Process flow for classification and clustering of fruit fly gene expression patterns

Heffel, Andreas; Stadler, Peter F.; Prohaska, Sonja J.; Kauer, Gerhard; Kuska, Jens-Peer

doi:10.1109/icip.2008.4711856

Cited by 5 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This network-based approach circumvents problems associated with traditional classification methods that rely solely on standardized images 19 and use of individual pixel classification methodologies 36, 37 . While some systems exist for classifying spatial patterns in zebrafish 17 , C. elegans 15 and Drosophila embryos 19,38–40 , previous approaches require specifically orientated and annotated images, are specific to the organism of interest, and/or often do not have single cell resolution. In particular, machine learning algorithms developed for positional dependence of patterning in Drosophila have not relied on individual cell segmentation for evolution of network connectivity over time.…”

Section: Discussionmentioning

confidence: 99%

Quantitative multivariate analysis of dynamic multicellular morphogenic trajectories

et al. 2015

View full text Add to dashboard Cite

Interrogating fundamental cell biology principles that govern tissue morphogenesis is critical to better understanding of developmental biology and engineering novel multicellular systems. Recently, functional micro-tissues derived from pluripotent embryonic stem cell (ESC) aggregates have provided novel platforms for experimental investigation; however elucidating the factors directing emergent spatial phenotypic patterns remains a significant challenge. Computational modelling techniques offer a unique complementary approach to probe mechanisms regulating morphogenic processes and provide a wealth of spatio-temporal data, but quantitative analysis of simulations and comparison to experimental data is extremely difficult. Quantitative descriptions of spatial phenomena across multiple systems and scales would enable unprecedented comparisons of computational simulations with experimental systems, thereby leveraging the inherent power of computational methods to interrogate the mechanisms governing emergent properties of multicellular biology. To address these challenges, we developed a portable pattern recognition pipeline consisting of: the conversion of cellular images into networks, extraction of novel features via network analysis, and generation of morphogenic trajectories. This novel methodology enabled the quantitative description of morphogenic pattern trajectories that could be compared across diverse systems: computational modelling of multicellular structures, differentiation of stem cell aggregates, and gastrulation of cichlid fish. Moreover, this method identified novel spatio-temporal features associated with different stages of embryo gastrulation, and elucidated a complex paracrine mechanism capable of explaining spatiotemporal pattern kinetic differences in ESC aggregates of different sizes.

show abstract

Section: Discussionmentioning

confidence: 99%

Quantitative multivariate analysis of dynamic multicellular morphogenic trajectories

et al. 2015

View full text Add to dashboard Cite

show abstract

“…As previously explained in our recent publication [14] the elaborated processing pipeline include six basic steps. The preprocessing (i) consists of a shading correction and a contrast optimization method resulting in a "'clean image"'.…”

Section: Methodsmentioning

confidence: 99%

“…The GEP extraction (v) step has been modified from the GMM method described in [14] to a HSV color space transformation. The pattern is extracted by taking the color intensity information from the V-channel and setting all values smaller than 20 percent to zero (denoising).…”

Section: Methodsmentioning

confidence: 99%

Automatic Classification of Embryonic Fruit Fly Gene Expression Patterns

Heffel

Prohaska

Stadler

et al. 2009

Bildverarbeitung Für Die Medizin 2009

Self Cite

View full text Add to dashboard Cite

Abstract. Carefully studied in-situ hybridization Gene expression patterns (GEP) can provide a first glance at possible relationships among genes. Automatic comparative analysis tools are an indispensable requirement to manage the constantly growing amount of such GEP images. We present here an automated processing pipeline for Segmenting, Classification, and Clustering large-scale sets of Drosophila melanogaster GEP images that facilitates automatic GEP analysis.

show abstract

“…Peng et al [15] developed an automatic image annotation framework using three different feature representations (based on Gaussian Mixture Models, Principal Component Analysis (PCA) and wavelet functions) and several classifiers, including Linear Discriminant Analysis (LDA), Support Vector Machines (SVM) and Quadratic Discriminant Analysis (QDA). Heffel et al [16] proposed an embryo outline extraction and transformation and conversion to Fourier coefficients-based feature representation.…”

Section: Introductionmentioning

confidence: 99%

Automatic Annotation of Spatial Expression Patterns via Sparse Bayesian Factor Models

2011

View full text Add to dashboard Cite

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.

show abstract

Process flow for classification and clustering of fruit fly gene expression patterns

Cited by 5 publications

References 15 publications

Quantitative multivariate analysis of dynamic multicellular morphogenic trajectories

Quantitative multivariate analysis of dynamic multicellular morphogenic trajectories

Automatic Classification of Embryonic Fruit Fly Gene Expression Patterns

Automatic Annotation of Spatial Expression Patterns via Sparse Bayesian Factor Models

Contact Info

Product

Resources

About