Merge branch 'develop'

MANIFEST.in

@@ -1,4 +1,4 @@
 include README.mkd
-include configuration_example_1_of_2.conf
-include configuration_example_2_of_2.conf
+include configuration_example_1_of_2.ini
+include configuration_example_2_of_2.ini
 include LICENSE.txt

configuration_example_1_of_2.conf → configuration_example_1_of_2.ini

@@ -5,6 +5,27 @@
 
 [1]
 # ##############################################################################
+# Checks sample contamination using the bafRegress tool
+# (http://genome.sph.umich.edu/wiki/BAFRegress). Field name can be modify using
+# options (as describe below).
+# ##############################################################################
+
+script = contamination
+raw-dir = /PATH/TO/DIRECTORY/CONTAINING/INTENSITIES.txt
+# colsample = Sample Name
+# colmarker = SNP Name
+# colbaf = B Allele Freq
+# colab1 = Allele1 - AB
+# colab2 = Allele2 - AB
+# sge
+# sge-walltime = WRITE WALLTIME ONLY IF REQUIRED
+# sge-nodes = WRITE NB NODES AND NB PROCESSOR PER NODE ONLY IF REQUIRED
+# sample-per-run-for-sge = 30
+
+
+
+[2]
+# ##############################################################################
 # Checks missing rate and pairwise concordance of duplicated samples. Duplicated
 # samples should have same family and individual identification numbers. The
 # names can be modified directly in the transposed pedfile.
@@ -16,7 +37,7 @@ script = duplicated_samples
 
 
 
-[2]
+[3]
 # ##############################################################################
 # Checks missing rate and pairwise concordance of duplicated markers. Duplicated
 # markers are found by looking at their chromosomal position. No modification of
@@ -30,7 +51,7 @@ script = duplicated_snps
 
 
 
-[3]
+[4]
 # ##############################################################################
 # Finds and removes markers which have a missing rate of 100% or markers (not
 # located on mitochondrial chromosome) that have a heterozygosity rate of 0%.
@@ -40,7 +61,7 @@ script = noCall_hetero_snps
 
 
 
-[4]
+[5]
 # ##############################################################################
 # Removes sample with a missing rate higher than a user defined threshold. For
 # this step, we recommend using a threshold of 10% missing rate as samples with
@@ -52,7 +73,7 @@ script = sample_missingness
 
 
 
-[5]
+[6]
 # ##############################################################################
 # Removes markers with a missing rate higher than a user defined threshold. For
 # this step, we recommend using a threshold of 2% missing rate.
@@ -63,7 +84,7 @@ script = snp_missingness
 
 
 
-[6]
+[7]
 # ##############################################################################
 # Removes sample with a missing rate higher than a user defined threshold. For
 # this step, we recommend using a threshold of 2% missing rate.
@@ -74,7 +95,7 @@ mind = 0.02
 
 
 
-[7]
+[8]
 # ##############################################################################
 # Using PLINK, finds samples with gender issues, according to heterozygosity
 # rate on the X chromosome. If you want to produce a gender plot, you need to
@@ -95,10 +116,11 @@ script = sex_check
 # lrr-baf
 # lrr-baf-raw-dir = /PATH/TO/DIRECTORY/CONTAINING/BAF_LRR_FILES.txt
 # lrr-baf-format = png
+# lrr-baf-dpi = 300
 
 
 
-[8]
+[9]
 # ##############################################################################
 # Using PLINK, performs a plate bias analysis, using a p value threshold of
 # 1.0e-7.
@@ -110,7 +132,7 @@ loop-assoc = /PATH/TO/FILE/CONTAINING/PLATE_INFORMATION.txt
 
 
 
-[9]
+[10]
 # ##############################################################################
 # Checks for related individual and randomly keeps one of each related group. If
 # you have a server with a DRMAA-compliant distributed resource management
@@ -130,7 +152,7 @@ script = find_related_samples
 
 
 
-[10]
+[11]
 # ##############################################################################
 # Using PLINK, computes the MDS value of each sample, and using three reference
 # populations (CEU, YRI and JPT-CHB), finds outliers of one of those three

configuration_example_2_of_2.conf → configuration_example_2_of_2.ini

@@ -19,21 +19,25 @@
 # directories using the PLINK's binary file located in
 # "remove_heterozygous_haploid".
 
