%0 Generic %A Nor, Bahiyah %A Young, Neil %A Korhonen, Pasi %A Hall, Ross %A Tan, Patrick %A Lonie, Andrew %A Gasser, Robin %D 2016 %T Additional file 1: of Pipeline for the identification and classification of ion channels in parasitic flatworms %U https://springernature.figshare.com/articles/dataset/Additional_file_1_of_Pipeline_for_the_identification_and_classification_of_ion_channels_in_parasitic_flatworms/4330763 %R 10.6084/m9.figshare.c.3600389_D2.v1 %2 https://springernature.figshare.com/ndownloader/files/7054424 %K Ion channels %K Identification %K Classification %K Parasitic flatworms %K Bioinformatic pipeline %X Table S1. Sequence counts per ion channel family obtained from the KEGG and SwissProt databases and included in the training and test datasets. Table S2. Accession numbers of ion channels selected for support vector machine model training. Table S3. The number of sequences in the testing dataset before and after BLASTp analyses. Table S4. The number of identified test data sequences from humans and C. elegans within each group and divided into known ion channel and non-ion channel datasets. Table S5. Cross-validation, training and testing accuracies of each model. Table S6. Final tables of confusion matrices for the “Classifier” and “Dipeptide” models. Table S7. Summary of flatworm ion channels predicted using the MuSICC identification and classification pipeline with high and medium confidence. Table S8. Complete set of flatworm ion channels predicted using the MuSICC identification and classification pipeline. (XLS 2960 kb) %I figshare