Output details

Gaussian process modelling of latent chemical species: applications to inferring transcription factor activities

<28> Transcription factors play a key role in gene expression but their concentrations are very expensive to measure, often prohibitively for high throughput biological experiments. This paper uses Gaussian process models and simple mechanistic models of gene regulation to indirectly infer these concentrations from gene expression measurements. The approach is much cheaper than direct attempts to measure transcription factors. The work extends a NIPS paper (48 GoogleScholar citations) and was instrumental in introducing Gaussian process models to the computational biology audience. They have now become a standard technique in that domain (GoogleScholar 45 citations).