-[11]
+[12]
 # ##############################################################################
 # After manually checking that everything went fine in the previous steps, you
 # need to create a list of samples to remove from steps [7] to [10] and a list
 # of markers to exclude from steps [6]. Just create a file containing family and
-# individual identification numbers for all those samples to remove.
+# individual identification numbers for all those samples to remove. Note that
+# the two options 'reason-marker' and 'reason-sample' are for the automatic
+# report generated after the analysis.
 # ##############################################################################
 
 script = subset
+reason-marker = reason for marker exclusion
+reason-sample = reason for sample exclusion
 remove = /PATH/TO/FILE/CONTAINING/ALL_SAMPLES_FROM_PREVIOUS_STEPS_TO_REMOVE.txt
 exclude = /PATH/TO/FILE/CONTAINING/ALL_MARKERS_FROM_PREVIOUS_STEPS_TO_EXCLUDE.txt
 
 
 
-[12]
+[13]
 # ##############################################################################
 # Removes heterozygous haploid genotypes from the dataset.
 # ##############################################################################
@@ -42,7 +46,7 @@ script = remove_heterozygous_haploid
 
 
 
-[13]
+[14]
 # ##############################################################################
 # Flags uninformative markers (with a MAF of 0). This step only flag markers.
 # You might want to exclude them later on.
@@ -52,7 +56,7 @@ script = flag_maf_zero
 
 
 
-[14]
+[15]
 # ##############################################################################
 # Flags markers that fail HWE test for a p value of 1e-4 and after Bonferroni
 # correction. This step only flag markers. You might want to exclude them later

docs/_static/configuration_files/configuration_example_1_of_2.conf → docs/_static/configuration_files/configuration_example_1_of_2.ini

@@ -5,6 +5,27 @@
 
 [1]
 # ##############################################################################
+# Checks sample contamination using the bafRegress tool
+# (http://genome.sph.umich.edu/wiki/BAFRegress). Field name can be modify using
+# options (as describe below).
+# ##############################################################################
+
+script = contamination
+raw-dir = /PATH/TO/DIRECTORY/CONTAINING/INTENSITIES.txt
+# colsample = Sample Name
+# colmarker = SNP Name
+# colbaf = B Allele Freq
+# colab1 = Allele1 - AB
+# colab2 = Allele2 - AB
+# sge
+# sge-walltime = WRITE WALLTIME ONLY IF REQUIRED
+# sge-nodes = WRITE NB NODES AND NB PROCESSOR PER NODE ONLY IF REQUIRED
+# sample-per-run-for-sge = 30
+
+
+
+[2]
+# ##############################################################################
 # Checks missing rate and pairwise concordance of duplicated samples. Duplicated
 # samples should have same family and individual identification numbers. The
 # names can be modified directly in the transposed pedfile.
@@ -16,7 +37,7 @@ script = duplicated_samples
 
 
 
-[2]
+[3]
 # ##############################################################################
 # Checks missing rate and pairwise concordance of duplicated markers. Duplicated
 # markers are found by looking at their chromosomal position. No modification of
@@ -30,7 +51,7 @@ script = duplicated_snps
 
 
 
-[3]
+[4]
 # ##############################################################################
 # Finds and removes markers which have a missing rate of 100% or markers (not
 # located on mitochondrial chromosome) that have a heterozygosity rate of 0%.
@@ -40,7 +61,7 @@ script = noCall_hetero_snps
 
 
 
-[4]
+[5]
 # ##############################################################################
 # Removes sample with a missing rate higher than a user defined threshold. For
 # this step, we recommend using a threshold of 10% missing rate as samples with
@@ -52,7 +73,7 @@ script = sample_missingness
 
 
 
-[5]
+[6]
 # ##############################################################################
 # Removes markers with a missing rate higher than a user defined threshold. For
 # this step, we recommend using a threshold of 2% missing rate.
@@ -63,7 +84,7 @@ script = snp_missingness
 
 
 
-[6]
+[7]
 # ##############################################################################
 # Removes sample with a missing rate higher than a user defined threshold. For
 # this step, we recommend using a threshold of 2% missing rate.
@@ -74,7 +95,7 @@ mind = 0.02
 
 
 
-[7]
+[8]
 # ##############################################################################
 # Using PLINK, finds samples with gender issues, according to heterozygosity
 # rate on the X chromosome. If you want to produce a gender plot, you need to
@@ -95,10 +116,11 @@ script = sex_check
 # lrr-baf
 # lrr-baf-raw-dir = /PATH/TO/DIRECTORY/CONTAINING/BAF_LRR_FILES.txt
 # lrr-baf-format = png
+# lrr-baf-dpi = 300
 
 
 
