-
Notifications
You must be signed in to change notification settings - Fork 13
/
determining_ploidy_2.html
826 lines (715 loc) · 27.9 KB
/
determining_ploidy_2.html
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8" />
<meta name="generator" content="pandoc" />
<meta http-equiv="X-UA-Compatible" content="IE=EDGE" />
<title>Determining ploidy 2</title>
<script src="site_libs/header-attrs-2.16/header-attrs.js"></script>
<script src="site_libs/jquery-3.6.0/jquery-3.6.0.min.js"></script>
<meta name="viewport" content="width=device-width, initial-scale=1" />
<link href="site_libs/bootstrap-3.3.5/css/sandstone.min.css" rel="stylesheet" />
<script src="site_libs/bootstrap-3.3.5/js/bootstrap.min.js"></script>
<script src="site_libs/bootstrap-3.3.5/shim/html5shiv.min.js"></script>
<script src="site_libs/bootstrap-3.3.5/shim/respond.min.js"></script>
<style>h1 {font-size: 34px;}
h1.title {font-size: 38px;}
h2 {font-size: 30px;}
h3 {font-size: 24px;}
h4 {font-size: 18px;}
h5 {font-size: 16px;}
h6 {font-size: 12px;}
code {color: inherit; background-color: rgba(0, 0, 0, 0.04);}
pre:not([class]) { background-color: white }</style>
<script src="site_libs/navigation-1.1/tabsets.js"></script>
<link href="site_libs/highlightjs-9.12.0/textmate.css" rel="stylesheet" />
<script src="site_libs/highlightjs-9.12.0/highlight.js"></script>
<!-- Global Site Tag (gtag.js) - Google Analytics -->
<script async src="https://www.googletagmanager.com/gtag/js?id=UA-107144798-2"></script>
<script>
window.dataLayer = window.dataLayer || [];
function gtag(){dataLayer.push(arguments)};
gtag('js', new Date());
gtag('config', 'UA-107144798-2');
</script>
<!-- Global Site Tag (gtag.js) - Google Analytics -->
<script async src="https://www.googletagmanager.com/gtag/js?id=UA-107144798-1"></script>
<script>
window.dataLayer = window.dataLayer || [];
function gtag(){dataLayer.push(arguments)};
gtag('js', new Date());
gtag('config', 'UA-107144798-1');
</script>
<style type="text/css">
code{white-space: pre-wrap;}
span.smallcaps{font-variant: small-caps;}
span.underline{text-decoration: underline;}
div.column{display: inline-block; vertical-align: top; width: 50%;}
div.hanging-indent{margin-left: 1.5em; text-indent: -1.5em;}
ul.task-list{list-style: none;}
</style>
<style type="text/css">code{white-space: pre;}</style>
<script type="text/javascript">
if (window.hljs) {
hljs.configure({languages: []});
hljs.initHighlightingOnLoad();
if (document.readyState && document.readyState === "complete") {
window.setTimeout(function() { hljs.initHighlighting(); }, 0);
}
}
</script>
<link rel="stylesheet" href="styles.css" type="text/css" />
<style type = "text/css">
.main-container {
max-width: 940px;
margin-left: auto;
margin-right: auto;
}
img {
max-width:100%;
}
.tabbed-pane {
padding-top: 12px;
}
.html-widget {
margin-bottom: 20px;
}
button.code-folding-btn:focus {
outline: none;
}
summary {
display: list-item;
}
details > summary > p:only-child {
display: inline;
}
pre code {
padding: 0;
}
</style>
<style type="text/css">
.dropdown-submenu {
position: relative;
}
.dropdown-submenu>.dropdown-menu {
top: 0;
left: 100%;
margin-top: -6px;
margin-left: -1px;
border-radius: 0 6px 6px 6px;
}
.dropdown-submenu:hover>.dropdown-menu {
display: block;
}
.dropdown-submenu>a:after {
display: block;
content: " ";
float: right;
width: 0;
height: 0;
border-color: transparent;
border-style: solid;
border-width: 5px 0 5px 5px;
border-left-color: #cccccc;
margin-top: 5px;
margin-right: -10px;
}
.dropdown-submenu:hover>a:after {
border-left-color: #adb5bd;
}
.dropdown-submenu.pull-left {
float: none;
}
.dropdown-submenu.pull-left>.dropdown-menu {
left: -100%;
margin-left: 10px;
border-radius: 6px 0 6px 6px;
}
</style>
<script type="text/javascript">
// manage active state of menu based on current page
$(document).ready(function () {
// active menu anchor
