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
|
#!/usr/bin/env Rscript
# Effect sizes for named markers, via R/qtl's fitqtl.
#
# The scan (/compute/rqtl) gives a LOD per marker but no effect: scanone
# reports a statistic, not a fitted model. fitqtl fits one -- at a marker
# or a QTL position -- and reports the QTL's effect, its standard error,
# the model LOD and the variance explained, which is what a table of
# effects needs.
#
# Reads the same GeneNetwork .geno file and the same two-column phenotype
# file (Sample + trait, "x" for missing) as rqtl_wrapper.R, builds the
# cross the same way, and writes one CSV row per requested marker:
#
# marker,chr,pos,lod,pct_var,additive,se,t,p
#
# `additive` is fitqtl's estimate for the QTL term. In R/qtl's coding the
# QTL genotype is +-1 for a riself cross, so this is half the difference
# between the two homozygote classes -- the same convention GeneNetwork's
# `additive` uses, and the number to quote beside a peak.
#
# The geno/pheno reading below is the same approach as rqtl_wrapper.R
# (GeneNetwork3's script, copied verbatim in this repository): that file is
# a verbatim copy and is not extended here, so the helpers it needs are
# repeated rather than sourced (sourcing it would run its option parser).
suppressPackageStartupMessages({
library(optparse)
library(qtl)
})
option_list = list(
make_option(c("-g", "--geno"), type="character", help=".geno file with the dataset's genotypes"),
make_option(c("-p", "--pheno"), type="character", help="two-column phenotype file: Sample, trait"),
make_option(c("-m", "--markers"), type="character", help="comma-separated marker names to fit"),
make_option(c("--model"), type="character", default="normal", help="normal or np"),
make_option(c("--method"), type="character", default="hk", help="hk, ehk, mr, em, imp"),
make_option(c("-s", "--scale"), type="character", default="mb", help="mb or cm"),
make_option(c("-o", "--outdir"), type="character", default=tempdir(), help="output directory"),
make_option(c("--covarstruct"), type="character", default=NULL, help="file listing covariate names and kinds (categorical/numerical)"),
make_option(c("-f", "--filename"), type="character", default="fitqtl.csv", help="output file name")
)
opt = parse_args(OptionParser(option_list=option_list))
if (is.null(opt$geno) || is.null(opt$pheno) || is.null(opt$markers)) {
stop("--geno, --pheno and --markers are required", call.=FALSE)
}
trim <- function(x) gsub("(^[[:space:]]+|[[:space:]]+$)", "", x)
get_geno_code <- function(header, name) {
mat = which(vapply(header, function(x) length(grep(paste0('@', name), x)) == 1, logical(1)))
if (length(mat) == 0) return(NULL)
trim(strsplit(header[mat], ':')[[1]][2])
}
header = readLines(opt$geno, 40)
toskip = which(vapply(header, function(x) length(grep("Chr\t", x)) == 1, logical(1))) - 1
type = get_geno_code(header, 'type')
scale_col = if (toupper(opt$scale) == "CM") "cM" else "Mb"
# `na.strings` on the whole file is wrong: DOL's `@unk:X` would turn every
# X chromosome into a missing chromosome (see scripts/rqtl_wrapper.R).
unk_code <- get_geno_code(header, 'unk')
genodata <- read.csv(opt$geno, sep='\t', skip=toskip, header=TRUE,
na.strings=character(0),
colClasses='character', comment.char = '#')
# Positions are Chr, Locus and whichever map column the file has: 44 of this
# deployment's .geno files carry cM only, and assuming "4 metadata columns"
# costs their first sample.
available <- names(genodata)
position_col <- if (scale_col %in% available) scale_col else
if ("Mb" %in% available) "Mb" else
if ("cM" %in% available) "cM" else
stop("the genotype file has neither an Mb nor a cM column", call.=FALSE)
first_sample <- match(position_col, available) + 1
n_individuals <- ncol(genodata) - (first_sample - 1)
if (!is.null(unk_code) && !identical(unk_code, "")) {
genotype_columns <- first_sample:ncol(genodata)
genodata[genotype_columns] <- lapply(genodata[genotype_columns], function(column) {
column[trim(column) == unk_code] <- NA
column
})
}
df <- read.table(opt$pheno, na.strings = "x", header=TRUE, check.names=FALSE)
trait_name <- colnames(df)[2]
if (length(df[[1]]) != n_individuals) {
stop(sprintf(paste("The phenotype file has %d samples but the genotype file has %d",
"individuals. Values are matched to individuals by position, so the",
"two must be one for one, in the genotype file's column order."),
length(df[[1]]), n_individuals), call.=FALSE)
}
cross_file = tempfile(pattern="fitqtl-cross-", fileext=".csv")
items = list(
c(paste0("T_", trait_name), '', '', unlist(df[2])),
c('sex', '', '', rep('m', n_individuals)),
cbind(genodata[, c('Locus', 'Chr', position_col)], genodata[, first_sample:ncol(genodata)])
)
write.table(do.call(rbind, items), file=cross_file, row.names=FALSE,
col.names=FALSE, quote=FALSE, sep=',')
genocodes <- if (identical(type, '4-way')) NULL else
c(get_geno_code(header, 'mat'), get_geno_code(header, 'het'), get_geno_code(header, 'pat'))
cross <- if (identical(type, '4-way')) {
read.cross(file=cross_file, 'csvr', genotypes=NULL, crosstype="4way")
} else if (identical(type, 'f2')) {
read.cross(file=cross_file, 'csvr', genotypes=genocodes, crosstype="f2")
} else {
read.cross(file=cross_file, 'csvr', genotypes=genocodes)
}
if (identical(type, 'riset')) cross <- convert2riself(cross)
unlink(cross_file)
