Mercurial > repos > devteam > dwt_cor_ava_perclass
comparison execute_dwt_cor_aVa_perClass.R @ 2:b87bbe6bc044 draft default tip
"planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/dwt_cor_ava_perclass commit f929353ffb0623f2218d7dec459c7da62f3b0d24"
author | devteam |
---|---|
date | Mon, 06 Jul 2020 20:28:54 -0400 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
1:a0defff5cf89 | 2:b87bbe6bc044 |
---|---|
1 ################################################################################## | |
2 ## code to do all correlation tests of form: motif(a) vs. motif(a) | |
3 ## add code to create null bands by permuting the original data series | |
4 ## generate plots and table matrix of correlation coefficients including p-values | |
5 ################################################################################## | |
6 library("wavethresh"); | |
7 library("waveslim"); | |
8 | |
9 options(echo = FALSE) | |
10 | |
11 ## normalize data | |
12 norm <- function(data) { | |
13 v <- (data - mean(data)) / sd(data); | |
14 if (sum(is.na(v)) >= 1) { | |
15 v <- data; | |
16 } | |
17 return(v); | |
18 } | |
19 | |
20 dwt_cor <- function(data_short, names_short, data_long, names_long, test, pdf, table, filter = 4, bc = "symmetric", method = "kendall", wf = "haar", boundary = "reflection") { | |
21 print(test); | |
22 print(pdf); | |
23 print(table); | |
24 | |
25 pdf(file = pdf); | |
26 final_pvalue <- NULL; | |
27 title <- NULL; | |
28 | |
29 short_levels <- wavethresh::wd(data_short[, 1], filter.number = filter, bc = bc)$nlevels; | |
30 title <- c("motif"); | |
31 for (i in 1:short_levels) { | |
32 title <- c(title, paste(i, "cor", sep = "_"), paste(i, "pval", sep = "_")); | |
33 } | |
34 print(title); | |
35 | |
36 ## normalize the raw data | |
37 data_short <- apply(data_short, 2, norm); | |
38 data_long <- apply(data_long, 2, norm); | |
39 | |
40 for (i in seq_len(length(names_short))) { | |
41 ## Kendall Tau | |
42 ## DWT wavelet correlation function | |
43 ## include significance to compare | |
44 wave1_dwt <- NULL; | |
45 wave2_dwt <- NULL; | |
46 tau_dwt <- NULL; | |
47 out <- NULL; | |
48 | |
49 print(names_short[i]); | |
50 print(names_long[i]); | |
51 | |
52 ## need exit if not comparing motif(a) vs motif(a) | |
53 if (names_short[i] != names_long[i]) { | |
54 stop(paste("motif", names_short[i], "is not the same as", names_long[i], sep = " ")); | |
55 } | |
56 else { | |
57 wave1_dwt <- waveslim::dwt(data_short[, i], wf = wf, short_levels, boundary = boundary); | |
58 wave2_dwt <- waveslim::dwt(data_long[, i], wf = wf, short_levels, boundary = boundary); | |
59 tau_dwt <- vector(length = short_levels) | |
60 | |
61 ## perform cor test on wavelet coefficients per scale | |
62 for (level in 1:short_levels) { | |
63 w1_level <- NULL; | |
64 w2_level <- NULL; | |
65 w1_level <- (wave1_dwt[[level]]); | |
66 w2_level <- (wave2_dwt[[level]]); | |
67 tau_dwt[level] <- cor.test(w1_level, w2_level, method = method)$estimate; | |
68 } | |
69 | |
70 ## CI bands by permutation of time series | |
71 feature1 <- NULL; | |
72 feature2 <- NULL; | |
73 feature1 <- data_short[, i]; | |
74 feature2 <- data_long[, i]; | |
75 null <- NULL; | |
76 results <- NULL; | |
77 med <- NULL; | |
78 cor_25 <- NULL; | |
79 cor_975 <- NULL; | |
80 | |
81 for (k in 1:1000) { | |
82 nk_1 <- NULL; | |
83 nk_2 <- NULL; | |
84 null_levels <- NULL; | |
85 cor <- NULL; | |
86 null_wave1 <- NULL; | |
87 null_wave2 <- NULL; | |
88 | |
89 nk_1 <- sample(feature1, length(feature1), replace = FALSE); | |
90 nk_2 <- sample(feature2, length(feature2), replace = FALSE); | |
