Deep Learning Benchmarks on L1000 Gene Expression Data.

Authors:
Jennifer Wang
Jennifer Wang
University of California
United States
Steven D Sheridan
Steven D Sheridan
Massachusetts General Hospital
United States
Peter Szolovits
Peter Szolovits
Massachusetts Institute of Technology
United States
Isaac Kohane
Isaac Kohane
Harvard Medical School
United States
Stephen J Haggarty
Stephen J Haggarty
Chemical Neurobiology Laboratory
United States
Roy H Perlis
Roy H Perlis
Massachusetts General Hospital
United States

IEEE/ACM Trans Comput Biol Bioinform 2019 Apr 11. Epub 2019 Apr 11.

Gene expression data can offer deep, physiological insights beyond the static coding of the genome alone. We believe that realizing this potential requires specialized, high-capacity machine learning methods capable of using underlying biological structure, but the development of such models is hampered by the lack of published benchmark tasks and well characterized baselines.

Download full-text PDF

Source
http://dx.doi.org/10.1109/TCBB.2019.2910061DOI Listing
April 2019

Publication Analysis

Top Keywords

expression data
8
gene expression
8
potential requires
4
realizing potential
4
lack published
4
capable underlying
4
genome realizing
4
benchmark tasks
4
static coding
4
coding genome
4
published benchmark
4
development models
4
machine learning
4
models hampered
4
learning methods
4
methods capable
4
high-capacity machine
4
requires specialized
4
specialized high-capacity
4
hampered lack
4

Similar Publications