OncoNetExplainer: Explainable predictions of cancer types based on gene expression data

Md Rezaul Karim, Michael Cochez, Oya Beyan, Stefan Decker, Christoph Lange

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

The discovery of important biomarkers is a significant step towards understanding the molecular mechanisms of carcinogenesis; enabling accurate diagnosis for, and prognosis of, a certain cancer type. Before recommending any diagnosis, genomics data such as gene expressions (GE) and clinical outcomes need to be analyzed. However, complex nature, high dimensionality, and heterogeneity in genomics data make the overall analysis challenging. Convolutional neural networks (CNN) have shown tremendous success in solving such problems. However, neural network models are perceived mostly as 'black box' methods because of their not well-understood internal functioning. However, interpretability is important to provide insights on why a given cancer case has a certain type. Besides, finding the most important biomarkers can help in recommending more accurate treatments and drug repositioning. Moreover, the 'right to explanation' of the EU GDPR gives patients the right to know why and how an algorithm made a diagnosis decision. Hence, in this paper, we propose a new approach called OncoNetExplainer to make explainable predictions of cancer types based on GE data. We used genomics data about 9,074 cancer patients covering 33 different cancer types from the Pan-Cancer Atlas on which we trained CNN and VGG16 networks using guided-gradient class activation maps++ (GradCAM++). Further, we generate class-specific heat maps to identify significant biomarkers and computed feature importance in terms of mean absolute impact to rank top genes across all the cancer types. Quantitative and qualitative analyses show that both models exhibit high confidence at predicting the cancer types correctly giving an average precision of 96.25%. To provide comparisons with the baselines, we identified top genes, and cancer-specific driver genes using gradient boosted trees and SHapley Additive exPlanations (SHAP). Finally, our findings were validated with the annotations provided by the TumorPortal.

Original languageEnglish
Title of host publication2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)
Subtitle of host publication[Proceedings]
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages415-422
Number of pages8
ISBN (Electronic)9781728146171
ISBN (Print)9781728146188
DOIs
Publication statusPublished - 2019
Event19th International Conference on Bioinformatics and Bioengineering, BIBE 2019 - Athens, Greece
Duration: 28 Oct 201930 Oct 2019

Conference

Conference19th International Conference on Bioinformatics and Bioengineering, BIBE 2019
Country/TerritoryGreece
CityAthens
Period28/10/1930/10/19

Keywords

  • Cancer genomics
  • Explainable AI
  • Feature importance
  • Gene expression
  • GradCAM++
  • Interpretability
  • Neural networks

Fingerprint

Dive into the research topics of 'OncoNetExplainer: Explainable predictions of cancer types based on gene expression data'. Together they form a unique fingerprint.

Cite this