href = window.location.pathname
href = href.substr(href.lastIndexOf('/') + 1)
if (href === "")
href = "index.html";
var menuAnchor = $('a[href="' + href + '"]');
// mark the anchor link active (and if it's in a dropdown, also mark that active)
var dropdown = menuAnchor.closest('li.dropdown');
if (window.bootstrap) { // Bootstrap 4+
menuAnchor.addClass('active');
dropdown.find('> .dropdown-toggle').addClass('active');
} else { // Bootstrap 3
menuAnchor.parent().addClass('active');
dropdown.addClass('active');
}
// Navbar adjustments
var navHeight = $(".navbar").first().height() + 15;
var style = document.createElement('style');
var pt = "padding-top: " + navHeight + "px; ";
var mt = "margin-top: -" + navHeight + "px; ";
var css = "";
// offset scroll position for anchor links (for fixed navbar)
for (var i = 1; i <= 6; i++) {
css += ".section h" + i + "{ " + pt + mt + "}\n";
}
style.innerHTML = "body {" + pt + "padding-bottom: 40px; }\n" + css;
document.head.appendChild(style);
});
</script>
<!-- tabsets -->
<style type="text/css">
.tabset-dropdown > .nav-tabs {
display: inline-table;
max-height: 500px;
min-height: 44px;
overflow-y: auto;
border: 1px solid #ddd;
border-radius: 4px;
}
.tabset-dropdown > .nav-tabs > li.active:before {
content: "";
font-family: 'Glyphicons Halflings';
display: inline-block;
padding: 10px;
border-right: 1px solid #ddd;
}
.tabset-dropdown > .nav-tabs.nav-tabs-open > li.active:before {
content: "";
border: none;
}
.tabset-dropdown > .nav-tabs.nav-tabs-open:before {
content: "";
font-family: 'Glyphicons Halflings';
display: inline-block;
padding: 10px;
border-right: 1px solid #ddd;
}
.tabset-dropdown > .nav-tabs > li.active {
display: block;
}
.tabset-dropdown > .nav-tabs > li > a,
.tabset-dropdown > .nav-tabs > li > a:focus,
.tabset-dropdown > .nav-tabs > li > a:hover {
border: none;
display: inline-block;
border-radius: 4px;
background-color: transparent;
}
.tabset-dropdown > .nav-tabs.nav-tabs-open > li {
display: block;
float: none;
}
.tabset-dropdown > .nav-tabs > li {
display: none;
}
</style>
<!-- code folding -->
</head>
<body>
<div class="container-fluid main-container">
<div class="navbar navbar-default navbar-fixed-top" role="navigation">
<div class="container">
<div class="navbar-header">
<button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-bs-toggle="collapse" data-target="#navbar" data-bs-target="#navbar">
<span class="icon-bar"></span>
<span class="icon-bar"></span>
<span class="icon-bar"></span>
</button>
<a class="navbar-brand" href="index.html">vcfR</a>
</div>
<div id="navbar" class="navbar-collapse collapse">
<ul class="nav navbar-nav">
<li>
<a href="index.html">Home</a>
</li>
<li>
<a href="rlanguage.html">R language</a>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" data-bs-toggle="dropdown" aria-expanded="false">
Tutorial
<span class="caret"></span>
</a>
<ul class="dropdown-menu" role="menu">
<li>
<a href="quick_intro.html">A quick introduction</a>
</li>
<li>
<a href="vcf_data.html">VCF data</a>
</li>
<li>
<a href="vcfR_object.html">vcfR objects</a>
</li>
<li>
<a href="how_much_memory.html">How much memory</a>
</li>
<li>
<a href="matrices.html">Extracting matrices</a>
</li>
<li>
<a href="tidy_vcfR.html">Tidy vcfR</a>
</li>
<li>
<a href="chromR_object.html">chromR objects</a>
</li>
<li>
<a href="visualization_1.html">Visualization 1</a>
</li>
<li>
<a href="visualization_2.html">Visualization 2</a>
</li>
<li>
<a href="sequence_coverage.html">Sequence coverage</a>
</li>
<li>
<a href="filtering_data.html">Filtering data</a>
</li>
<li>
<a href="ranking_data.html">Ranking data</a>
</li>
<li>
<a href="windowing.html">Windowing</a>
</li>
<li>
<a href="genetic_differentiation.html">Genetic differentiation</a>
</li>
</ul>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" data-bs-toggle="dropdown" aria-expanded="false">
GBS class
