期刊
JOURNAL OF COMPUTATIONAL BIOLOGY
卷 16, 期 2, 页码 201-212出版社
MARY ANN LIEBERT, INC
DOI: 10.1089/cmb.2008.07TT
关键词
Bayesian networks; flow cytometry; graphical models; proteomics; signaling pathways
类别
资金
- NIH [AI06584, GM68762, N01-HV-28183, U19 AI057229, 2P01 AI36535, U19 AI062623, R01-AI065824, 1P50 CA114747, 2P01 CA034233-22A1, HHSN272200700038C]
- Burroughs Wellcome Fund
- NCI [U54 RFA-CA-05-024]
- LLS [7017-6]
Flow cytometric measurement of signaling protein abundances has proved particularly useful for elucidation of signaling pathway structure. The single cell nature of the data ensures a very large dataset size, providing a statistically robust dataset for structure learning. Moreover, the approach is easily scaled to many conditions in high throughput. However, the technology suffers from a dimensionality constraint: at the cutting edge, only about 12 protein species can be measured per cell, far from sufficient for most signaling pathways. Because the structure learning algorithm ( in practice) requires that all variables be measured together simultaneously, this restricts structure learning to the number of variables that constitute the flow cytometer's upper dimensionality limit. To address this problem, we present here an algorithm that enables structure learning for sparsely distributed data, allowing structure learning beyond the measurement technology's upper dimensionality limit for simultaneously measurable variables. The algorithm assesses pairwise (or n-wise) dependencies, constructs Markov neighborhoods for each variable based on these dependencies, measures each variable in the context of its neighborhood, and performs structure learning using a constrained search.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据