is 0.976, which is at least 25.5% higher than that of the other two algorithms.
Figure 4 ROC curves of the three algorithms obtained on the dataset of COAD. The red, green, and magenta lines depict the ROC curves of deepDriver, 20/20+ and SVM, respectively. The AUC value of deepDriver is 0.976, which is at least 25.5% higher than that of the other two algorithms.CC BY · PubMed Central
Figure 5 ROC curves of the three algorithms obtained on the dataset of LUAD. The red, green, and magenta lines depict the ROC curves of deepDriver, 20/20+ and SVM, respectively. The AUC value of deepDriver is 0.998, which is at least 24.9% higher than that of the other two algorithms.
Figure 5 ROC curves of the three algorithms obtained on the dataset of LUAD. The red, green, and magenta lines depict the ROC curves of deepDriver, 20/20+ and SVM, respectively. The AUC value of deepDriver is 0.998, which is at least 24.9% higher than that of the other two algorithms.CC BY · PubMed Central
Figure 6 Learning curve for BRCA.
Figure 6 Learning curve for BRCA.CC BY · PubMed Central
Figure 7 Learning curve for COAD.
Figure 7 Learning curve for COAD.CC BY · PubMed Central
Figure 8 Learning curve for LUAD.
Figure 8 Learning curve for LUAD.CC BY · PubMed Central
Figure 9 ROC curves of deepDriver obtained from the second sets of driver genes.
Figure 9 ROC curves of deepDriver obtained from the second sets of driver genes.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 54 references

Cited by

Sorted by citations

Items 101–122 of 122

Related

See all

Metadata

Authors
Luo, P., Ding, Y., Lei, X., & Wu, F.-X.
Affiliations
  • University of Saskatchewan (CA)
  • Shaanxi Normal University (CN)
  • Hainan Normal University (CN)
Corresponding author
Wu, Fang-Xiang
ORCID
Venue
Frontiers in Genetics
Publisher
Frontiers Media SA
Published
2019-01-29
Volume
10
Pages
13-13
ISSN
1664-8021 (ISSN-L)
DOI
10.3389/fgene.2019.00013
PMC
PMC6361806
OpenAlex
W2913030342
Cited by
107
References
54
Citations by year
2026: 4 · 2025: 6 · 2024: 19 · 2023: 30 · 2022: 17 · 2021: 17 · 2020: 9 · 2019: 5
FWCI
4.19
Type
journal article
Language
en
Open access
Licence
Locations
  • Frontiers in Genetics (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • China Scholarship Council
  • Natural Sciences and Engineering Research Council of Canada
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Cancer Research › Cancer Genomics and Diagnostics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Genomics and Rare Diseases
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
Keywords
cancer driver genes, somatic mutations, deep convolutional neural networks, similarity networks, multi-omics integration, breast cancer, colorectal cancer, oncogenic mutations

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review