-[8]
+[9]
 # ##############################################################################
 # Using PLINK, performs a plate bias analysis, using a p value threshold of
 # 1.0e-7.
@@ -110,7 +132,7 @@ loop-assoc = /PATH/TO/FILE/CONTAINING/PLATE_INFORMATION.txt
 
 
 
-[9]
+[10]
 # ##############################################################################
 # Checks for related individual and randomly keeps one of each related group. If
 # you have a server with a DRMAA-compliant distributed resource management
@@ -130,7 +152,7 @@ script = find_related_samples
 
 
 
-[10]
+[11]
 # ##############################################################################
 # Using PLINK, computes the MDS value of each sample, and using three reference
 # populations (CEU, YRI and JPT-CHB), finds outliers of one of those three

docs/_static/configuration_files/configuration_example_2_of_2.conf → docs/_static/configuration_files/configuration_example_2_of_2.ini

@@ -19,21 +19,25 @@
 # directories using the PLINK's binary file located in
 # "remove_heterozygous_haploid".
 
-[11]
+[12]
 # ##############################################################################
 # After manually checking that everything went fine in the previous steps, you
 # need to create a list of samples to remove from steps [7] to [10] and a list
 # of markers to exclude from steps [6]. Just create a file containing family and
-# individual identification numbers for all those samples to remove.
+# individual identification numbers for all those samples to remove. Note that
+# the two options 'reason-marker' and 'reason-sample' are for the automatic
+# report generated after the analysis.
 # ##############################################################################
 
 script = subset
+reason-marker = reason for marker exclusion
+reason-sample = reason for sample exclusion
 remove = /PATH/TO/FILE/CONTAINING/ALL_SAMPLES_FROM_PREVIOUS_STEPS_TO_REMOVE.txt
 exclude = /PATH/TO/FILE/CONTAINING/ALL_MARKERS_FROM_PREVIOUS_STEPS_TO_EXCLUDE.txt
 
 
 
-[12]
+[13]
 # ##############################################################################
 # Removes heterozygous haploid genotypes from the dataset.
 # ##############################################################################
@@ -42,7 +46,7 @@ script = remove_heterozygous_haploid
 
 
 
-[13]
+[14]
 # ##############################################################################
 # Flags uninformative markers (with a MAF of 0). This step only flag markers.
 # You might want to exclude them later on.
@@ -52,7 +56,7 @@ script = flag_maf_zero
 
 
 
-[14]
+[15]
 # ##############################################################################
 # Flags markers that fail HWE test for a p value of 1e-4 and after Bonferroni
 # correction. This step only flag markers. You might want to exclude them later

docs/automatic_report.rst

@@ -25,7 +25,7 @@ Report merging
 ==============
 
 On a typical data clean up pipeline, multiple directories will be created (one
-for each of the parts of the pipeline. A script is provided to merge all those
+for each of the parts of the pipeline). A script is provided to merge all those
 reports (one per ``data_clean_up.YYYY-MM-DD_HH.MM.SS`` directory) into a single
 report. Here is the usage of this script:
 
@@ -76,3 +76,12 @@ To execute the report merging procedure, perform the following command:
     background of the automatic report by using the ``--report-title``,
     ``--report-author``, ``--report-number`` or ``--report-background``
     options, respectively.
+
+
+Once again, to compile the final report, perform the following command:
+
+.. code-block:: console
+
+    $ pdflatex pyGenClean_report.tex
+    $ pdflatex pyGenClean_report.tex
+    $ pdflatex pyGenClean_report.tex

docs/configuration_files.rst

@@ -28,7 +28,7 @@ If you want to generate the gender and BAF and LRR plots, you will require to
 provide the intensities (``sex-chr-intensities``  and ``lrr-baf-raw-dir`` in the
 ``sex_check`` section (``[7]``) after uncommenting the required options).
 
-.. literalinclude:: _static/configuration_files/configuration_example_1_of_2.conf
+.. literalinclude:: _static/configuration_files/configuration_example_1_of_2.ini
     :linenos:
     :language: lighttpd
 
@@ -46,7 +46,7 @@ A file containing the samples and markers to be removed should be created using
 the output of the ``sex_check``, ``find_related_samples``, ``check_ethnicity``
 and ``plate_bias`` sections of the :ref:`first_conf_file`.
 
-.. literalinclude:: _static/configuration_files/configuration_example_2_of_2.conf
+.. literalinclude:: _static/configuration_files/configuration_example_2_of_2.ini
     :linenos:
     :language: lighttpd