Debian Codegraph @

paper/manuscript/main/tex/datasets_table.tex

raw
1 \begin{table}[htbp]
2 \centering
3 \begin{tabular}{lccrrr}
4 Data Set & Error Rate* & Read Length & \multicolumn{1}{l}{Total Read Pairs} & \multicolumn{1}{c}{Reads w/ Adapters**} & \multicolumn{1}{c}{Adapter Bases**} \\
5 \midrule
6 Simulated 1 & 0.20\% & 125 & 781,923 & 325,982 & 12,447,262 \\
7 Simulated 2 & 0.60\% & 125 & 780,899 & 325,105 & 12,416,861 \\
8 Simulated 3 & 1.20\% & 125 & 782,237 & 325,860 & 12,464,235 \\
9 GM12878 WGBS & 2.79\% & 125 & 1,000,000 & 57,130 & 3,082,003 \\
10 K562 mRNA-seq & 4.31\% & 75 & 6,100,265 & 14,384 & 749,451 \\
11 \end{tabular}%
12 \caption{Description of data sets. For the real data sets, * actual error rates are unknown -- we estimate error rates from base qualities over a sample of 10,000 read pairs; and ** total adapter content is unknown -- we provide the number of reads containing exact matches for the first 35 adapter bases, and the number of adapter bases present.}\label{datasets}%
13 \end{table}%