<span class="caret"></span>
</a>
<ul class="dropdown-menu" role="menu">
<li>
<a href="gbs_class.html">GBS class</a>
</li>
<li>
<a href="vcf_data.html">VCF data</a>
</li>
<li>
<a href="extract_data.html">Extract data</a>
</li>
<li>
<a href="depth_plot.html">Depth plot</a>
</li>
<li>
<a href="missing_data.html">Missing data</a>
</li>
<li>
<a href="censoring_data.html">Censoring data</a>
</li>
<li>
<a href="omitting_data.html">Omitting data</a>
</li>
<li>
<a href="apply.html">Apply</a>
</li>
</ul>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" data-bs-toggle="dropdown" aria-expanded="false">
Ploidy
<span class="caret"></span>
</a>
<ul class="dropdown-menu" role="menu">
<li>
<a href="ploidy.html">Ploidy</a>
</li>
<li>
<a href="determining_ploidy_1.html">Determining ploidy 1</a>
</li>
<li>
<a href="determining_ploidy_2.html">Determining ploidy 2</a>
</li>
</ul>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" data-bs-toggle="dropdown" aria-expanded="false">
Export
<span class="caret"></span>
</a>
<ul class="dropdown-menu" role="menu">
<li>
<a href="export.html">Overview</a>
</li>
<li>
<a href="export_vcfgz.html">Export to *vcf.gz</a>
</li>
<li>
<a href="export_genind_genclone.html">Genind and Genclone</a>
</li>
<li>
<a href="export_genlight_snpclone.html">Genlight and SNPclone</a>
</li>
<li>
<a href="dnabin.html">DNAbin</a>
</li>
</ul>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" data-bs-toggle="dropdown" aria-expanded="false">
FAQ
<span class="caret"></span>
</a>
<ul class="dropdown-menu" role="menu">
<li>
<a href="subset_data_to_1chrom.html">Subset to 1 chromosome</a>
</li>
<li>
<a href="missing_data.html">Missing data</a>
</li>
<li>
<a href="vcf_software.html">VCF software</a>
</li>
<li>
<a href="dip_to_hap.html">Haploidizing diploid data</a>
</li>
<li>
<a href="compiling_vcfR.html">Compiling vcfR</a>
</li>
<li>
<a href="reporting_issue.html">Reporting an issue</a>
</li>
</ul>
</li>
</ul>
<ul class="nav navbar-nav navbar-right">
</ul>
</div><!--/.nav-collapse -->
</div><!--/.container -->
</div><!--/.navbar -->
<p>
<center>
<h3>vcfR documentation</h3>
by
<br>
Brian J. Knaus and Niklaus J. Grünwald
</center>
</p>
<div id="header">
<h1 class="title toc-ignore">Determining ploidy 2</h1>
</div>
<p>Previously we showed how to create histograms based on the ratio of
alleles observed at heterozygous positions. These histograms may present
desireable perspectives when a constant ploidy is expected.
Investigators interested in whether there is variation in copy number
along a chromosome may require a more detailed perspective. Here we
present a perspective of copy number variation along the length of a
chromosome.</p>
<p>Instead of using all of the data each chromosome can be divided into
windows of user specified width. For each of these windows a numerical
summary of where the peak would be is made. Creating a numerical summary
is important because when we move to genome scale data it is easy to
generate more windows than we can manually curate. We can visualize some
of this data, but the numerical summary will allow us to process many
windows over many samples.</p>
<div id="input-data" class="section level2">
<h2>Input data</h2>
<p>Data import is performed similar to other examples.</p>
<pre class="r"><code># Load libraries
library(vcfR)
library(pinfsc50)
# Determine file locations
vcf_file <- system.file("extdata", "pinf_sc50.vcf.gz",
package = "pinfsc50")
# Read data into memory
vcf <- read.vcfR(vcf_file, verbose = FALSE)
vcf</code></pre>
<pre><code>## ***** Object of Class vcfR *****
## 18 samples
## 1 CHROMs
## 22,031 variants
## Object size: 22.4 Mb
## 7.929 percent missing data
## ***** ***** *****</code></pre>
</div>
<div id="depth-filtering" class="section level2">
<h2>Depth filtering</h2>
<p>We’ll also filter on depth by removng high and low coverage variants.
