git-svn-id: file:///home/git/hedgehog.fhcrc.org/bioconductor/trunk/madman/Rpacks/crlmm@117087 bc3139a8-67e5-0310-9ffc-ced21a209358
... | ... |
@@ -16,9 +16,9 @@ |
16 | 16 |
} |
17 | 17 |
\usage{ |
18 | 18 |
genotypeInf(cnSet, mixtureParams, probs = rep(1/3, 3), SNRMin = 5, |
19 |
-recallMin = 10, recallRegMin = 1000, verbose = TRUE, returnParams = |
|
20 |
-TRUE, badSNP = 0.7, gender = NULL, DF = 6, cdfName, call.method="crlmm", |
|
21 |
-trueCalls = NULL) |
|
19 |
+ recallMin = 10, recallRegMin = 1000, verbose = TRUE, returnParams = TRUE, |
|
20 |
+ badSNP = 0.7, gender = NULL, DF = 6, cdfName, nopackage.norm="quantile", |
|
21 |
+ call.method="crlmm", trueCalls = NULL) |
|
22 | 22 |
} |
23 | 23 |
%- maybe also 'usage' for other objects documented here. |
24 | 24 |
\arguments{ |
... | ... |
@@ -44,6 +44,8 @@ trueCalls = NULL) |
44 | 44 |
t-distribution.} |
45 | 45 |
\item{cdfName}{\code{character} string indicating which annotation |
46 | 46 |
package to load.} |
47 |
+ \item{nopackage.norm}{character string specifying normalization to be used when \code{cdfName}='nopackage'. |
|
48 |
+ Options are 'none', 'quantile' (within channel, between array) and 'quantileloess'.} |
|
47 | 49 |
\item{call.method}{character string specifying the genotype calling algorithm to use ('crlmm' or 'krlmm').} |
48 | 50 |
\item{trueCalls}{ matrix specifying known Genotype calls for a subset of samples and features(1 - AA, 2 - AB, 3 - BB).} |
49 | 51 |
} |
git-svn-id: file:///home/git/hedgehog.fhcrc.org/bioconductor/trunk/madman/Rpacks/crlmm@80947 bc3139a8-67e5-0310-9ffc-ced21a209358
... | ... |
@@ -17,7 +17,8 @@ |
17 | 17 |
\usage{ |
18 | 18 |
genotypeInf(cnSet, mixtureParams, probs = rep(1/3, 3), SNRMin = 5, |
19 | 19 |
recallMin = 10, recallRegMin = 1000, verbose = TRUE, returnParams = |
20 |
-TRUE, badSNP = 0.7, gender = NULL, DF = 6, cdfName, call.method="crlmm") |
|
20 |
+TRUE, badSNP = 0.7, gender = NULL, DF = 6, cdfName, call.method="crlmm", |
|
21 |
+trueCalls = NULL) |
|
21 | 22 |
} |
22 | 23 |
%- maybe also 'usage' for other objects documented here. |
23 | 24 |
\arguments{ |
... | ... |
@@ -44,6 +45,7 @@ TRUE, badSNP = 0.7, gender = NULL, DF = 6, cdfName, call.method="crlmm") |
44 | 45 |
\item{cdfName}{\code{character} string indicating which annotation |
45 | 46 |
package to load.} |
46 | 47 |
\item{call.method}{character string specifying the genotype calling algorithm to use ('crlmm' or 'krlmm').} |
48 |
+ \item{trueCalls}{ matrix specifying known Genotype calls for a subset of samples and features(1 - AA, 2 - AB, 3 - BB).} |
|
47 | 49 |
} |
48 | 50 |
|
49 | 51 |
\details{ |
... | ... |
@@ -60,6 +62,16 @@ TRUE, badSNP = 0.7, gender = NULL, DF = 6, cdfName, call.method="crlmm") |
60 | 62 |
the transformation 'round(-1000*log2(1-p))', where p is the |
61 | 63 |
probability. The function \code{i2P} can be used to convert the |
62 | 64 |
integers back to the scale of probabilities. |
65 |
+ |
|
66 |
+ An optional \code{trueCalls} argument can be provided to KRLMM method |
|
67 |
+ which contains known genotype calls(can contain some NAs) for some |
|
68 |
+ samples and SNPs. This will used to compute KRLMM parameters by calling |
|
69 |
+ \code{vglm} function from \code{VGAM} package. |
|
70 |
+ |
|
71 |
+ The KRLMM method makes use of functions provided in \code{parallel} |
|
72 |
+ package to speed up the process. It by default initialises up to |
|
73 |
+ 8 clusters. This is configurable by setting up an option named |
|
74 |
+ "krlmm.cores", e.g. options("krlmm.cores" = 16). |
|
63 | 75 |
} |
64 | 76 |
|
65 | 77 |
\value{ |
* collab:
add warning in vignette about NAs with BafLrrSetList function
Added Human Omni Express Exome 8 v1.1b as a supported chip
updated version number of pacakge and man pages to reflect these changes
skeleton for krlmm capability added. genotype.Illumina() can now take and XY object as input
