Sparse combinatorial inference with an application in cancer biology

Sach Mukherjee, Steven Pelech, Richard M. Neve, Wen Lin Kuo, Safiyyah Ziyad, Paul Spellman, Joe Gray, Terence P. Speed

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

Motivation: Combinatorial effects, in which several variables jointly influence an output or response, play an important role in biological systems. In many settings, Boolean functions provide a natural way to describe such influences. However, biochemical data using which we may wish to characterize such influences are usually subject to much variability. Furthermore, in high-throughput biological settings Boolean relationships of interest are very often sparse, in the sense of being embedded in an overall dataset of higher dimensionality. This motivates a need for statistical methods capable of making inferences regarding Boolean functions under conditions of noise and sparsity. Results: We put forward a statistical model for sparse, noisy Boolean functions and methods for inference under the model. We focus on the case in which the form of the underlying Boolean function, as well as the number and identity of its inputs are all unknown. We present results on synthetic data and on a study of signalling proteins in cancer biology.

Original languageEnglish (US)
Pages (from-to)265-271
Number of pages7
JournalBioinformatics
Volume25
Issue number2
DOIs
StatePublished - Jan 2009
Externally publishedYes

Fingerprint

Boolean functions
Boolean Functions
Biology
Cancer
Statistical Models
Noise
Neoplasms
Biological systems
Several Variables
Synthetic Data
Sparsity
Biological Systems
Statistical method
Statistical Model
High Throughput
Dimensionality
Statistical methods
Proteins
Throughput
Protein

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Biology
  • Computational Theory and Mathematics
  • Computer Science Applications
  • Computational Mathematics
  • Statistics and Probability

Cite this

Mukherjee, S., Pelech, S., Neve, R. M., Kuo, W. L., Ziyad, S., Spellman, P., ... Speed, T. P. (2009). Sparse combinatorial inference with an application in cancer biology. Bioinformatics, 25(2), 265-271. https://doi.org/10.1093/bioinformatics/btn611

Sparse combinatorial inference with an application in cancer biology. / Mukherjee, Sach; Pelech, Steven; Neve, Richard M.; Kuo, Wen Lin; Ziyad, Safiyyah; Spellman, Paul; Gray, Joe; Speed, Terence P.

In: Bioinformatics, Vol. 25, No. 2, 01.2009, p. 265-271.

Research output: Contribution to journalArticle

Mukherjee, S, Pelech, S, Neve, RM, Kuo, WL, Ziyad, S, Spellman, P, Gray, J & Speed, TP 2009, 'Sparse combinatorial inference with an application in cancer biology', Bioinformatics, vol. 25, no. 2, pp. 265-271. https://doi.org/10.1093/bioinformatics/btn611
Mukherjee, Sach ; Pelech, Steven ; Neve, Richard M. ; Kuo, Wen Lin ; Ziyad, Safiyyah ; Spellman, Paul ; Gray, Joe ; Speed, Terence P. / Sparse combinatorial inference with an application in cancer biology. In: Bioinformatics. 2009 ; Vol. 25, No. 2. pp. 265-271.
@article{046855c343544360ac3d28f83671091e,
title = "Sparse combinatorial inference with an application in cancer biology",
abstract = "Motivation: Combinatorial effects, in which several variables jointly influence an output or response, play an important role in biological systems. In many settings, Boolean functions provide a natural way to describe such influences. However, biochemical data using which we may wish to characterize such influences are usually subject to much variability. Furthermore, in high-throughput biological settings Boolean relationships of interest are very often sparse, in the sense of being embedded in an overall dataset of higher dimensionality. This motivates a need for statistical methods capable of making inferences regarding Boolean functions under conditions of noise and sparsity. Results: We put forward a statistical model for sparse, noisy Boolean functions and methods for inference under the model. We focus on the case in which the form of the underlying Boolean function, as well as the number and identity of its inputs are all unknown. We present results on synthetic data and on a study of signalling proteins in cancer biology.",
author = "Sach Mukherjee and Steven Pelech and Neve, {Richard M.} and Kuo, {Wen Lin} and Safiyyah Ziyad and Paul Spellman and Joe Gray and Speed, {Terence P.}",
year = "2009",
month = "1",
doi = "10.1093/bioinformatics/btn611",
language = "English (US)",
volume = "25",
pages = "265--271",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "2",

}

TY - JOUR

T1 - Sparse combinatorial inference with an application in cancer biology

AU - Mukherjee, Sach

AU - Pelech, Steven

AU - Neve, Richard M.

AU - Kuo, Wen Lin

AU - Ziyad, Safiyyah

AU - Spellman, Paul

AU - Gray, Joe

AU - Speed, Terence P.

PY - 2009/1

Y1 - 2009/1

N2 - Motivation: Combinatorial effects, in which several variables jointly influence an output or response, play an important role in biological systems. In many settings, Boolean functions provide a natural way to describe such influences. However, biochemical data using which we may wish to characterize such influences are usually subject to much variability. Furthermore, in high-throughput biological settings Boolean relationships of interest are very often sparse, in the sense of being embedded in an overall dataset of higher dimensionality. This motivates a need for statistical methods capable of making inferences regarding Boolean functions under conditions of noise and sparsity. Results: We put forward a statistical model for sparse, noisy Boolean functions and methods for inference under the model. We focus on the case in which the form of the underlying Boolean function, as well as the number and identity of its inputs are all unknown. We present results on synthetic data and on a study of signalling proteins in cancer biology.

AB - Motivation: Combinatorial effects, in which several variables jointly influence an output or response, play an important role in biological systems. In many settings, Boolean functions provide a natural way to describe such influences. However, biochemical data using which we may wish to characterize such influences are usually subject to much variability. Furthermore, in high-throughput biological settings Boolean relationships of interest are very often sparse, in the sense of being embedded in an overall dataset of higher dimensionality. This motivates a need for statistical methods capable of making inferences regarding Boolean functions under conditions of noise and sparsity. Results: We put forward a statistical model for sparse, noisy Boolean functions and methods for inference under the model. We focus on the case in which the form of the underlying Boolean function, as well as the number and identity of its inputs are all unknown. We present results on synthetic data and on a study of signalling proteins in cancer biology.

UR - http://www.scopus.com/inward/record.url?scp=58349111535&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58349111535&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/btn611

DO - 10.1093/bioinformatics/btn611

M3 - Article

C2 - 19038985

AN - SCOPUS:58349111535

VL - 25

SP - 265

EP - 271

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - 2

ER -