Additional file 4 of seqQscorer: automated quality control of next-generation sequencing data using machine learning

Additional file 4. Table of optimal models used by seqQscorer. Optimal models are the best models for each data subset (Dataset column). Dataset: species-subset-layout, generic: all data. Feature sets: RAW (raw data), MAP (genome mapping), LOC (genomic localization), TSS (transcription start sites profile). Feature Selection: method-percentage (percentage of retained features), chi-square (chi2), recursive feature elimination (RFE). Algorithm Parameters: relevant to a scikit-learn implementation.