def generate_cummerbund_plots(self, ctx, cummerbundParams):
# ctx is the context object
# return variables are: returnVal
#BEGIN generate_cummerbund_plots
params = cummerbundParams
returnVal = params['ws_cummerbund_output']
#Set up workspace client
user_token = ctx['token']
ws_client = Workspace(url=self.__WS_URL, token=user_token)
#Read the input cuffdiff workspace object json file and get filehandle for cuffdiff tar file
s_res = ws_client.get_objects([{
'name' : params['ws_cuffdiff_id'],
'workspace' : params['workspace_name']
}])
# Check if workspace has data
if len(s_res) == 0:
self.__LOGGER.info("Workspace did not return any objects")
return returnVal
cuffdiff_dir = script_util2.extract_cuffdiff_data (self.__LOGGER, self.__SHOCK_URL, self.__SCRATCH, s_res, user_token)
self.__LOGGER.info("Cuffdiff folder = " + cuffdiff_dir)
if (cuffdiff_dir is False):
return returnVal
# Run R script to run cummerbund json and update the cummerbund output json file
# Prepare output object.
outputobject=dict()
# Prepare output plot list
cummerbundplotset=[]
# List of plots to generate
plotlist = [
{ 'file': "dispersionplot.R",
'title': "Dispersion plot",
'description': "Dispersion plot is the quality measure of the data. It estimates deviation from threshold against counts in FPKM." },
{ 'file': "fpkmscvplot.R",
'title': "Genes CV plot",
'description': "The squared coefficient of variation plot is a normalized measure of cross-replicate variability that can be useful for evaluating the quality of RNA-seq data." },
{ 'file': "isoformscvplot.R",
'title': "Isoform CV plot",
'description': "The squared coefficient of variation plot is a normalized measure of cross-replicate variability that can be useful for evaluating the quality of RNA-seq data.Differences in CV2 can result in lower numbers of differentially expressed isoforms due to a higher degree of variability between replicate fpkm estimates." },
{ 'file': "densityplot.R",
'title': "Density plot",
'description': "The density plot shows the distribution of FPKM scores across samples" },
{ 'file': "csdensityrepplot.R",
'title': "Replicates density plot",
'description': "The replicates density plot shows the distribution of FPKM scores across sample replicates" },
{ 'file': "boxplot.R",
'title': "Box plots",
'description': "The box plots show the FPKM distribution across samples." },
{ 'file': "boxrepplot.R",
'title': "Box plots of replicates",
'description': "The box plots of replicates show the FPKM distribution across sample replicates." },
{ 'file': "pairwisescatterplots.R",
'title': "Pairwise scatter plots",
'description': "The scatterplots show differences in gene expression between two samples. If two samples are identical, all genes will fall on the mid-line." },
{ 'file': "volcanomatrixplot.R",
'title': "Volcano matrix plots",
'description': "Volcano matrix plot is a scatter plot that also identifies differentially expressed genes (by color) between samples based on log2 fold change cut off." },
{ 'file': "pcaplot.R",
'title': "PCA plot",
'description': "Principal Component Analysis (PCA) is an informative approach for dimensionality reduction for exploring teh relationship between sample conditions." },
{ 'file': "pcarepplot.R",
'title': "PCA plot including replicates",
'description': "Principal Component Analysis (PCA) is an informative approach for dimensionality reduction for exploring teh relationship between sample conditions including replicates." },
{ 'file': "mdsplot.R",
'title': "Multi-dimensional scaling plot",
'description': "Multi-dimensional scaling plots are similar to PCA plots and useful for determining the major sources of variation in the dataset. " },
{ 'file': "mdsrepplot.R",
'title': "Multi-dimensional scaling plot including replicates",
'description': "Multi-dimensional scaling plot including replicates are similar to PCA plots and useful for determining the major sources of variation in the dataset with replicates. These can be useful to determine any systematic bias that may be present between conditions." }
]
#TODO.. Giving Rplot.pdf
# { 'file': "dendrogramplot.R",
# 'title': "Dendrogram",
# 'description': "Dendrogram based on the JS (Jensen-Shannon divergence) distance" },
#
# { 'file': "dendrogramrepplot.R",
# 'title': "Dendrogram including replicates",
# 'description': "Dendrogram including replicates based on the JS (Jensen-Shannon divergence) distance" },
# Iterate through the plotlist and generate the images and json files.
for plot in plotlist:
status = script_util2.rplotandupload(self.__LOGGER, self.__SCRATCH, self.__RSCRIPTS,
plot['file'], self.__SHOCK_URL, self.__HS_URL, user_token,
cummerbundplotset, plot['title'], plot['description'], cuffdiff_dir)
if status == False:
self.__LOGGER.info("Problem generating image and json file - " + plot["file"])
# Populate the output object
outputobject['cummerbundplotSet'] = cummerbundplotset
#TODO: Need to figure out how to get rnaseq experiment id
outputobject['rnaseq_experiment_id'] = "rnaseq_experiment_id"
outputobject['cuffdiff_input_id'] = params['ws_cuffdiff_id']
res = ws_client.save_objects({
"workspace":params['workspace_name'],
"objects": [{
"type":"KBaseRNASeq.cummerbund_output",
"data":outputobject,
"name":params["ws_cummerbund_output"]}]
})
#END generate_cummerbund_plots
# At some point might do deeper type checking...
if not isinstance(returnVal, basestring):
raise ValueError('Method generate_cummerbund_plots return value ' +
'returnVal is not type basestring as required.')