# Covariates, if any: the phenotype file carries the trait in column 2 and
# one column per covariate after it, and --covarstruct says which of those
# are categorical. Those are dummy-expanded here (R/qtl's fitqtl wants a
# numeric covar frame), one column per non-reference level, the same coding
# the R/qtl wrapper applies for /compute/rqtl.
covar <- NULL
if (!is.null(opt$covarstruct) && file.exists(opt$covarstruct)) {
struct <- read.table(opt$covarstruct, header=FALSE, sep="\t", stringsAsFactors=FALSE,
col.names=c("name", "kind"), quote="")
covar <- data.frame(row.names=seq_len(n_individuals))
for (i in seq_len(nrow(struct))) {
column <- df[[2 + i]] # column 2 is the trait; covariates follow
if (identical(struct$kind[i], "categorical")) {
# k-1 dummies against the first level (sorted, as the server codes
# them), with a missing value left missing -- model.matrix() would
# drop those rows and misalign the covariate frame with the cross.
levels_all <- sort(unique(column[!is.na(column)]))
if (length(levels_all) < 2) {
stop(sprintf("covariate '%s' has %d usable level(s)", struct$name[i], length(levels_all)),
call.=FALSE)
}
for (j in 2:length(levels_all)) {
covar[[paste0(struct$name[i], ".", levels_all[j])]] <-
ifelse(is.na(column), NA, as.numeric(column == levels_all[j]))
}
} else {
covar[[struct$name[i]]] <- as.numeric(column)
}
}
# A column that does not vary among the individuals with a phenotype is
# singular in the fit (R/qtl stops with "system is exactly singular"), and
# contributes nothing anyway -- the same rule the GEMMA covariate file
# applies. It matters in practice: a covariate can be perfectly spread
# across the panel and constant in the subset a trait happens to cover.
with_phenotype <- !is.na(df[[2]])
varies <- vapply(covar, function(column) {
values <- column[with_phenotype]
length(unique(values[!is.na(values)])) > 1
}, logical(1))
dropped <<- colnames(covar)[!varies]
if (length(dropped) > 0) {
covar <- covar[, varies, drop=FALSE]
}
if (ncol(covar) == 0) covar <- NULL
cat("covariates:", paste(colnames(covar), collapse=", "), "\n")
}
# step=0: probabilities at the markers themselves, which is all fitqtl
# needs for a marker-level fit (and much cheaper than a dense grid).
cross <- calc.genoprob(cross, step=0)
map <- pull.map(cross)
dropped_covariates <- if (exists("dropped")) dropped else character(0)
wanted <- trim(strsplit(opt$markers, ',')[[1]])
wanted <- wanted[nzchar(wanted)]
rows <- list()
for (marker in wanted) {
hit <- which(vapply(map, function(m) marker %in% names(m), logical(1)))
if (length(hit) == 0) {
warning(sprintf("marker '%s' is not in this genotype file", marker), call.=FALSE)
next
}
chr <- hit[1]
pos <- as.numeric(map[[chr]][[marker]])
qtl <- makeqtl(cross, chr=chr, pos=pos, what="prob")
fit <- tryCatch(
fitqtl(cross, qtl=qtl, pheno.col=1, model=opt$model, method=opt$method,
covar=if (is.null(covar)) NULL else covar, get.ests=TRUE),
error = function(e) { warning(sprintf("fitqtl failed at %s: %s", marker, conditionMessage(e)),
call.=FALSE); NULL })
if (is.null(fit)) next
full <- fit$result.full
pvalue <- if ("Pvalue(F)" %in% colnames(full)) full["Model", "Pvalue(F)"] else
if ("Pvalue(Chi2)" %in% colnames(full)) full["Model", "Pvalue(Chi2)"] else NA
additive <- NA; se <- NA; tstat <- NA
if (!is.null(fit$ests)) {
s <- summary(fit)$ests
# Row 1 is the intercept; the QTL term is the last row.
if (nrow(s) >= 2) {
term <- s[nrow(s), ]
additive <- as.numeric(term["est"])
se <- as.numeric(term["SE"])
tstat <- as.numeric(term["t"])
}
}
rows[[length(rows) + 1]] <- data.frame(
marker = marker, chr = chr, pos = pos, lod = fit$lod,
pct_var = as.numeric(full["Model", "%var"]),
additive = additive, se = se, t = tstat, p = as.numeric(pvalue),
stringsAsFactors = FALSE)
}
out <- file.path(opt$outdir, opt$filename)
if (length(rows) == 0) {
writeLines("marker,chr,pos,lod,pct_var,additive,se,t,p", out)
cat("wrote", out, ": no marker could be fitted\n")
} else {
result <- do.call(rbind, rows)
write.csv(result, out, row.names=FALSE, quote=FALSE)
best <- result[which.max(result$lod), ]
cat(sprintf("wrote %s: %d marker(s) fitted; strongest %s chr%s %.1f Mb LOD %.2f, additive %+.3f (SE %.3f), %.1f%% variance%s\n",
out, nrow(result), best$marker, best$chr, best$pos, best$lod,
best$additive, best$se, best$pct_var,
if (length(dropped_covariates) > 0)
paste0("; covariate column(s) left out because they do not vary among the fitted individuals: ",
paste(dropped_covariates, collapse=", "))
else ""))
}
|