Learning signaling network structures with sparsely distributed data
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...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Mary Ann Liebert, Inc.
2010
|
| Online Access: | http://hdl.handle.net/1721.1/60319 |
| _version_ | 1826201996911181824 |
|---|---|
| author | Sachs, Karen Itani, Solomon Carlisle, Jennifer Nolan, Garry P. Pe'er, Dana Lauffenburger, Douglas A. |
| author2 | Massachusetts Institute of Technology. Department of Biological Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Biological Engineering Sachs, Karen Itani, Solomon Carlisle, Jennifer Nolan, Garry P. Pe'er, Dana Lauffenburger, Douglas A. |
| author_sort | Sachs, Karen |
| collection | MIT |
| description | 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. |
| first_indexed | 2024-09-23T12:00:18Z |
| format | Article |
| id | mit-1721.1/60319 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T12:00:18Z |
| publishDate | 2010 |
| publisher | Mary Ann Liebert, Inc. |
| record_format | dspace |
| spelling | mit-1721.1/603192022-09-27T23:25:34Z Learning signaling network structures with sparsely distributed data Sachs, Karen Itani, Solomon Carlisle, Jennifer Nolan, Garry P. Pe'er, Dana Lauffenburger, Douglas A. Massachusetts Institute of Technology. Department of Biological Engineering Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Lauffenburger, Douglas A. Lauffenburger, Douglas A. Itani, Solomon Carlisle, Jennifer 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. National Institutes of Health (U.S.) (grant AI06584) Burroughs Wellcome Fund National Institutes of Health (U.S.) (U19 AI057229) National Institutes of Health (U.S.) (2P01 AI36535) National Institutes of Health (U.S.) (U19 AI062623) National Institutes of Health (U.S.) (R01-AI065824) National Institutes of Health (U.S.) (1P50 CA114747) National Institutes of Health (U.S.) (2P01 CA034233-22A1) National Cancer Institute (U.S.) (grant U54 RFA-CA-05-024) Leukemia & Lymphoma Society of America (grant 7017-6) Leukemia & Lymphoma Society of America (postdoctoral fellowship) National Institutes of Health (U.S.) (HHSN272200700038C) 2010-12-17T21:50:09Z 2010-12-17T21:50:09Z 2009-02 Article http://purl.org/eprint/type/JournalArticle 1066-5277 1557-8666 http://hdl.handle.net/1721.1/60319 Sachs, Karen et al. “Learning Signaling Network Structures with Sparsely Distributed Data.” Journal of Computational Biology 16.2 (2010): 201-212. © 2009 Mary Ann Liebert, Inc. en_US http://dx.doi.org/10.1089/cmb.2008.07TT Journal of Computational Biology Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Mary Ann Liebert, Inc. Prof. Lauffenburger |
| spellingShingle | Sachs, Karen Itani, Solomon Carlisle, Jennifer Nolan, Garry P. Pe'er, Dana Lauffenburger, Douglas A. Learning signaling network structures with sparsely distributed data |
| title | Learning signaling network structures with sparsely distributed data |
| title_full | Learning signaling network structures with sparsely distributed data |
| title_fullStr | Learning signaling network structures with sparsely distributed data |
| title_full_unstemmed | Learning signaling network structures with sparsely distributed data |
| title_short | Learning signaling network structures with sparsely distributed data |
| title_sort | learning signaling network structures with sparsely distributed data |
| url | http://hdl.handle.net/1721.1/60319 |
| work_keys_str_mv | AT sachskaren learningsignalingnetworkstructureswithsparselydistributeddata AT itanisolomon learningsignalingnetworkstructureswithsparselydistributeddata AT carlislejennifer learningsignalingnetworkstructureswithsparselydistributeddata AT nolangarryp learningsignalingnetworkstructureswithsparselydistributeddata AT peerdana learningsignalingnetworkstructureswithsparselydistributeddata AT lauffenburgerdouglasa learningsignalingnetworkstructureswithsparselydistributeddata |