update copynumber.Rnw to use BafLrrSetList
updates to vignettes
update namespace
# Please enter a commit message to explain why this merge is necessary,
# especially if it merges an updated upstream into a topic branch.
#
# Lines starting with '#' will be ignored, and an empty message aborts
# the commit.
git-svn-id: file:///home/git/hedgehog.fhcrc.org/bioconductor/trunk/madman/Rpacks/crlmm@79138 bc3139a8-67e5-0310-9ffc-ced21a209358
... | ... |
@@ -9,7 +9,7 @@ |
9 | 9 |
\description{ |
10 | 10 |
|
11 | 11 |
Genotyping of Illumina Infinium II arrays. This function |
12 |
- provides CRLMM genotypes and confidence scores for the the |
|
12 |
+ provides CRLMM/KRLMM genotypes and confidence scores for the the |
|
13 | 13 |
polymorphic markers and is a required step prior to copy |
14 | 14 |
number estimation. |
15 | 15 |
|
... | ... |
@@ -17,7 +17,7 @@ |
17 | 17 |
\usage{ |
18 | 18 |
genotypeInf(cnSet, mixtureParams, probs = rep(1/3, 3), SNRMin = 5, |
19 | 19 |
recallMin = 10, recallRegMin = 1000, verbose = TRUE, returnParams = |
20 |
-TRUE, badSNP = 0.7, gender = NULL, DF = 6, cdfName) |
|
20 |
+TRUE, badSNP = 0.7, gender = NULL, DF = 6, cdfName, call.method="crlmm") |
|
21 | 21 |
} |
22 | 22 |
%- maybe also 'usage' for other objects documented here. |
23 | 23 |
\arguments{ |
... | ... |
@@ -43,11 +43,12 @@ TRUE, badSNP = 0.7, gender = NULL, DF = 6, cdfName) |
43 | 43 |
t-distribution.} |
44 | 44 |
\item{cdfName}{\code{character} string indicating which annotation |
45 | 45 |
package to load.} |
46 |
+ \item{call.method}{character string specifying the genotype calling algorithm to use ('crlmm' or 'krlmm').} |
|
46 | 47 |
} |
47 | 48 |
|
48 | 49 |
\details{ |
49 | 50 |
|
50 |
- The CRLMM genotype calls and confidence scores are written to |
|
51 |
+ The genotype calls and confidence scores are written to |
|
51 | 52 |
file using \code{ff} protocols for I/O. For the most part, |
52 | 53 |
the calls and confidence scores can be accessed as though the |
53 | 54 |
data is in memory through the methods \code{snpCall} and |
* mymac:
add AffyGW.pdf
update vignettes in inst/scripts
Change argument of validCEL to celfiles
Update constructInf to accommodate GenomeDataFrame class for featureData
bump version to 1.13.7
Add doRUnit.R
Add celfile-utils.Rd
Streamlne some of the Rd files
add validCEL function that checks whether all celfiles can be read
getFeatureData returns GenomeAnnotatedDataFrame
Remove imports from methods. Remove pdf of illumina_copynumber.pdf (large file) and copynumber.pdf
getFeatureDAta returns GenomeAnnotatedDataFrame
Remove separate vignette for copy number in inst/scripts. Include copynumber section in both affy and illumina pipelines.
