Automatic annotation of spatial expression patterns via sparse Bayesian factor models.
Automatic annotation of spatial expression patterns via sparse Bayesian factor models.
复制标题
DOI：
10.1371/journal.pcbi.1002098
复制
发表时间：
2011-07
影响因子：
4.3
通讯作者：
Ohler U
中科院分区：
文献类型：
--
作者：
Pruteanu-Malinici I;Mace DL;Ohler U
基因表达报告基因的进步使得记录和量化 2D-4D 表达模式成为可能。微阵列提供许多基因的数据，但以平均和/或低分辨率提供数据，与此相反，图像揭示了基因表达的高空间动态。考虑到可用数据正在迅速增加，开发基于图像比较、注释和建模基因表达的计算方法势在必行。我们开发了一种稀疏贝叶斯因子分析模型，其中观察到的大量高维图像中的表达多样性是通过少量隐藏的共同因子来建模的。我们将这种方法应用于来自果蝇 RNA 原位图像数据库的胚胎表达模式，并表明自动推断的因子提供了有意义的分解并代表了常见的共同调节或生物功能。低维因子混合权重集进一步被分类器用作特征，以用功能类别注释表达模式。在人工管理的注释中，与使用数千个难以解释的特征的其他自动图像注释方法相比，我们的稀疏方法在不同发育阶段达到了相似或更好的表达模式分类。因此，我们的研究概述了大型显微镜数据集的一般框架，其中生成模型本身及其在自动注释等分析任务中的应用，可以提供对生物学问题的洞察。高通量图像采集是计算生物学问题（例如表型筛选）中快速增长的新数据源。鉴于成像技术、样本和生物学问题的多样性，方法通常是针对特定数据集量身定制的。特别是，通过原位杂交等方法对基因表达模式进行基于图像的基因组规模分析需要开发准确和自动的图像分析系统，以了解多细胞生物的调控网络和发育。在这里，我们提出了一种自动注释果蝇基因表达图像的计算方法。这个框架使我们能够提取、识别和比较高等生物本质上的空间表达模式。基于稀疏特征提取技术，我们成功地对表达模式进行了高可靠性的聚类和注释，并表明该模型代表了反映共同功能或调节的基本模式的“词汇”。
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. 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.
登录
查看更多内容
DOI：
10.1016/s0097-8485(96)80004-0
发表时间：
1996-03-01
期刊：
COMPUTERS & CHEMISTRY
影响因子：
--
作者：
Gribskov, M;Robinson, NL
通讯作者：
Robinson, NL
DOI：
10.1109/tpami.2005.188
发表时间：
2005-10-01
影响因子：
23.6
作者：
Mikolajczyk, K;Schmid, C
通讯作者：
Schmid, C
影响因子：
3
作者：
Costa, Ivan G.;Krause, Roland;Schliep, Alexander
通讯作者：
Schliep, Alexander
影响因子：
5.8
作者：
Mace, Daniel L.;Varnado, Nicole;Ohler, Uwe
通讯作者：
Ohler, Uwe
影响因子：
5.8
作者：
Adryan, Boris;Teichmann, Sarah A.
通讯作者：
Teichmann, Sarah A.