91 null_levels <- wavethresh::wd(nk_1, filter.number = filter, bc = bc)$nlevels; | |
92 cor <- vector(length = null_levels); | |
93 null_wave1 <- waveslim::dwt(nk_1, wf = wf, short_levels, boundary = boundary); | |
94 null_wave2 <- waveslim::dwt(nk_2, wf = wf, short_levels, boundary = boundary); | |
95 | |
96 for (level in 1:null_levels) { | |
97 null_level1 <- NULL; | |
98 null_level2 <- NULL; | |
99 null_level1 <- (null_wave1[[level]]); | |
100 null_level2 <- (null_wave2[[level]]); | |
101 cor[level] <- cor.test(null_level1, null_level2, method = method)$estimate; | |
102 } | |
103 null <- rbind(null, cor); | |
104 } | |
105 | |
106 null <- apply(null, 2, sort, na.last = TRUE); | |
107 print(paste("NAs", length(which(is.na(null))), sep = " ")); | |
108 cor_25 <- null[25, ]; | |
109 cor_975 <- null[975, ]; | |
110 med <- (apply(null, 2, median, na.rm = TRUE)); | |
111 | |
112 ## plot | |
113 results <- cbind(tau_dwt, cor_25, cor_975); | |
114 matplot(results, type = "b", pch = "*", lty = 1, col = c(1, 2, 2), ylim = c(-1, 1), xlab = "Wavelet Scale", ylab = "Wavelet Correlation Kendall's Tau", main = (paste(test, names_short[i], sep = " ")), cex.main = 0.75); | |
115 abline(h = 0); | |
116 | |
117 ## get pvalues by comparison to null distribution | |
118 ### modify pval calculation for error type II of T test #### | |
119 out <- (names_short[i]); | |
120 for (m in seq_len(length(tau_dwt))) { | |
121 print(paste("scale", m, sep = " ")); | |
122 print(paste("tau", tau_dwt[m], sep = " ")); | |
123 print(paste("med", med[m], sep = " ")); | |
124 out <- c(out, format(tau_dwt[m], digits = 3)); | |
125 pv <- NULL; | |
126 if (is.na(tau_dwt[m])) { | |
127 pv <- "NA"; | |
128 } | |
129 else { | |
130 if (tau_dwt[m] >= med[m]) { | |
131 ## R tail test | |
132 print(paste("R")); | |
133 ### per sv ok to use inequality not strict | |
134 pv <- (length(which(null[, m] >= tau_dwt[m]))) / (length(na.exclude(null[, m]))); | |
135 if (tau_dwt[m] == med[m]) { | |
136 print("tau == med"); | |
137 print(summary(null[, m])); | |
138 } | |
139 } | |
140 else if (tau_dwt[m] < med[m]) { | |
141 ## L tail test | |
142 print(paste("L")); | |
143 pv <- (length(which(null[, m] <= tau_dwt[m]))) / (length(na.exclude(null[, m]))); | |
144 } | |
145 } | |
146 out <- c(out, pv); | |
147 print(paste("pval", pv, sep = " ")); | |
148 } | |
149 final_pvalue <- rbind(final_pvalue, out); | |
150 print(out); | |
151 } | |
152 } | |
153 colnames(final_pvalue) <- title; | |
154 write.table(final_pvalue, file = table, sep = "\\t", quote = FALSE, row.names = FALSE) | |
155 dev.off(); | |
156 } | |
157 ## execute | |
158 ## read in data | |
159 args <- commandArgs(trailingOnly = TRUE) | |
160 | |
161 input_data1 <- NULL; | |
162 input_data2 <- NULL; | |
163 input_data_short1 <- NULL; | |
164 input_data_short2 <- NULL; | |
165 input_data_names_short1 <- NULL; | |
166 input_data_names_short2 <- NULL; | |
167 | |
168 input_data1 <- read.delim(args[1]); | |
169 input_data_short1 <- input_data1[, +c(seq_len(ncol(input_data1)))]; | |
170 input_data_names_short1 <- colnames(input_data_short1); | |
171 | |
172 input_data2 <- read.delim(args[2]); | |
173 input_data_short2 <- input_data2[, +c(seq_len(ncol(input_data2)))]; | |
174 input_data_names_short2 <- colnames(input_data_short2); | |
175 | |
176 ## cor test for motif(a) in input_data1 vs motif(a) in input_data2 | |
177 dwt_cor(input_data_short1, input_data_names_short1, input_data_short2, input_data_names_short2, test = "cor_aVa", pdf = args[3], table = args[4]); | |
178 print("done with the correlation test"); |