TY - GEN
T1 - Dimensionality Reduction based Transfer Learning applied to Pharmacogenomics Databases
AU - Dhruba, Saugato Rahman
AU - Rahmanl, Raziur
AU - Matlockl, Kevin
AU - Ghosh, Soupatno
AU - Pal, Ranadip
N1 - Funding Information:
*This work was supported by NIH Grant R01GM122084 1 Texas Tech University, Department of Electrical and Computer Engineering, Lubbock, TX, 79409, USA ranadip.pal@ttu.edu 2 Texas Tech University, Department of Mathematics and Statistics, Lubbock, TX, 79409, USA.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/10/26
Y1 - 2018/10/26
N2 - Recent years have observed a number of Pharmacogenomics databases being published that enable testing of various predictive modeling techniques for personalized therapy applications. However, the consistencies between the databases are usually limited in spite of having significant number of common cell lines and drugs. In this article, we consider the problem of whether we can use the model learned from one secondary database to improve the prediction for the other target database. We illustrate using two pharmacogenomics databases that representing the databases using common basis vectors can improve prediction performance as compared to the naive application of a model trained on one database to another. We also elucidate the robustness of using PCA based basis vectors for scenarios with low correlated input features.
AB - Recent years have observed a number of Pharmacogenomics databases being published that enable testing of various predictive modeling techniques for personalized therapy applications. However, the consistencies between the databases are usually limited in spite of having significant number of common cell lines and drugs. In this article, we consider the problem of whether we can use the model learned from one secondary database to improve the prediction for the other target database. We illustrate using two pharmacogenomics databases that representing the databases using common basis vectors can improve prediction performance as compared to the naive application of a model trained on one database to another. We also elucidate the robustness of using PCA based basis vectors for scenarios with low correlated input features.
UR - http://www.scopus.com/inward/record.url?scp=85056613300&partnerID=8YFLogxK
U2 - 10.1109/EMBC.2018.8512457
DO - 10.1109/EMBC.2018.8512457
M3 - Conference contribution
C2 - 30440616
AN - SCOPUS:85056613300
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 1246
EP - 1249
BT - 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 18 July 2018 through 21 July 2018
ER -