Skip to main content

Table 1 The list of all features considered prior to feature selection

From: Using epigenomics data to predict gene expression in lung cancer

  Average M value (Methylation) Average Log Fold Change (Methylation) Number of hypermethylated probes Number of hypomethylated probes Single nucleotide composition Dinucleotide composition Trinucleotide composition Length of segment Histone reads Histone read comparisons (difference of reads/average of reads) Conservation scores (PHASTCONS)  
TSS 1500 TSS1500_avgMval TSS1500_avglogFC TSS1500_numHyper TSS1500_numHypo TSS1500_A TSS1500_AA TSS1500_AAA -- TSS1500_S27 TSS1500_A27_minus_S27_divavg TSS1500_vertebrate  
TSS 200 TSS200_avgMval TSS200_avglogFC TSS200_numHyper TSS200_numHypo TSS200_A TSS200_AA TSS200_AAA -- TSS200_S27 TSS200_A27_minus_S27_divavg TSS200_vertebrate  
UTR5 UTR5_avgMval UTR5_avglogFC UTR5_numHyper UTR5_numHypo UTR5_A UTR5_AA UTR5_AAA UTR5_length UTR5_S27 UTR5_A27_minus_S27_divavg UTR5_vertebrate  
First exon first_exon_avgMval first_exon_avglogFC first_exon_numHyper first_exon_numHypo first_exon_A first_exon_AA first_exon_AAA first_exon_length first_exon_S27 first_exon_A27_minus_S27_divavg first_exon_vertebrate  
First Intron first_intron_avgMval first_intron_avglogFC first_intron_numHyper first_intron_numHypo first_intron_A first_intron_AA first_intron_AAA first_intron_length first_intron_S27 first_intron_A27_minus_S27_divavg first_intron_vertebrate  
Exon Body exon_avgMval exon_avglogFC exon_numHyper exon_numHypo exon_A exon_AA exon_AAA exon_length exon_S27 exon_A27_minus_S27_divavg exon_vertebrate  
Intron Body intron_avgMval intron_avglogFC intron_numHyper intron_numHypo intron_A intron_AA intron_AAA intron_length intron_S27 intron_A27_minus_S27_divavg intron_vertebrate  
Coding Region (CDS) CDS_avgMval CDS_avglogFC CDS_numHyper CDS_numHypo CDS_A CDS_AA CDS_AAA CDS_length CDS_S27 CDS_A27_minus_S27_divavg CDS_vertebrate  
Last Intron last_intron_avgMval last_intron_avglogFC last_intron_numHyper last_intron_numHypo last_intron_A last_intron_AA last_intron_AAA last_intron_length last_intron_S27 last_intron_A27_minus_S27_divavg last_intron_vertebrate  
Last Exon last_exon_avgMval last_exon_avglogFC last_exon_numHyper last_exon_numHypo last_exon_A last_exon_AA last_exon_AAA last_exon_length last_exon_S27 last_exon_A27_minus_S27_divavg last_exon_vertebrate  
UTR3 UTR3_avgMval UTR3_avglogFC UTR3_numHyper UTR3_numHypo UTR3_A UTR3_AA UTR3_AAA UTR3_length UTR3_S27 UTR3_A27_minus_S27_divavg UTR3_vertebrate  
Full Transcript fullTranscript_avgMval fullTranscript_avglogFC fullTranscript_numHyper fullTranscript_numHypo fullTranscript_A fullTranscript_AA fullTranscript_AAA fullTranscript_length fullTranscript_S27 fullTranscript_A27_minus_S27_divavg fullTranscript_vertebrate  
Single Exon single_exon_avgMval single_exon_avglogFC single_exon_numHyper single_exon_numHypo single_exon_A single_exon_AA single_exon_AAA single_exon_length single_exon_S27 single_exon_A27_minus_S27_divavg single_exon_vertebrate  
Single Intron single_intron_avgMval single_intron_avglogFC single_intron_numHyper single_intron_numHypo single_intron_A single_intron_AA single_intron_AAA single_intron_length single_intron_S27 single_intron_A27_minus_S27_divavg single_intron_vertebrate  
Total Features 14 14 14 14 56 224 896 12 84 42 42 1412
Exon-exon junction distances: Maximum distance to 5' end Maximum distance to 3' end Minimum distance to 5' end Minimum distance to 3' end Average distance to 5' end Average Distance to 3' end       
Hypermethylated maxHyperTo5 maxHyperTo3 minHyperTo5 minHyperTo3 avgHyperTo5 avgHyperTo3       
Hypomethylated maxHypoTo5 maxHypoTo3 minHypoTo5 minHypoTo3 avgHypoTo5 avgHypoTo3       
Total Features 2 2 2 2 2 2 12