BiCoN: Network-constrained biclustering of patients and omics data
Preprint
- 3 February 2020
- preprint
- Published by Cold Spring Harbor Laboratory in bioRxiv
Abstract
Motivation: Unsupervised learning approaches are frequently employed to identify patient subgroups and biomarkers such as disease-associated genes. Thus, clustering and biclustering are powerful techniques often used with expression data, but are usually not suitable to unravel molecular mechanisms along with patient subgroups. To alleviate this, we developed the network-constrained biclustering approach BiCoN (Biclustering Constrained by Networks) which (i) restricts biclusters to functionally related genes connected in molecular interaction networks and (ii) maximizes the difference in gene expression between two subgroups of patients.Results: Our analyses of non-small cell lung and breast cancer gene expression data demonstrate that BiCoN clusters patients in agreement with known cancer subtypes while discovering gene subnetworks pointing to functional differences between these subtypes. Furthermore, we show that BiCoN is robust to noise and batch effects and can distinguish between high and low load of tumor-infiltrating leukocytes while identifying subnetworks related to immune cell function. In summary, BiCoN is a powerful new systems medicine tool to stratify patients while elucidating the responsible disease mechanism.Availability: PyPI package:https://pypi.org/project/biconWeb interface:https://exbio.wzw.tum.de/biconContact: olga.lazareva@tum.deSupplementary information: Supplementary data are available atBioinformaticsonline.Keywords
All Related Versions
- Published version: Bioinformatics, 37 (16), 2398.
This publication has 33 references indexed in Scilit:
- Efficient key pathway mining: combining networks and OMICS dataIntegrative Biology, 2012
- Removing Batch Effects in Analysis of Expression Microarray Data: An Evaluation of Six Batch Adjustment MethodsPLOS ONE, 2011
- A Comparison of PAM50 Intrinsic Subtyping with Immunohistochemistry and Clinical Prognostic Factors in Tamoxifen-Treated Estrogen Receptor–Positive Breast CancerClinical Cancer Research, 2010
- A comparison of batch effect removal methods for enhancement of prediction performance using MAQC-II microarray gene expression dataThe Pharmacogenomics Journal, 2010
- QUBIC: a qualitative biclustering algorithm for analyses of gene expression dataNucleic Acids Research, 2009
- Supervised Risk Predictor of Breast Cancer Based on Intrinsic SubtypesJournal of Clinical Oncology, 2009
- A systematic comparison and evaluation of biclustering methods for gene expression dataBioinformatics, 2006
- Normalized cuts and image segmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Implementing agglomerative hierarchic clustering algorithms for use in document retrievalInformation Processing & Management, 1986
- Direct Clustering of a Data MatrixJournal of the American Statistical Association, 1972