number of reads vs. coverage

gistfile1.r

excap_cov.df = read.table("input.txt", header=F, sep="\t")
colnames(excap_cov.df) = c("sample_name", "total_reads", "pct_mapped", "pct_dup", 
                           "mean_cov", "pct_on_target", "pct_10X", "pct_20X", "pct_50X", 
                           "mean_insert_size", "std_dev_insert_size")

# convert character of percentage into numeric
excap_cov.df$pct_dup = as.numeric(sub("%","", excap_cov.df$pct_dup))/100
excap_cov.df$pct_mapped = as.numeric(sub("%","", excap_cov.df$pct_mapped))/100


plot(excap_cov.df$total_reads, excap_cov.df$pct_50X, type="n", xlim=c(4E7, 17E7), ylim=c(0.1, 1), 
     xlab="Number of Reads (millions)", ylab="Percent of Target Bases",
     xaxt="n")
axis(1, at=c(4E7,6E7,8E7,10E7,12E7,14E7,16E7), lab=c(40,60,80,100,120,140,160), las=TRUE)
points(excap_cov.df$total_reads, excap_cov.df$pct_10X, col=2)
points(excap_cov.df$total_reads, excap_cov.df$pct_20X, col=3)
points(excap_cov.df$total_reads, excap_cov.df$pct_50X, col=4)
#points(excap_cov.df$total_reads, excap_cov.df$pct_dup*4, col=5)
#points(excap_cov.df$total_reads, excap_cov.df$pct_on_target, col=6)
abline(h=c(0.8, 0.85, 0.9, 0.95, 1), v=c(4E7,5E7,6E7), col="gray", lty=2)
#axis(2, at=0.9, lab=0.9)
legend("bottomright", c("10X", "20X", "50X"), 
       cex=1.0, col=c(2,3,4), pch=c(1))

# ####### sample input #########
# Sample_166  58813472   99.1595531037515%  6.53918450889311%  75.958748   0.720462  0.988849  0.962762  0.726212  205.337706  58.299572
# Sample_24   81387961   99.1211390588837%  7.73714057572404%  100.646632  0.699841  0.991437  0.976463  0.842493  208.112771  58.11621
# Sample_342  102884512  99.5059567372006%  8.7230955658487%   130.156246  0.720437  0.994725  0.985788  0.909254  210.253886  60.151855
# Sample_39   80207169   99.3799980647615%  7.90178783097556%  101.543205  0.715267  0.99169   0.976851  0.846229  207.140338  58.748312
# Sample_306  67518068   99.3890361317803%  6.3031817658713%   89.36837    0.734432  0.989541  0.968627  0.786992  204.999749  56.458639
# Sample_433  83194307   99.346550239309%   7.35631615063642%  106.274024  0.717374  0.991882  0.978217  0.858742  208.344091  60.73573
# Sample_409  93837178   99.313161357005%   11.4215522447073%  120.520611  0.754171  0.992857  0.981756  0.884586  200.518061  53.214942
# Sample_42   79439315   99.216979652959%   11.8172032875488%  95.268749   0.709971  0.991094  0.971653  0.813539  202.84699   57.401023
# Sample_429  75583441   99.0963999641138%  7.89564488561799%  97.773103   0.733215  0.991193  0.972376  0.819246  205.827773  57.607437
# Sample_4    78982334   99.0092176815134%  8.624254162632%    102.545717  0.742471  0.991759  0.974714  0.834647  199.473671  54.357755