10.6084/m9.figshare.9728531.v1 Nathan Wan Nathan Wan David Weinberg David Weinberg Tzu-Yu Liu Tzu-Yu Liu Katherine Niehaus Katherine Niehaus Eric Ariazi Eric Ariazi Daniel Delubac Daniel Delubac Ajay Kannan Ajay Kannan Brandon White Brandon White Mitch Bailey Mitch Bailey Marvin Bertin Marvin Bertin Nathan Boley Nathan Boley Derek Bowen Derek Bowen James Cregg James Cregg Adam Drake Adam Drake Riley Ennis Riley Ennis Signe Fransen Signe Fransen Erik Gafni Erik Gafni Loren Hansen Loren Hansen Yaping Liu Yaping Liu Gabriel Otte Gabriel Otte Jennifer Pecson Jennifer Pecson Brandon Rice Brandon Rice Gabriel Sanderson Gabriel Sanderson Aarushi Sharma Aarushi Sharma John St. John John St. John Catherina Tang Catherina Tang Abraham Tzou Abraham Tzou Leilani Young Leilani Young Girish Putcha Girish Putcha Imran Haque Imran Haque Additional file 5: of Machine learning enables detection of early-stage colorectal cancer by whole-genome sequencing of plasma cell-free DNA Springer Nature 2019 Cell-free DNA Colorectal cancer Screening Whole-genome sequencing Early-stage cancer 2019-08-24 03:52:50 Journal contribution https://springernature.figshare.com/articles/journal_contribution/Additional_file_5_of_Machine_learning_enables_detection_of_early-stage_colorectal_cancer_by_whole-genome_sequencing_of_plasma_cell-free_DNA/9728531 Figure S4. Non-linear relationship between the total number of samples used for training and sensitivity at 85% specificity for colorectal cancer detection. The method was trained again with k-fold, except the number of training samples per fold was downsampled. The lower numbers are comparable to those available for balanced k-batch and were used to investigate decreased classifier performance due to smaller sample sizes in training. (DOCX 60 kb)