The thresholds for this filtering will be determined by quantiles.
Researchers may want to explore other methods available in R (e.g., fit
a distribution, mixture models, etc.).</p>
<p>First we extract the alleles and create frequencies</p>
<pre class="r"><code>ad <- extract.gt(vcf, element = 'AD')
allele1 <- masplit(ad, record = 1)
allele2 <- masplit(ad, record = 2)
ad1 <- allele1 / (allele1 + allele2)
ad2 <- allele2 / (allele1 + allele2)</code></pre>
<p>We create thresholds based on the most abundant allele as
follows.</p>
<pre class="r"><code>dp <- allele1
#sums <- apply(dp, MARGIN=2, quantile, probs=c(0.15, 0.95), na.rm=TRUE)
sums <- apply(dp, MARGIN=2, quantile, probs=c(0.1, 0.9), na.rm=TRUE)
par(mfrow=c(4,3))
par(mar=c(2,2,1,1))
par(oma=c(1,1,0,0))
for(i in 1:12){
hist(allele1[,i], breaks = seq(0,1e3,by=1), xlim=c(0,100), col=8, main="", xlab="", ylab="")
title(main = colnames(allele1)[i])
abline(v=sums[,i], col=2)
}
title(xlab = "Depth", line=0, outer = TRUE, font=2)
title(ylab = "Count", line=0, outer = TRUE, font=2)</code></pre>
<p><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-3-1.png" width="768" style="display: block; margin: auto;" /></p>
<pre class="r"><code>par(mar=c(5,4,4,2))
par(oma=c(0,0,0,0))</code></pre>
<p>We performa similar operation for the second most abundant
allele.</p>
<pre class="r"><code>par(mfrow=c(4,3))
par(mar=c(2,2,1,1))
par(oma=c(1,1,0,0))
for(i in 1:12){
tmp <- allele2[,i]
tmp <- tmp[ tmp > 0 ]
hist(tmp, breaks = seq(0,1e3,by=1), xlim=c(0,100),
# ylim=c(0,1000),
col=8, main="", xlab="", ylab="")
title(main = colnames(allele1)[i])
}
title(xlab = "Depth", line=0, outer = TRUE, font=2)
title(ylab = "Count", line=0, outer = TRUE, font=2)</code></pre>
<p><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-4-1.png" width="768" style="display: block; margin: auto;" /></p>
<pre class="r"><code>par(mfrow=c(1,1))
par(mar=c(5,4,4,2))
par(oma=c(0,0,0,0))</code></pre>
</div>
<div id="find-peaks-of-density" class="section level2">
<h2>Find peaks of density</h2>
<p>In order to avoid assumptions about the distribution of the allele
balance ratios we employ a non-parametric method. The data are binned
into bins of user specified widths and the bin with the highest density
is chosen as the frequency. This is our numerical summary of our peak
density and will be retained in a matrix of samples and windows.</p>
<pre class="r"><code># Filter on depth quantiles.
sums <- apply(allele1, MARGIN=2, quantile, probs=c(0.1, 0.9), na.rm=TRUE)
# Allele 1
dp2 <- sweep(allele1, MARGIN=2, FUN = "-", sums[1,])
#allele1[dp2 < 0] <- NA
vcf@gt[,-1][ dp2 < 0 & !is.na(vcf@gt[,-1]) ] <- NA
dp2 <- sweep(allele1, MARGIN=2, FUN = "-", sums[2,])
#allele1[dp2 > 0] <- NA
vcf@gt[,-1][dp2 > 0] <- NA
# Allele 2
dp2 <- sweep(allele2, MARGIN=2, FUN = "-", sums[1,])
vcf@gt[,-1][ dp2 < 0 & !is.na(vcf@gt[,-1]) ] <- NA
dp2 <- sweep(allele2, MARGIN=2, FUN = "-", sums[2,])
