Moanna: Multi-Omics Autoencoder-Based Neural Network Algorithm for Predicting Breast Cancer Subtypes

Cancer subtyping delivers valuable insights into the study of cancer heterogeneity and fulfills an essential step toward personalized medicine. For example, studies in breast cancer have shown that cancer subtypes based on molecular differences are associated with different patient survival and trea...

Full description

Saved in:
Bibliographic Details
Main Authors: Richard Lupat, Rashindrie Perera, Sherene Loi, Jason Li
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10029336/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849233886635098112
author Richard Lupat
Rashindrie Perera
Sherene Loi
Jason Li
author_facet Richard Lupat
Rashindrie Perera
Sherene Loi
Jason Li
author_sort Richard Lupat
collection DOAJ
description Cancer subtyping delivers valuable insights into the study of cancer heterogeneity and fulfills an essential step toward personalized medicine. For example, studies in breast cancer have shown that cancer subtypes based on molecular differences are associated with different patient survival and treatment responses. However, recent studies have suggested inconsistent breast cancer subtype classifications using alternative approaches, suggesting that current methods are yet to be optimized. Existing computation-based methods have also been limited by their dependency on incomplete prior knowledge and ineffectiveness in handling high-dimensional data beyond gene expression. Here, we propose a novel deep-learning-based algorithm, Moanna, that is trained to integrate multi-omics data for predicting breast cancer subtypes. Moanna’s architecture consists of a semi-supervised Autoencoder attached to a multi-task learning network for generalizing the combination of gene expression, copy number and somatic mutation data. We trained Moanna on a subset of the METABRIC breast cancer dataset and evaluated the performance on the remaining hold-out METABRIC samples and a fully independent cohort of TCGA samples. We evaluated our use of Autoencoder against other dimensionality reduction techniques and demonstrated its superiority in learning patterns associated with breast cancer subtypes. The overall Moanna model also achieved high accuracy in predicting samples’ ER status (96%), differentiating basal-like samples (98%), and classifying samples into PAM50 subtypes (85%). Moreover, Moanna’s predicted subtypes show a stronger correlation with patient survival when compared to the original PAM50 subtypes.
format Article
id doaj-art-1a35ec6ee62d4fd793cadaba0110e28f
institution Kabale University
issn 2169-3536
language English
publishDate 2023-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-1a35ec6ee62d4fd793cadaba0110e28f2025-08-20T04:03:21ZengIEEEIEEE Access2169-35362023-01-0111109121092410.1109/ACCESS.2023.324051510029336Moanna: Multi-Omics Autoencoder-Based Neural Network Algorithm for Predicting Breast Cancer SubtypesRichard Lupat0https://orcid.org/0000-0002-6435-7100Rashindrie Perera1https://orcid.org/0000-0001-6822-2900Sherene Loi2https://orcid.org/0000-0001-6137-9171Jason Li3https://orcid.org/0000-0002-1150-3549Division of Cancer Research, Peter MacCallum Cancer Centre, Melbourne, VIC, AustraliaDivision of Cancer Research, Peter MacCallum Cancer Centre, Melbourne, VIC, AustraliaDivision of Cancer Research, Peter MacCallum Cancer Centre, Melbourne, VIC, AustraliaDivision of Cancer Research, Peter MacCallum Cancer Centre, Melbourne, VIC, AustraliaCancer subtyping delivers valuable insights into the study of cancer heterogeneity and fulfills an essential step toward personalized medicine. For example, studies in breast cancer have shown that cancer subtypes based on molecular differences are associated with different patient survival and treatment responses. However, recent studies have suggested inconsistent breast cancer subtype classifications using alternative approaches, suggesting that current methods are yet to be optimized. Existing computation-based methods have also been limited by their dependency on incomplete prior knowledge and ineffectiveness in handling high-dimensional data beyond gene expression. Here, we propose a novel deep-learning-based algorithm, Moanna, that is trained to integrate multi-omics data for predicting breast cancer subtypes. Moanna’s architecture consists of a semi-supervised Autoencoder attached to a multi-task learning network for generalizing the combination of gene expression, copy number and somatic mutation data. We trained Moanna on a subset of the METABRIC breast cancer dataset and evaluated the performance on the remaining hold-out METABRIC samples and a fully independent cohort of TCGA samples. We evaluated our use of Autoencoder against other dimensionality reduction techniques and demonstrated its superiority in learning patterns associated with breast cancer subtypes. The overall Moanna model also achieved high accuracy in predicting samples’ ER status (96%), differentiating basal-like samples (98%), and classifying samples into PAM50 subtypes (85%). Moreover, Moanna’s predicted subtypes show a stronger correlation with patient survival when compared to the original PAM50 subtypes.https://ieeexplore.ieee.org/document/10029336/Feature extractioncancer subtypingartificial neural networksmachine learningclassification algorithmscancer genomics
spellingShingle Richard Lupat
Rashindrie Perera
Sherene Loi
Jason Li
Moanna: Multi-Omics Autoencoder-Based Neural Network Algorithm for Predicting Breast Cancer Subtypes
IEEE Access
Feature extraction
cancer subtyping
artificial neural networks
machine learning
classification algorithms
cancer genomics
title Moanna: Multi-Omics Autoencoder-Based Neural Network Algorithm for Predicting Breast Cancer Subtypes
title_full Moanna: Multi-Omics Autoencoder-Based Neural Network Algorithm for Predicting Breast Cancer Subtypes
title_fullStr Moanna: Multi-Omics Autoencoder-Based Neural Network Algorithm for Predicting Breast Cancer Subtypes
title_full_unstemmed Moanna: Multi-Omics Autoencoder-Based Neural Network Algorithm for Predicting Breast Cancer Subtypes
title_short Moanna: Multi-Omics Autoencoder-Based Neural Network Algorithm for Predicting Breast Cancer Subtypes
title_sort moanna multi omics autoencoder based neural network algorithm for predicting breast cancer subtypes
topic Feature extraction
cancer subtyping
artificial neural networks
machine learning
classification algorithms
cancer genomics
url https://ieeexplore.ieee.org/document/10029336/
work_keys_str_mv AT richardlupat moannamultiomicsautoencoderbasedneuralnetworkalgorithmforpredictingbreastcancersubtypes
AT rashindrieperera moannamultiomicsautoencoderbasedneuralnetworkalgorithmforpredictingbreastcancersubtypes
AT shereneloi moannamultiomicsautoencoderbasedneuralnetworkalgorithmforpredictingbreastcancersubtypes
AT jasonli moannamultiomicsautoencoderbasedneuralnetworkalgorithmforpredictingbreastcancersubtypes