Analysis of composition changes in Romiguier’s data
d<- read.table("data_summary.csv")
Error in scan(file = file, what = what, sep = sep, quote = quote, dec = dec, :
line 2 did not have 104 elementssummary(d)
Filename Number.Invariant.Sites Number.Invariant.Sites.Excluding.Ambiguous Max.GC Max.GC.Excluding.Ambiguous
ENSG00000000005_TNMD_NT.fas : 1 Min. : 0.00 Min. : 23.0 Min. :0.3442 Min. :0.3483
ENSG00000000419_DPM1_NT.fas : 1 1st Qu.: 0.00 1st Qu.: 329.0 1st Qu.:0.5244 1st Qu.:0.5529
ENSG00000000457_SCYL3_NT.fas : 1 Median : 25.00 Median : 550.0 Median :0.5885 Median :0.6145
ENSG00000000460_C1orf112_NT.fas: 1 Mean : 67.43 Mean : 753.4 Mean :0.5808 Mean :0.6054
ENSG00000000938_FGR_NT.fas : 1 3rd Qu.: 89.00 3rd Qu.: 928.8 3rd Qu.:0.6380 3rd Qu.:0.6613
ENSG00000001036_FUCA2_NT.fas : 1 Max. :3094.00 Max. :55169.0 Max. :0.8007 Max. :0.8333
(Other) :13104
Max.Invariant.Block.Length Max.Invariant.Block.Length.Excluding.Ambiguous Max.Pairwise.Difference Max.Pairwise.Difference.Excluding.Ambiguous
Min. : 0.000 Min. : 2.000 Min. : 25.0 Min. : 30
1st Qu.: 0.000 1st Qu.: 6.000 1st Qu.: 241.0 1st Qu.: 655
Median : 3.000 Median : 8.000 Median : 378.0 Median : 1058
Mean : 3.467 Mean : 9.805 Mean : 500.7 Mean : 1365
3rd Qu.: 5.000 3rd Qu.: 11.000 3rd Qu.: 610.0 3rd Qu.: 1704
Max. :65.000 Max. :153.000 Max. :13839.0 Max. :71420
Max.Variable.Block.Length Max.Variable.Block.Length.Excluding.Ambiguous Min.GC Min.GC.Excluding.Ambiguous Min.Pairwise.Difference
Min. : 0.0 Min. : 2.00 Min. :0.02778 Min. :0.3046 Min. : 0.00
1st Qu.: 0.0 1st Qu.: 20.00 1st Qu.:0.22823 1st Qu.:0.4149 1st Qu.: 3.00
Median : 217.0 Median : 33.00 Median :0.27083 Median :0.4664 Median : 7.00
Mean : 503.3 Mean : 44.67 Mean :0.27934 Mean :0.4718 Mean : 10.51
3rd Qu.: 675.8 3rd Qu.: 55.00 3rd Qu.:0.32025 3rd Qu.:0.5250 3rd Qu.: 12.00
Max. :20229.0 Max. :695.00 Max. :0.65196 Max. :0.7546 Max. :1654.00
Min.Pairwise.Difference.Excluding.Ambiguous Number.Characters Number.Taxa Number.Invariable.Block Number.Invariable.Block.Excluding.Ambiguous Mean.GC
Min. : 0.00 Min. : 129 Min. : 6.00 Min. : 0.00 Min. : 20.0 Min. :0.2326
1st Qu.: 4.00 1st Qu.: 915 1st Qu.:31.00 1st Qu.: 0.00 1st Qu.: 182.0 1st Qu.:0.4234
Median : 8.00 Median : 1407 Median :34.00 Median : 16.00 Median : 296.0 Median :0.4827
Mean : 16.25 Mean : 1838 Mean :32.82 Mean : 34.78 Mean : 397.2 Mean :0.4818
3rd Qu.: 16.00 3rd Qu.: 2226 3rd Qu.:37.00 3rd Qu.: 48.00 3rd Qu.: 485.0 3rd Qu.:0.5368
Max. :4015.00 Max. :96549 Max. :39.00 Max. :1471.00 Max. :26342.0 Max. :0.7611
Mean.GC.Excluding.Ambiguous Mean.GC.1 Mean.GC.1.Excluding.Ambiguous Mean.GC.2 Mean.GC.2.Excluding.Ambiguous Mean.GC.3
Min. :0.3238 Min. :0.2520 Min. :0.3326 Min. :0.1614 Min. :0.2102 Min. :0.2020
1st Qu.:0.4676 1st Qu.:0.4653 1st Qu.:0.5157 1st Qu.:0.3421 1st Qu.:0.3784 1st Qu.:0.4377
Median :0.5354 Median :0.5048 Median :0.5589 Median :0.3769 Median :0.4160 Median :0.5659