vcf@gt[,-1][dp2 > 0] <- NA
# Censor homozygotes.
gt <- extract.gt(vcf, element = 'GT')
hets <- is_het(gt)
is.na( vcf@gt[,-1][ !hets ] ) <- TRUE
# Extract allele depths
ad <- extract.gt(vcf, element = 'AD')
allele1 <- masplit(ad, record = 1)
allele2 <- masplit(ad, record = 2)
ad1 <- allele1 / (allele1 + allele2)
ad2 <- allele2 / (allele1 + allele2)
# Parameters
#winsize <- 1e5
#
winsize <- 2e5
#bin_width <- 0.1
#bin_width <- 0.05
#bin_width <- 0.025
#
bin_width <- 0.02
#bin_width <- 0.01
# Find peaks
freq1 <- ad1/(ad1+ad2)
freq2 <- ad2/(ad1+ad2)
myPeaks1 <- freq_peak(freq1, getPOS(vcf), winsize = winsize, bin_width = bin_width)
#myCounts1 <- freq_peak(freq1, getPOS(vcf), winsize = winsize, bin_width = bin_width, count = TRUE)
is.na(myPeaks1$peaks[myPeaks1$counts < 20]) <- TRUE
myPeaks2 <- freq_peak(freq2, getPOS(vcf), winsize = winsize, bin_width = bin_width, lhs = FALSE)
#myCounts2 <- freq_peak(freq2, getPOS(vcf), winsize = winsize, bin_width = bin_width, count = TRUE)
is.na(myPeaks2$peaks[myPeaks2$counts < 20]) <- TRUE</code></pre>
<p>As a proof of concep we can visualize plots of the major allele with
a red horizontal line at our predicted peak. We repeat this for the
minor allele.</p>
<pre class="r"><code>par(mfrow=c(4,4))
par(mar=c(2,2,1,1))
par(oma=c(1,1,0,0))
mySample <- "BL2009P4_us23"
for(i in 1:4){
hist(freq1[ myPeaks1$wins[i,'START_row']:myPeaks1$wins[i,'END_row'], mySample ],
breaks = seq(0,1,by=bin_width), xlim=c(0,1), col=8, main = "", xaxt='n')
axis(side=1, at=c(0,0.25,0.333,0.5,0.666,0.75,1),
labels=c(0,'1/4','1/3','1/2','2/3','3/4',1), las=1)
abline(v=myPeaks1$peaks[i,mySample], col=2)
if(i==2){ title(main=mySample) }
}
mySample <- "DDR7602"
for(i in 1:4){
hist(freq1[ myPeaks1$wins[i,'START_row']:myPeaks1$wins[i,'END_row'], mySample ],
breaks = seq(0,1,by=bin_width), xlim=c(0,1), col=8, main = "", xaxt='n')
axis(side=1, at=c(0,0.25,0.333,0.5,0.666,0.75,1),
labels=c(0,'1/4','1/3','1/2','2/3','3/4',1), las=1)
abline(v=myPeaks1$peaks[i,mySample], col=2)
if(i==2){ title(main=mySample) }
}
mySample <- "IN2009T1_us22"
for(i in 1:4){
hist(freq1[ myPeaks1$wins[i,'START_row']:myPeaks1$wins[i,'END_row'], mySample ],
breaks = seq(0,1,by=bin_width), xlim=c(0,1), col=8, main = "", xaxt='n')
axis(side=1, at=c(0,0.25,0.333,0.5,0.666,0.75,1),
labels=c(0,'1/4','1/3','1/2','2/3','3/4',1), las=1)
abline(v=myPeaks1$peaks[i,mySample], col=2)
if(i==2){ title(main=mySample) }
}
mySample <- "P17777us22"
for(i in 1:4){
hist(freq1[ myPeaks1$wins[i,'START_row']:myPeaks1$wins[i,'END_row'], mySample ],
breaks = seq(0,1,by=bin_width), xlim=c(0,1), col=8, main = "", xaxt='n')
axis(side=1, at=c(0,0.25,0.333,0.5,0.666,0.75,1),
labels=c(0,'1/4','1/3','1/2','2/3','3/4',1), las=1)
abline(v=myPeaks1$peaks[i,mySample], col=2)
if(i==2){ title(main=mySample) }
}</code></pre>
<p><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-5-1.png" width="768" style="display: block; margin: auto;" /></p>
<pre class="r"><code>par(mfrow=c(1,1))
par(mar=c(5,4,4,2))
par(oma=c(0,0,0,0))</code></pre>
<p>Second most abundant allele.</p>
<pre class="r"><code>par(mfrow=c(4,4))
par(mar=c(2,2,1,1))
par(oma=c(1,1,0,0))
mySample <- "BL2009P4_us23"
for(i in 1:4){
hist(freq2[ myPeaks1$wins[i,'START_row']:myPeaks1$wins[i,'END_row'], mySample ],
breaks = seq(0,1,by=bin_width), xlim=c(0,1), col=8, main = "", xaxt='n')
axis(side=1, at=c(0,0.25,0.333,0.5,0.666,0.75,1),
labels=c(0,'1/4','1/3','1/2','2/3','3/4',1), las=1)
abline(v=myPeaks2$peaks[i,mySample], col=2)
if(i==2){ title(main=mySample) }
}
mySample <- "DDR7602"
for(i in 1:4){
hist(freq2[ myPeaks1$wins[i,'START_row']:myPeaks1$wins[i,'END_row'], mySample ],
