KELM-CPPpred: Kernel Extreme Learning Machine Based Prediction Model for Cell-Penetrating Peptides Poonam Pandey 1, + , Vinal Patel 2, + , Nithin V. George 2 , and Sairam S. Mallajosyula 3, * 1 Department of Biological Engineering, Indian Institute of Technology Gandhinagar, Gujarat, India, 382355 3 Department of Chemistry, Indian Institute of Technology Gandhinagar, Gujarat, India, 382355 2 Department of Electrical Engineering, Indian Institute of Technology Gandhinagar, Gujarat, India, 382355 * msairam@iitgn.ac.in + these authors contributed equally to this work SUPPLEMENTARY INFORMATION Table of Contents Supporting Material S1: Benchmark dataset information. Supporting Material S2: Feature extraction information. Supporting Material S3: Web application development. Supporting Figure S1: Schematic representation of sequence order correlation mode used in PseAAC feature vector. Supporting Figure S2: Developed web application KELM-CPPpred for CPP prediction. Supporting Figure S3: Amino acid composition and Physicochemical analysis of CPPs and Non-CPPs. Supporting Figure S4: ROC curve analysis for the proposed model for Independent dataset. Supporting Table S1: Summary of five benchmark datasets used for comparative analysis. Supporting Table S2: Annotation and coverage of MERCI motifs extracted from Cell penetrating peptides (CPP). Supporting Table S3: Comparision of the efficiency of the KELM-CPPpred server with existing servers. S-1