update documentation files for genotype.Illumina, preprocessInf, and genotypeInf (cdfName added as argument. Indicate that 'batch' should be a character string)
pass cdfName to genotypeInf and preprocessInf
add unitTests and cn-functions for 'simple usage'
Combine AffyPreprocess and copynumber. Combine IlluminaPreprocess and copynumber
remove depency on ff to allow installation on my mac
git-svn-id: file:///home/git/hedgehog.fhcrc.org/bioconductor/trunk/madman/Rpacks/crlmm@62108 bc3139a8-67e5-0310-9ffc-ced21a209358
... | ... |
@@ -15,7 +15,9 @@ |
15 | 15 |
|
16 | 16 |
} |
17 | 17 |
\usage{ |
18 |
-genotypeInf(cnSet, mixtureParams, probs = rep(1/3, 3), SNRMin = 5, recallMin = 10, recallRegMin = 1000, verbose = TRUE, returnParams = TRUE, badSNP = 0.7, gender = NULL, DF = 6) |
|
18 |
+genotypeInf(cnSet, mixtureParams, probs = rep(1/3, 3), SNRMin = 5, |
|
19 |
+recallMin = 10, recallRegMin = 1000, verbose = TRUE, returnParams = |
|
20 |
+TRUE, badSNP = 0.7, gender = NULL, DF = 6, cdfName) |
|
19 | 21 |
} |
20 | 22 |
%- maybe also 'usage' for other objects documented here. |
21 | 23 |
\arguments{ |
... | ... |
@@ -37,7 +39,10 @@ genotypeInf(cnSet, mixtureParams, probs = rep(1/3, 3), SNRMin = 5, recallMin = 1 |
37 | 39 |
\item{gender}{ integer vector ( male = 1, female =2 ) or missing, |
38 | 40 |
with same length as filenames. If missing, the gender is |
39 | 41 |
predicted.} |
40 |
- \item{DF}{'integer' with number of degrees of freedom to use with t-distribution.} |
|
42 |
+ \item{DF}{'integer' with number of degrees of freedom to use with |
|
43 |
+ t-distribution.} |
|
44 |
+ \item{cdfName}{\code{character} string indicating which annotation |
|
45 |
+ package to load.} |
|
41 | 46 |
} |
42 | 47 |
|
43 | 48 |
\details{ |
... | ... |
@@ -69,7 +74,8 @@ confidence scores can be retrieved using accessors for the |
69 | 74 |
R. Scharpf |
70 | 75 |
} |
71 | 76 |
\seealso{ |
72 |
- \code{\link{crlmm}}, \code{\link{snpCall}}, \code{\link{snpCallProbability}} |
|
77 |
+ \code{\link{crlmm}}, \code{\link{snpCall}}, |
|
78 |
+ \code{\link{snpCallProbability}}, \code{\link{annotationPackages}} |
|
73 | 79 |
} |
74 | 80 |
\examples{ |
75 | 81 |
## See the 'illumina_copynumber' vignette in inst/scripts of |
git-svn-id: file:///home/git/hedgehog.fhcrc.org/bioconductor/trunk/madman/Rpacks/crlmm@54164 bc3139a8-67e5-0310-9ffc-ced21a209358
1 | 1 |
new file mode 100644 |
... | ... |
@@ -0,0 +1,78 @@ |
1 |
+\name{genotypeInf} |
|
2 |
+\alias{genotypeInf} |
|
3 |
+ |
|
4 |
+\title{ |
|
5 |
+ |
|
6 |
+ Genotyping of Illumina Infinium II arrays. |
|
7 |
+ |
|
8 |
+} |
|
9 |
+\description{ |
|
10 |
+ |
|
11 |
+ Genotyping of Illumina Infinium II arrays. This function |
|
12 |
+ provides CRLMM genotypes and confidence scores for the the |
|
13 |
+ polymorphic markers and is a required step prior to copy |
|
14 |
+ number estimation. |
|
15 |
+ |
|
16 |
+} |
|
17 |
+\usage{ |
|
18 |