breaks = seq(0,1,by=bin_width), xlim=c(0,1), col=8, main = "", xaxt='n')
axis(side=1, at=c(0,0.25,0.333,0.5,0.666,0.75,1),
labels=c(0,'1/4','1/3','1/2','2/3','3/4',1), las=1)
abline(v=myPeaks2$peaks[i,mySample], col=2)
if(i==2){ title(main=mySample) }
}
mySample <- "IN2009T1_us22"
for(i in 1:4){
hist(freq2[ myPeaks1$wins[i,'START_row']:myPeaks1$wins[i,'END_row'], mySample ],
breaks = seq(0,1,by=bin_width), xlim=c(0,1), col=8, main = "", xaxt='n')
axis(side=1, at=c(0,0.25,0.333,0.5,0.666,0.75,1),
labels=c(0,'1/4','1/3','1/2','2/3','3/4',1), las=1)
abline(v=myPeaks2$peaks[i,mySample], col=2)
if(i==2){ title(main=mySample) }
}
mySample <- "P17777us22"
for(i in 1:4){
hist(freq2[ myPeaks2$wins[i,'START_row']:myPeaks1$wins[i,'END_row'], mySample ],
breaks = seq(0,1,by=bin_width), xlim=c(0,1), col=8, main = "", xaxt='n')
axis(side=1, at=c(0,0.25,0.333,0.5,0.666,0.75,1),
labels=c(0,'1/4','1/3','1/2','2/3','3/4',1), las=1)
abline(v=myPeaks2$peaks[i,mySample], col=2)
if(i==2){ title(main=mySample) }
}</code></pre>
<p><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-6-1.png" width="768" style="display: block; margin: auto;" /></p>
<pre class="r"><code>par(mfrow=c(1,1))
par(mar=c(5,4,4,2))
par(oma=c(0,0,0,0))</code></pre>
</div>
<div id="visualization" class="section level2">
<h2>Visualization</h2>
<p>There are a number of ways to visualize this data. One way is to turn
our histogram on its side, as a form of marginal summary, and plot our
window summaries.</p>
<pre class="r"><code>i <- 2
layout(matrix(1:2, nrow=1), widths = c(4,1))
par(mar=c(5,4,4,0))
mySample <- colnames(freq1)[i]
plot(getPOS(vcf), freq1[,mySample], ylim=c(0,1), type="n", yaxt='n',
main = mySample, xlab = "POS", ylab = "Allele balance")
axis(side=2, at=c(0,0.25,0.333,0.5,0.666,0.75,1),
labels=c(0,'1/4','1/3','1/2','2/3','3/4',1), las=1)
abline(h=c(0.25,0.333,0.5,0.666,0.75), col=8)
points(getPOS(vcf), freq1[,mySample], pch = 20, col= "#A6CEE344")
points(getPOS(vcf), freq2[,mySample], pch = 20, col= "#1F78B444")
segments(x0=myPeaks1$wins[,'START_pos'], y0=myPeaks1$peaks[,mySample],
x1=myPeaks1$wins[,'END_pos'], lwd=3)
segments(x0=myPeaks1$wins[,'START_pos'], y0=myPeaks2$peaks[,mySample],
x1=myPeaks1$wins[,'END_pos'], lwd=3)
bp1 <- hist(freq1[,mySample], breaks = seq(0,1,by=bin_width), plot = FALSE)
bp2 <- hist(freq2[,mySample], breaks = seq(0,1,by=bin_width), plot = FALSE)
par(mar=c(5,1,4,2))
barplot(height=bp1$counts, width=0.02, space = 0, horiz = T, add = FALSE, col="#A6CEE3")
barplot(height=bp2$counts, width=0.02, space = 0, horiz = T, add = TRUE, col="#1F78B4")</code></pre>
<p><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-7-1.png" width="768" style="display: block; margin: auto;" /></p>
<pre class="r"><code>par(mar=c(5,4,4,2))
par(mfrow=c(1,1))</code></pre>
<p>Once we determine how to make one plot we can loop over all the
samples.</p>
<p><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-8-1.png" width="768" style="display: block; margin: auto;" /><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-8-2.png" width="768" style="display: block; margin: auto;" /><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-8-3.png" width="768" style="display: block; margin: auto;" /><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-8-4.png" width="768" style="display: block; margin: auto;" /><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-8-5.png" width="768" style="display: block; margin: auto;" /><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-8-6.png" width="768" style="display: block; margin: auto;" /><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-8-7.png" width="768" style="display: block; margin: