Automatic Annotation of Spatial Expression Patterns via Sparse Bayesian Factor Models

Advances in reporters for gene expression have made it possible to document and quantify expression patterns in 2D–4D. In contrast to microarrays, which provide data for many genes but averaged and/or at low resolution, images reveal the high spatial dynamics of gene expression. Developing computational methods to compare, annotate, and model gene expression based on images is imperative, considering that available data are rapidly increasing. We have developed a sparse Bayesian factor analysis model in which the observed expression diversity of among a large set of high-dimensional images is modeled by a small number of hidden common factors. We apply this approach on embryonic expression patterns from a Drosophila RNA in situ image database, and show that the automatically inferred factors provide for a meaningful decomposition and represent common co-regulation or biological functions. The low-dimensional set of factor mixing weights is further used as features by a classifier to annotate expression patterns with functional categories. On human-curated annotations, our sparse approach reaches similar or better classification of expression patterns at different developmental stages, when compared to other automatic image annotation methods using thousands of hard-to-interpret features. Our study therefore outlines a general framework for large microscopy data sets, in which both the generative model itself, as well as its application for analysis tasks such as automated annotation, can provide insight into biological questions. Author Summary: High throughput image acquisition is a quickly increasing new source of data for problems in computational biology, such as phenotypic screens. Given the very diverse nature of imaging technology, samples, and biological questions, approaches are oftentimes very tailored and ad hoc to a specific data set. In particular, the image-based genome scale profiling of gene expression patterns via approaches like in situ hybridization requires the development of accurate and automatic image analysis systems for understanding regulatory networks and development of multicellular organisms. Here, we present a computational method for automated annotation of Drosophila gene expression images. This framework allows us to extract, identify and compare spatial expression patterns, of essence for higher organisms. Based on a sparse feature extraction technique, we successfully cluster and annotate expression patterns with high reliability, and show that the model represents a “vocabulary” of basic patterns reflecting common function or regulation.