TY - JOUR
T1 - Techniques to cope with missing data in host-pathogen protein interaction prediction
AU - Kshirsagar, Meghana
AU - Carbonell, Jaime
AU - Klein-Seetharaman, Judith
N1 - Funding Information:
Funding: In part, Richard King Mellon Foundation, EraSysBio+ from the European Union and BMBF to SHIPREC, NIH (P50GM082251 and 2RO1LM007994-05), and NSF (CCF-1144281).
PY - 2012/9
Y1 - 2012/9
N2 - Motivation: Approaches that use supervised machine learning techniques for protein-protein interaction (PPI) prediction typically use features obtained by integrating several sources of data. Often certain attributes of the data are not available, resulting in missing values. In particular, our host-pathogen PPI datasets have a large fraction, in the range of 58-85% of missing values, which makes it challenging to apply machine learning algorithms. Results: We show that specialized techniques for missing value imputation can improve the performance of the models significantly. We use cross species information in combination with machine learning techniques like Group lasso with l1/l2 regularization. We demonstrate the benefits of our approach on two PPI prediction problems. In our first example of Salmonella-human PPI prediction, we are able to obtain high prediction accuracies with 77.6% precision and 84% recall. Comparison with various other techniques shows an improvement of 9 in F1 score over the next best technique. We also apply our method to Yersinia-human PPI prediction successfully, demonstrating the generality of our approach.
AB - Motivation: Approaches that use supervised machine learning techniques for protein-protein interaction (PPI) prediction typically use features obtained by integrating several sources of data. Often certain attributes of the data are not available, resulting in missing values. In particular, our host-pathogen PPI datasets have a large fraction, in the range of 58-85% of missing values, which makes it challenging to apply machine learning algorithms. Results: We show that specialized techniques for missing value imputation can improve the performance of the models significantly. We use cross species information in combination with machine learning techniques like Group lasso with l1/l2 regularization. We demonstrate the benefits of our approach on two PPI prediction problems. In our first example of Salmonella-human PPI prediction, we are able to obtain high prediction accuracies with 77.6% precision and 84% recall. Comparison with various other techniques shows an improvement of 9 in F1 score over the next best technique. We also apply our method to Yersinia-human PPI prediction successfully, demonstrating the generality of our approach.
UR - http://www.scopus.com/inward/record.url?scp=84866452395&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84866452395&partnerID=8YFLogxK
U2 - 10.1093/bioinformatics/bts375
DO - 10.1093/bioinformatics/bts375
M3 - Article
C2 - 22962468
AN - SCOPUS:84866452395
SN - 1367-4803
VL - 28
SP - i466-i472
JO - Bioinformatics
JF - Bioinformatics
IS - 18
M1 - bts375
ER -