def runPyCombat(fl):
""" This method was added specifically for AltAnalyze version 2.0.8 (not in the original GitHub code) """
print "Running Combat...",
expr_input_dir = fl.ExpFile()
pheno_dir = formatPhenoFile(fl)
moved_exp_dir = export.findParentDir(expr_input_dir) + "Non-Combat/" + export.findFilename(expr_input_dir)
try:
export.copyFile(expr_input_dir, moved_exp_dir)
print "Moved original expression file to:"
print "\t" + moved_exp_dir
### now overwrite the origin excluding the commented rows
export.cleanFile(expr_input_dir, removeExtra="#") ### remove comments from the original file
except Exception:
None
pheno = pa.read_table(pheno_dir, index_col=0)
dat = pa.read_table(expr_input_dir, index_col=0)
mod = patsy.dmatrix("group", pheno, return_type="dataframe")
t = time.time()
# print dat, pheno.batch, mod;sys.exit()
ebat = combat(dat, pheno.batch, mod, 0)
print "...Combat completed in %.2f seconds" % (time.time() - t)
print "Original expression file over-written with batch effect removal results..."
ebat.to_csv(expr_input_dir, sep="\t")
def normalizeDataset(filename,
output=None,
normalization='quantile',
platform="3'array"):
""" Perform Quantile Normalization on an input expression dataset """
if output == None:
output = filename
moved_exp_dir = export.findParentDir(
filename) + 'Non-Normalized/' + export.findFilename(filename)
try:
export.copyFile(filename, moved_exp_dir)
print 'Moved original expression file to:'
print '\t' + moved_exp_dir
except Exception:
None
if normalization == 'Quantile' or normalization == 'quantile':
print "Importing data..."
sample_expression_db = importExpressionValues(filename)
print "Performing quantile normalization..."
sample_expression_db = RNASeq.quantileNormalizationSimple(
sample_expression_db)
exportExpressionData(output, sample_expression_db)
elif normalization == 'group':
performGroupNormalization(moved_exp_dir, filename, platform)
print 'Exported expression input file to:', output
def runPyCombat(fl):
""" This method was added specifically for AltAnalyze version 2.0.8 (not in the original GitHub code) """
print 'Running Combat...',
expr_input_dir = fl.ExpFile()
pheno_dir = formatPhenoFile(fl)
moved_exp_dir = export.findParentDir(
expr_input_dir) + 'Non-Combat/' + export.findFilename(expr_input_dir)
try:
export.copyFile(expr_input_dir, moved_exp_dir)
print 'Moved original expression file to:'
print '\t' + moved_exp_dir
### now overwrite the origin excluding the commented rows
export.cleanFile(
expr_input_dir,
removeExtra='#') ### remove comments from the original file
except Exception:
None
pheno = pa.read_table(pheno_dir, index_col=0)
dat = pa.read_table(expr_input_dir, index_col=0)
mod = patsy.dmatrix("group", pheno, return_type="dataframe")
t = time.time()
#print dat, pheno.batch, mod;sys.exit()
ebat = combat(dat, pheno.batch, mod, 0)
print "...Combat completed in %.2f seconds" % (time.time() - t)
print 'Original expression file over-written with batch effect removal results...'
ebat.to_csv(expr_input_dir, sep="\t")
def copyReformattedSpeciesMiRAnnotations(type):
existing_species_dirs = unique.read_directory('/AltDatabase/ensembl')
for species in existing_species_dirs:
try:
ir = filepath('AltDatabase/ensembl/'+species+'/'+species+'_microRNA-Ensembl-GOElite_'+type+'.txt')
er = filepath('GOElite/'+species+'_microRNA-Ensembl-GOElite_'+type+'.txt')
export.copyFile(ir, er)
print 'Copied miRNA-target database for:',species, type
except Exception: null=[] ### Occurs for non-species directories
def transferGOSlimGeneAssociations(selected_species):
if selected_species != None: ### Restrict to selected species only
current_species_dirs=selected_species
else:
current_species_dirs = unique.read_directory('/'+database_dir)
for species_code in current_species_dirs:
try:
ens_go_file_dir = filepath(database_dir+'/'+species_code+'/gene-go/Ensembl-GOSlim.txt')
goslim_ens_file = filepath(database_dir+'/'+species_code+'/uid-gene/Ensembl-goslim_goa.txt')
export.copyFile(goslim_ens_file,ens_go_file_dir)
translateToEntrezGene(species_code,ens_go_file_dir)
except Exception: null=[]
def copyJunctionFiles(directory):
root_dir = getFolders(directory)
#print root_dir
for top_level in root_dir: ### e.g.,
try:
files = getFiles(directory+'/'+top_level)
for file in files:
if 'junctions.bed' in file and 'junctionBEDfiles' not in top_level:
source_file = directory+'/'+top_level+'/'+file
source_file = filepath(source_file)
destination_file = directory+'/'+'junctionBEDfiles/'+top_level+'__junctions.bed'
destination_file = filepath(destination_file)
export.copyFile(source_file,destination_file)
print 'copying to:',destination_file
except Exception:
print 'failed to copy', source_file
def normalizeDataset(filename, output=None):
""" Perform Quantile Normalization on an input expression dataset """
print "Importing data..."
sample_expression_db = importExpressionValues(filename)
print "Performing quantile normalization..."
sample_expression_db = RNASeq.quantileNormalizationSimple(sample_expression_db)
if output == None:
output = filename
moved_exp_dir = export.findParentDir(filename) + "Non-Quantile/" + export.findFilename(filename)
try:
export.copyFile(filename, moved_exp_dir)
print "Moved original expression file to:"
print "\t" + moved_exp_dir
except Exception:
None
exportExpressionData(output, sample_expression_db)
print "Exported expression input file to:", output
def normalizeDataset(filename,output = None, normalization='quantile',platform="3'array"):
""" Perform Quantile Normalization on an input expression dataset """
if output==None:
output = filename
moved_exp_dir = export.findParentDir(filename)+'Non-Normalized/'+export.findFilename(filename)
try:
export.copyFile(filename, moved_exp_dir)
print 'Moved original expression file to:'
print '\t'+moved_exp_dir
except Exception: None
if normalization == 'Quantile' or normalization == 'quantile':
print "Importing data..."
sample_expression_db = importExpressionValues(filename)
print "Performing quantile normalization..."
sample_expression_db = RNASeq.quantileNormalizationSimple(sample_expression_db)
exportExpressionData(output,sample_expression_db)
elif normalization == 'group':
performGroupNormalization(moved_exp_dir,filename,platform)
print 'Exported expression input file to:',output
def normalizeDataset(filename, output=None):
""" Perform Quantile Normalization on an input expression dataset """
print "Importing data..."
sample_expression_db = importExpressionValues(filename)
print "Performing quantile normalization..."
sample_expression_db = RNASeq.quantileNormalizationSimple(
sample_expression_db)
if output == None:
output = filename
moved_exp_dir = export.findParentDir(
filename) + 'Non-Quantile/' + export.findFilename(filename)
try:
export.copyFile(filename, moved_exp_dir)
print 'Moved original expression file to:'
print '\t' + moved_exp_dir
except Exception:
None
exportExpressionData(output, sample_expression_db)
print 'Exported expression input file to:', output
def importDomainGeneAssociations(species_code,source_path):
try:
destination_path = filepath(database_dir+'/'+species_code+'/gene-mapp/Ensembl-Domains.txt')
export.copyFile(source_path,destination_path)
translateToEntrezGene(species_code,destination_path)
except Exception: null=[]