auto;" /><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-8-8.png" width="768" style="display: block; margin: auto;" /><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-8-9.png" width="768" style="display: block; margin: auto;" /><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-8-10.png" width="768" style="display: block; margin: auto;" /><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-8-11.png" width="768" style="display: block; margin: auto;" /><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-8-12.png" width="768" style="display: block; margin: auto;" /><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-8-13.png" width="768" style="display: block; margin: auto;" /><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-8-14.png" width="768" style="display: block; margin: auto;" /><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-8-15.png" width="768" style="display: block; margin: auto;" /><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-8-16.png" width="768" style="display: block; margin: auto;" /><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-8-17.png" width="768" style="display: block; margin: auto;" /><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-8-18.png" width="768" style="display: block; margin: auto;" /></p>
<p>We can also create a matrix of plots.</p>
<pre class="r"><code>par(mfrow=c(4,3))
par(mar=c(2,2,1,1))
par(oma=c(1,1,0,0))
for(i in 1:12){
mySample <- colnames(freq1)[i]
plot(getPOS(vcf), freq1[,mySample], ylim=c(0,1), type="n", yaxt='n',
main = mySample, xlab = "POS", ylab = "Allele balance")
axis(side=2, at=c(0,0.25,0.333,0.5,0.666,0.75,1),
labels=c(0,'1/4','1/3','1/2','2/3','3/4',1), las=1)
abline(h=c(0.25,0.333,0.5,0.666,0.75), col=8)
points(getPOS(vcf), freq1[,mySample], pch = 20, col= "#A6CEE344")
points(getPOS(vcf), freq2[,mySample], pch = 20, col= "#1F78B444")
segments(x0=myPeaks1$wins[,'START_pos'], y0=myPeaks1$peaks[,mySample],
x1=myPeaks1$wins[,'END_pos'], lwd=3)
segments(x0=myPeaks1$wins[,'START_pos'], y0=myPeaks2$peaks[,mySample],
x1=myPeaks1$wins[,'END_pos'], lwd=3)
}</code></pre>
<p><img src="determining_ploidy_2_files/figure-html/unnamed-chunk-9-1.png" width="768" style="display: block; margin: auto;" /></p>
<pre class="r"><code>par(mfrow=c(1,1))
par(mar=c(5,4,4,2))
par(oma=c(0,0,0,0))</code></pre>
<p>We now have a way to create windows of allele balance ratios. We also
have several ways to visualize this data. Perhaps most importantly, we
have a numerical summary of the peak in each window so we can loop over
all of the chromosomes in our reference.</p>
</div>
<center>
<hr class="style1">
<p>Copyright © 2017, 2018 Brian J. Knaus. All rights reserved.</p>
<p>USDA Agricultural Research Service, Horticultural Crops Research Lab.</p>
</center>
</div>
<script>
// add bootstrap table styles to pandoc tables
function bootstrapStylePandocTables() {
$('tr.odd').parent('tbody').parent('table').addClass('table table-condensed');
}
$(document).ready(function () {
bootstrapStylePandocTables();
});
</script>
<!-- tabsets -->
<script>
$(document).ready(function () {
window.buildTabsets("TOC");
});
$(document).ready(function () {
$('.tabset-dropdown > .nav-tabs > li').click(function () {
$(this).parent().toggleClass('nav-tabs-open');
});
});
</script>
<!-- code folding -->
<!-- dynamically load mathjax for compatibility with self-contained -->
<script>
(function () {
var script = document.createElement("script");
script.type = "text/javascript";
script.src = "https://mathjax.rstudio.com/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML";
document.getElementsByTagName("head")[0].appendChild(script);
})();
</script>
</body>
</html>