netDx: interpretable patient classification using integrated patient similarity networks

Abstract Patient classification has widespread biomedical and clinical applications, including diagnosis, prognosis, and treatment response prediction. A clinically useful prediction algorithm should be accurate, generalizable, be able to integrate diverse data types, and handle sparse data. A clini...

Full description

Saved in:
Bibliographic Details
Main Authors: Shraddha Pai, Shirley Hui, Ruth Isserlin, Muhammad A Shah, Hussam Kaka, Gary D Bader
Format: Article
Language:English
Published: Springer Nature 2019-03-01
Series:Molecular Systems Biology
Subjects:
Online Access:https://doi.org/10.15252/msb.20188497
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849389036927451136
author Shraddha Pai
Shirley Hui
Ruth Isserlin
Muhammad A Shah
Hussam Kaka
Gary D Bader
author_facet Shraddha Pai
Shirley Hui
Ruth Isserlin
Muhammad A Shah
Hussam Kaka
Gary D Bader
author_sort Shraddha Pai
collection DOAJ
description Abstract Patient classification has widespread biomedical and clinical applications, including diagnosis, prognosis, and treatment response prediction. A clinically useful prediction algorithm should be accurate, generalizable, be able to integrate diverse data types, and handle sparse data. A clinical predictor based on genomic data needs to be interpretable to drive hypothesis‐driven research into new treatments. We describe netDx, a novel supervised patient classification framework based on patient similarity networks, which meets these criteria. In a cancer survival benchmark dataset integrating up to six data types in four cancer types, netDx significantly outperforms most other machine‐learning approaches across most cancer types. Compared to traditional machine‐learning‐based patient classifiers, netDx results are more interpretable, visualizing the decision boundary in the context of patient similarity space. When patient similarity is defined by pathway‐level gene expression, netDx identifies biological pathways important for outcome prediction, as demonstrated in breast cancer and asthma. netDx can serve as a patient classifier and as a tool for discovery of biological features characteristic of disease. We provide a free software implementation of netDx with automation workflows.
format Article
id doaj-art-0309d2c4a4e24c699be79e46aa0bf371
institution Kabale University
issn 1744-4292
language English
publishDate 2019-03-01
publisher Springer Nature
record_format Article
series Molecular Systems Biology
spelling doaj-art-0309d2c4a4e24c699be79e46aa0bf3712025-08-20T03:42:04ZengSpringer NatureMolecular Systems Biology1744-42922019-03-0115311110.15252/msb.20188497netDx: interpretable patient classification using integrated patient similarity networksShraddha Pai0Shirley Hui1Ruth Isserlin2Muhammad A Shah3Hussam Kaka4Gary D Bader5The Donnelly Centre, University of TorontoThe Donnelly Centre, University of TorontoThe Donnelly Centre, University of TorontoThe Donnelly Centre, University of TorontoThe Donnelly Centre, University of TorontoThe Donnelly Centre, University of TorontoAbstract Patient classification has widespread biomedical and clinical applications, including diagnosis, prognosis, and treatment response prediction. A clinically useful prediction algorithm should be accurate, generalizable, be able to integrate diverse data types, and handle sparse data. A clinical predictor based on genomic data needs to be interpretable to drive hypothesis‐driven research into new treatments. We describe netDx, a novel supervised patient classification framework based on patient similarity networks, which meets these criteria. In a cancer survival benchmark dataset integrating up to six data types in four cancer types, netDx significantly outperforms most other machine‐learning approaches across most cancer types. Compared to traditional machine‐learning‐based patient classifiers, netDx results are more interpretable, visualizing the decision boundary in the context of patient similarity space. When patient similarity is defined by pathway‐level gene expression, netDx identifies biological pathways important for outcome prediction, as demonstrated in breast cancer and asthma. netDx can serve as a patient classifier and as a tool for discovery of biological features characteristic of disease. We provide a free software implementation of netDx with automation workflows.https://doi.org/10.15252/msb.20188497multimodal data integrationmulti‐omicspatient similarity networksprecision medicinesupervised machine learning
spellingShingle Shraddha Pai
Shirley Hui
Ruth Isserlin
Muhammad A Shah
Hussam Kaka
Gary D Bader
netDx: interpretable patient classification using integrated patient similarity networks
Molecular Systems Biology
multimodal data integration
multi‐omics
patient similarity networks
precision medicine
supervised machine learning
title netDx: interpretable patient classification using integrated patient similarity networks
title_full netDx: interpretable patient classification using integrated patient similarity networks
title_fullStr netDx: interpretable patient classification using integrated patient similarity networks
title_full_unstemmed netDx: interpretable patient classification using integrated patient similarity networks
title_short netDx: interpretable patient classification using integrated patient similarity networks
title_sort netdx interpretable patient classification using integrated patient similarity networks
topic multimodal data integration
multi‐omics
patient similarity networks
precision medicine
supervised machine learning
url https://doi.org/10.15252/msb.20188497
work_keys_str_mv AT shraddhapai netdxinterpretablepatientclassificationusingintegratedpatientsimilaritynetworks
AT shirleyhui netdxinterpretablepatientclassificationusingintegratedpatientsimilaritynetworks
AT ruthisserlin netdxinterpretablepatientclassificationusingintegratedpatientsimilaritynetworks
AT muhammadashah netdxinterpretablepatientclassificationusingintegratedpatientsimilaritynetworks
AT hussamkaka netdxinterpretablepatientclassificationusingintegratedpatientsimilaritynetworks
AT garydbader netdxinterpretablepatientclassificationusingintegratedpatientsimilaritynetworks