+genotypeInf(cnSet, mixtureParams, probs = rep(1/3, 3), SNRMin = 5, recallMin = 10, recallRegMin = 1000, verbose = TRUE, returnParams = TRUE, badSNP = 0.7, gender = NULL, DF = 6) |
|
19 |
+} |
|
20 |
+%- maybe also 'usage' for other objects documented here. |
|
21 |
+\arguments{ |
|
22 |
+ \item{cnSet}{An object of class \code{CNSet}} |
|
23 |
+ \item{mixtureParams}{ |
|
24 |
+ \code{data.frame} containing mixture model parameters needed for |
|
25 |
+ genotyping. The mixture model parameters are estimated from the |
|
26 |
+ \code{preprocessInf} function. |
|
27 |
+ } |
|
28 |
+ \item{probs}{'numeric' vector with priors for AA, AB and BB.} |
|
29 |
+ \item{SNRMin}{'numeric' scalar defining the minimum SNR used to filter |
|
30 |
+ out samples.} |
|
31 |
+ \item{recallMin}{Minimum number of samples for recalibration. } |
|
32 |
+ \item{recallRegMin}{Minimum number of SNP's for regression.} |
|
33 |
+ \item{verbose}{ 'logical.' Whether to print descriptive messages during processing.} |
|
34 |
+ \item{returnParams}{'logical'. Return recalibrated parameters from crlmm.} |
|
35 |
+ \item{badSNP}{'numeric'. Threshold to flag as bad SNP (affects |
|
36 |
+ batchQC)} |
|
37 |
+ \item{gender}{ integer vector ( male = 1, female =2 ) or missing, |
|
38 |
+ with same length as filenames. If missing, the gender is |
|
39 |
+ predicted.} |
|
40 |
+ \item{DF}{'integer' with number of degrees of freedom to use with t-distribution.} |
|
41 |
+} |
|
42 |
+ |
|
43 |
+\details{ |
|
44 |
+ |
|
45 |
+ The CRLMM genotype calls and confidence scores are written to |
|
46 |
+ file using \code{ff} protocols for I/O. For the most part, |
|
47 |
+ the calls and confidence scores can be accessed as though the |
|
48 |
+ data is in memory through the methods \code{snpCall} and |
|
49 |
+ \code{snpCallProbability}, respectively. |
|
50 |
+ |
|
51 |
+ The genotype calls are stored using an integer representation: 1 |
|
52 |
+ - AA, 2 - AB, 3 - BB. Similarly, the call probabilities are |
|
53 |
+ stored using an integer representation to reduce file size using |
|
54 |
+ the transformation 'round(-1000*log2(1-p))', where p is the |
|
55 |
+ probability. The function \code{i2P} can be used to convert the |
|
56 |
+ integers back to the scale of probabilities. |
|
57 |
+ } |
|
58 |
+ |
|
59 |
+\value{ |
|
60 |
+ |
|
61 |
+Logical. If the genotyping is completed, the value 'TRUE' is |
|
62 |
+returned. Note that \code{assayData} elements 'call' and |
|
63 |
+'callProbability' are updated on disk. Therefore, the genotypes and |
|
64 |
+confidence scores can be retrieved using accessors for the |
|
65 |
+\code{CNSet} class. |
|
66 |
+ |
|
67 |
+} |
|
68 |
+\author{ |
|
69 |
+R. Scharpf |
|
70 |
+} |
|
71 |
+\seealso{ |
|
72 |
+ \code{\link{crlmm}}, \code{\link{snpCall}}, \code{\link{snpCallProbability}} |
|
73 |
+} |
|
74 |
+\examples{ |
|
75 |
+ ## See the 'illumina_copynumber' vignette in inst/scripts of |
|
76 |
+ ## the source package |
|
77 |
+} |
|
78 |
+\keyword{classif} |
|
0 | 79 |
\ No newline at end of file |