TY - GEN
T1 - Long-short term memory network for RNA structure profiling super-resolution
AU - WONG, Pak Kan
AU - WONG, Man Leung
AU - LEUNG, Kwong Sak
PY - 2017/11
Y1 - 2017/11
N2 - Profiling of RNAs improves understanding of cellular mechanisms, which can be essential to cure various diseases. It is estimated to take years to fully characterize the three-dimensional structure of around 200,000 RNAs in human using the mutate-and-map strategy. In order to speed up the profiling process, we propose a solution based on super-resolution. We applied five machine learning regression methods to perform RNA structure profiling super-resolution, i.e. to recover the whole data sets using self-similarity in low-resolution (undersampled) data sets. In particular, our novel Interaction Encoded Long-Short Term Memory (IELSTM) network can handle multiple distant interactions in the RNA sequences. When compared with ridge regression, LASSO regression, multilayer perceptron regression, and random forest regression, IELSTM network can reduce the mean squared error and the median absolute error by at least 33% and 31% respectively in three RNA structure profiling data sets.
AB - Profiling of RNAs improves understanding of cellular mechanisms, which can be essential to cure various diseases. It is estimated to take years to fully characterize the three-dimensional structure of around 200,000 RNAs in human using the mutate-and-map strategy. In order to speed up the profiling process, we propose a solution based on super-resolution. We applied five machine learning regression methods to perform RNA structure profiling super-resolution, i.e. to recover the whole data sets using self-similarity in low-resolution (undersampled) data sets. In particular, our novel Interaction Encoded Long-Short Term Memory (IELSTM) network can handle multiple distant interactions in the RNA sequences. When compared with ridge regression, LASSO regression, multilayer perceptron regression, and random forest regression, IELSTM network can reduce the mean squared error and the median absolute error by at least 33% and 31% respectively in three RNA structure profiling data sets.
KW - Long-short term memory
KW - Machine learning regression methods
KW - RNA structure
UR - http://commons.ln.edu.hk/sw_master/6741
U2 - 10.1007/978-3-319-71069-3_20
DO - 10.1007/978-3-319-71069-3_20
M3 - Conference paper (refereed)
SN - 9783319710686
T3 - Lecture Notes in Computer Science (LNCS) book series
SP - 255
EP - 266
BT - Theory and Practice of Natural Computing : 6th International Conference, TPNC 2017, Prague, Czech Republic, December 18-20, 2017, proceedings
PB - Springer-Verlag GmbH and Co. KG
T2 - 6th International Conference on Theory and Practice of Natural Computing
Y2 - 18 December 2017 through 20 December 2017
ER -
