Deep learning benchmarks on L1000 gene expression data
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | eng |
| Published: |
Massachusetts Institute of Technology
2019
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/1721.1/121738 |
| _version_ | 1811072341519630336 |
|---|---|
| author | McDermott, Matthew B. A.(Matthew Brian Andrew) |
| author2 | Peter Szolovits. |
| author_facet | Peter Szolovits. McDermott, Matthew B. A.(Matthew Brian Andrew) |
| author_sort | McDermott, Matthew B. A.(Matthew Brian Andrew) |
| collection | MIT |
| description | Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019 |
| first_indexed | 2024-09-23T09:04:27Z |
| format | Thesis |
| id | mit-1721.1/121738 |
| institution | Massachusetts Institute of Technology |
| language | eng |
| last_indexed | 2024-09-23T09:04:27Z |
| publishDate | 2019 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1217382019-08-07T03:03:36Z Deep learning benchmarks on L1000 gene expression data McDermott, Matthew B. A.(Matthew Brian Andrew) Peter Szolovits. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Electrical Engineering and Computer Science. Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019 Cataloged from PDF version of thesis. Includes bibliographical references (pages 57-62). Gene expression data holds the potential to offer deep, physiological insights about the dynamic state of a cell beyond the static coding of the genome alone. I believe that realizing this potential requires specialized machine learning methods capable of using underlying biological structure, but the development of such models is hampered by the lack of an empirical methodological foundation, including published benchmarks and well characterized baselines. In this work, we lay that foundation by profiling a battery of classifiers against newly defined biologically motivated classification tasks on multiple L1000 gene expression datasets. In addition, on our smallest dataset, a privately produced L1000 corpus, we profile per-subject generalizability to provide a novel assessment of performance that is lost in many typical analyses. We compare traditional classifiers, including feed-forward artificial neural networks (FF-ANNs), linear methods, random forests, decision trees, and K nearest neighbor classifiers, as well as graph convolutional neural networks (GCNNs), which augment learning via prior biological domain knowledge. We find GCNNs offer performance improvements given sufficient data, excelling at all tasks on our largest dataset. On smaller datasets, FF-ANNs offer greatest performance. Linear models significantly underperform on all dataset scales, but offer the best per-subject generalizability. Ultimately, these results suggest that structured models such as GCNNs can represent a new direction of focus for the field as our scale of data continues to increase. by Matthew B. A. McDermott. S.M. S.M. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science 2019-07-17T20:59:28Z 2019-07-17T20:59:28Z 2019 2019 Thesis https://hdl.handle.net/1721.1/121738 1102050364 eng MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582 62 pages application/pdf Massachusetts Institute of Technology |
| spellingShingle | Electrical Engineering and Computer Science. McDermott, Matthew B. A.(Matthew Brian Andrew) Deep learning benchmarks on L1000 gene expression data |
| title | Deep learning benchmarks on L1000 gene expression data |
| title_full | Deep learning benchmarks on L1000 gene expression data |
| title_fullStr | Deep learning benchmarks on L1000 gene expression data |
| title_full_unstemmed | Deep learning benchmarks on L1000 gene expression data |
| title_short | Deep learning benchmarks on L1000 gene expression data |
| title_sort | deep learning benchmarks on l1000 gene expression data |
| topic | Electrical Engineering and Computer Science. |
| url | https://hdl.handle.net/1721.1/121738 |
| work_keys_str_mv | AT mcdermottmatthewbamatthewbrianandrew deeplearningbenchmarksonl1000geneexpressiondata |