Modelling transcriptional regulation using Gaussian processes

The MIT Press eBooksPublished 7 September 2007

Neil D. Lawrence, Guido Sanguinetti, Magnus Rattray

DOI10.7551/mitpress/7503.003.0103

Citations102

TL;DR

This paper treats the protein concentration as a latent function with a Gaussian process prior, and includes the sensitivities, mRNA decay rates and baseline expression levels as hyperparameters and applies this procedure to a human leukemia dataset, focusing on the tumour repressor p53.

Abstract

Modelling the dynamics of transcriptional processes in the cell requires the knowledge of a number of key biological quantities.While some of them are relatively easy to measure, such as mRNA decay rates and mRNA abundance levels, it is still very hard to measure the active concentration levels of the transcription factor proteins that drive the process and the sensitivity of target genes to these concentrations.In this paper we show how these quantities for a given transcription factor can be inferred from gene expression levels of a set of known target genes.We treat the protein concentration as a latent function with a Gaussian process prior, and include the sensitivities, mRNA decay rates and baseline expression levels as hyperparameters.We apply this procedure to a human leukemia dataset, focusing on the tumour repressor p53 and obtaining results in good accordance with recent biological studies.

Keywords

Computer Science

Directory of Open access Books (OAPEN Foundation)

19,683 Citations2022Carl Edward Rasmussen, Christopher K. I. Williams

View PDF

The MIT Press eBooksGaussian Processes for Machine Learning

10,409 Citations2005Carl Edward Rasmussen, Christopher K. I. Williams

The book provides a long-needed, systematic and unified treatment of theoretical and practical aspects of GPs in machine learning, targeted at researchers and students in machine learning and applied statistics.

Lecture notes in statisticsBayesian Learning for Neural Networks

4,375 Citations1996Radford M. Neal

Bayesian Learning for Neural Networks shows that Bayesian methods allow complex neural network models to be used without fear of the "overfitting" that can occur with traditional neural network learning methods.

Proceedings of the National Academy of SciencesNetwork component analysis: Reconstruction of regulatory signals in biological systems

624 Citations2003James C. Liao, Riccardo Boscolo +4 more

This work develops a method, called network component analysis, for uncovering hidden regulatory signals from outputs of networked systems, when only a partial knowledge of the underlying network topology is available.

View PDF

Neural ComputationComputation with Infinite Neural Networks

152 Citations1998Christopher K. I. Williams

Genome biologyRanked prediction of p53 targets using hidden variable dynamic modeling

130 Citations2006Martino Barenco, Tomescu Daniela +4 more

A new approach, hidden variable dynamic modeling (HVDM), is presented, which derives the hidden profile of a transcription factor from time series microarray data, and generates a ranked list of predicted targets.

View PDF

BioinformaticsA tractable probabilistic model for Affymetrix probe-level analysis across multiple chips

78 Citations2005Xuejun Liu, Marta Milo +2 more

It is demonstrated how the probabilistic model can be used to estimate credibility intervals for expression levels and their log-ratios between conditions, and is much more computationally efficient than a competing hierarchical Bayesian approach that requires MCMC sampling.

Solving noisy linear operator equations by Gaussian processes: application to ordinary and partial differential equations

49 Citations2003Thore Graepel

The problem of solving stochastic linear operator equations in a Bayesian Ganssian process (GP) framework is formulated in the spirit of a collocation method based on noisy evaluations of the target function at randomly drawn or deliberately chosen points.

View PDF

BioinformaticsA probabilistic dynamical model for quantitative inference of the regulatory mechanism of transcription

37 Citations2006Guido Sanguinetti, Magnus Rattray +1 more

A novel probabilistic model to infer transcription factor activities from microarray data when the structure of the regulatory network is known is introduced, based on regression, but is rendered more flexible by sampling regression coefficients independently for each gene.

Lecture notes in computer scienceTransformations of Gaussian Process Priors

26 Citations2005Roderick Murray‐Smith, Barak A. Pearlmutter

This framework incorporates measurements of derivative information and of filtered versions of the process, thereby allowing GPs to perform sensor fusion and tomography; allows certain group invariances to be weakly enforced; and under certain conditions suitable application allows the dataset to be dramatically reduced in size.