SetQuence & SetOmic: Deep Set Transformer-based Representations of Cancer Multi-Omics

Research output: Contribution to book/conference proceedings/anthology/reportConference contributionContributedpeer-review

Abstract

In oncology, Deep Learning has shown great potential to personalise tasks such as tumour type classification, based on per-patient omics data-sets. Being high dimensional, incorporation of such data in one model is a challenge, often leading to one-dimensional studies and, therefore, information loss. Instead, we first propose relying on non-fixed sets of mutated genome sequences, which can be used for supervised learning of oncology-relevant tasks by our Transformer-based Deep Neural Network, SETQUENCE. Second, we extend the model to incorporate these representations as well as multiple sources of omics data in a flexible way with SETOMIC. Evaluation, using these representations, shows improved robustness and reduced information loss compared to previous approaches, while still being computationally tractable. By means of Explainable Artificial Intelligence methods, our models are shown to be able to recapitulate the biological contribution of several features in cancer, such as individual expression loci. This validation opens the door to novel directions in multi-faceted genome-wide biomarker discovery and personalised treatment among other presently clinically relevant tasks.

Details

Original languageEnglish
Title of host publication2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022
PublisherIEEE, New York [u. a.]
Pages139-147
ISBN (electronic)9781665484626
ISBN (print)9781665484626
Publication statusPublished - 2022
Peer-reviewedYes

Publication series

Series2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022

Conference

Title2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022
Duration15 - 17 August 2022
CityOttawa
CountryCanada

External IDs

Mendeley d568ec15-527f-338d-9541-7c209549efcd
unpaywall 10.1109/cibcb55180.2022.9863058
ORCID /0000-0001-9756-6390/work/142250119

Keywords

Sustainable Development Goals

Keywords

  • Deep Neural Network, gene expression, genome, molecular sequence analysis, multi-omics, mutome, natural language processing, Set Representations