Mean :0.5323 Mean :0.5105 Mean :0.5639 Mean :0.3832 Mean :0.4231 Mean :0.5518
3rd Qu.:0.5958 3rd Qu.:0.5509 3rd Qu.:0.6080 3rd Qu.:0.4190 3rd Qu.:0.4626 3rd Qu.:0.6625
Max. :0.7959 Max. :0.7800 Max. :0.8621 Max. :0.7181 Max. :0.7499 Max. :0.9482
Mean.GC.3.Excluding.Ambiguous Var.GC Var.GC.Excluding.Ambiguous Var.GC.1 Var.GC.1.Excluding.Ambiguous Var.GC.2
Min. :0.2242 Min. :6.884e-05 Min. :2.002e-05 Min. :2.873e-05 Min. :1.046e-05 Min. :0.000000
1st Qu.:0.4852 1st Qu.:3.481e-03 1st Qu.:4.546e-04 1st Qu.:3.833e-03 1st Qu.:2.040e-04 1st Qu.:0.002120
Median :0.6274 Median :5.116e-03 Median :7.423e-04 Median :5.614e-03 Median :3.801e-04 Median :0.003170
Mean :0.6099 Mean :6.014e-03 Mean :9.505e-04 Mean :6.424e-03 Mean :5.495e-04 Mean :0.003768
3rd Qu.:0.7358 3rd Qu.:7.734e-03 3rd Qu.:1.196e-03 3rd Qu.:8.151e-03 3rd Qu.:6.943e-04 3rd Qu.:0.004775
Max. :0.9575 Max. :4.105e-02 Max. :1.025e-02 Max. :4.520e-02 Max. :9.126e-03 Max. :0.032777
Var.GC.2.Excluding.Ambiguous Var.GC.3 Var.GC.3.Excluding.Ambiguous Number.Taxa.Missing.50 Number.Taxa.Missing.30 Number.Taxa.Missing.10
Min. :0.0000000 Min. :0.0003198 Min. :8.388e-05 Min. : 3.0 Min. : 2.00 Min. : 1.00
1st Qu.:0.0001342 1st Qu.:0.0056909 1st Qu.:2.255e-03 1st Qu.:30.0 1st Qu.:28.00 1st Qu.:24.00
Median :0.0002621 Median :0.0089109 Median :3.514e-03 Median :34.0 Median :32.00 Median :28.00
Mean :0.0004091 Mean :0.0101544 Mean :4.322e-03 Mean :32.7 Mean :31.23 Mean :27.23
3rd Qu.:0.0005099 3rd Qu.:0.0133824 3rd Qu.:5.435e-03 3rd Qu.:36.0 3rd Qu.:35.00 3rd Qu.:32.00
Max. :0.0112883 Max. :0.0517883 Max. :5.262e-02 Max. :39.0 Max. :39.00 Max. :39.00
Theta Tajima.D Tajima.Pi Segregating.Sites
Min. :0.06294 Min. : 65 Min. :-4.710 Min. :0.02260
1st Qu.:0.22962 1st Qu.: 825 1st Qu.:-2.310 1st Qu.:0.09327
Median :0.23845 Median : 1345 Median :-1.899 Median :0.11821
Mean :0.23335 Mean : 1771 Mean :-1.799 Mean :0.12401
3rd Qu.:0.24380 3rd Qu.: 2176 3rd Qu.:-1.390 3rd Qu.:0.14882
Max. :0.42305 Max. :93624 Max. : 2.317 Max. :0.38523
plot(d$Min.GC, d$Max.GC, pch=20, col=rgb(0,0,0,0.5))
abline(a=0, b=1, col="grey")
plot(d$Mean.GC, sqrt(d$Var.GC), pch=20, col=rgb(0,0,0,0.5), ylab="Standard deviation in GC")
abline(a=0, b=1, col="grey")
plot(d$Mean.GC.Excluding.Ambiguous, d$Mean.GC.1.Excluding.Ambiguous, pch=20, col=rgb(1,0,0,0.5), ylab="Mean GCs without ambiguous sites", xlab="Mean GC over all positions", xlim=c(0.2, 0.95), ylim=c(0.2, 0.95))
points(d$Mean.GC.Excluding.Ambiguous, d$Mean.GC.2.Excluding.Ambiguous, pch=20, col=rgb(0,1,0,0.5))points(d$Mean.GC.Excluding.Ambiguous, d$Mean.GC.3.Excluding.Ambiguous, pch=20, col=rgb(0,0,1,0.5))
abline(a=0, b=1, col="grey")legend("topleft", col=c(rgb(1,0,0,0.5), rgb(0,1,0,0.5), rgb(0,0,1,0.5)), pch=c(20, 20, 20), legend=c("Mean GC1", "Mean GC2", "Mean GC3"))
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