# return the results
return [returnVal]
def generate_cummerbund_plots(self, ctx, cummerbundParams):
# ctx is the context object
# return variables are: returnVal
#BEGIN generate_cummerbund_plots
params = cummerbundParams
returnVal = params['ws_cummerbund_output']
#Set up workspace client
user_token = ctx['token']
ws_client = Workspace(url=self.__WS_URL, token=user_token)
#Read the input cuffdiff workspace object json file and get filehandle for cuffdiff tar file
s_res = ws_client.get_objects([{
'name' : params['ws_cuffdiff_id'],
'workspace' : params['workspace_name']
}])
# Check if workspace has data
if len(s_res) == 0:
self.__LOGGER.info("Workspace did not return any objects")
return returnVal
# Get input data Shock Id and Filename.
cuffdiff_shock_id = s_res[0]['data']['file']['id']
cuffdiff_file_name = s_res[0]['data']['file']['file_name']
#cuffdiff_file_name =None
filesize = None
# Download tar file
dx = script_util.download_file_from_shock( self.__LOGGER,
self.__SHOCK_URL, cuffdiff_shock_id, cuffdiff_file_name,
self.__SCRATCH, filesize, user_token)
#Decompress tar file and keep it in a directory
tarfile = join(self.__SCRATCH, cuffdiff_file_name)
dstnExtractFolder = join(self.__SCRATCH, "cuffdiffData")
if not os.path.exists(dstnExtractFolder):
os.makedirs(dstnExtractFolder)
untarStatus = script_util2.untar_files(self.__LOGGER, tarfile, dstnExtractFolder)
if untarStatus == False:
self.__LOGGER.info("Problem extracting the archive")
return returnVal
foldersinExtractFolder = os.listdir(dstnExtractFolder)
if len(foldersinExtractFolder) == 0:
self.__LOGGER.info("Problem extracting the archive")
return returnVal
# Run R script to run cummerbund json and update the cummerbund output json file
cuffdiff_dir = join(dstnExtractFolder, foldersinExtractFolder[0])
self.__LOGGER.info("Cuffdiff folder = " + cuffdiff_dir)
# Prepare output object.
outputobject=dict()
# Prepare output plot list
cummerbundplotset=[]
# List of plots to generate
plotlist = [
{ 'file': "dispersionplot.R",
'title': "Dispersion plot",
'description': "Dispersion plot" },
{ 'file': "pcaplot.R",
'title': "PCA plot",
'description': "PCA plot" },
{ 'file': "fpkmscvplot.R",
'title': "FPKM SCV plot",
'description': "FPKM SCV plot" }
]
# Iterate through the plotlist and generate the images and json files.
for plot in plotlist:
status = script_util2.rplotandupload(self.__LOGGER, self.__SCRATCH, self.__RSCRIPTS,
plot['file'], self.__SHOCK_URL, self.__HS_URL, user_token,
cummerbundplotset, plot['title'], plot['description'], cuffdiff_dir)
if status == False:
self.__LOGGER.info("Problem generating image and json file - " + plot["file"])
# Populate the output object
outputobject['cummerbundplotSet'] = cummerbundplotset
#TODO: Need to figure out how to get rnaseq experiment id
outputobject['rnaseq_experiment_id'] = "rnaseq_experiment_id"
outputobject['cuffdiff_input_id'] = params['ws_cuffdiff_id']
res = ws_client.save_objects({
"workspace":params['workspace_name'],
"objects": [{
"type":"KBaseRNASeq.cummerbund_output",
"data":outputobject,
"name":params["ws_cummerbund_output"]}]
})
#END generate_cummerbund_plots
# At some point might do deeper type checking...
if not isinstance(returnVal, basestring):
raise ValueError('Method generate_cummerbund_plots return value ' +
'returnVal is not type basestring as required.')
# return the results
return [returnVal]
def generate_cummerbund_plots(self, ctx, cummerbundParams):
# ctx is the context object
# return variables are: returnVal
#BEGIN generate_cummerbund_plots
params = cummerbundParams
returnVal = params['ws_cummerbund_output']
#Set up workspace client
user_token = ctx['token']
ws_client = Workspace(url=self.__WS_URL, token=user_token)
#Read the input cuffdiff workspace object json file and get filehandle for cuffdiff tar file
s_res = ws_client.get_objects([{
'name': params['ws_cuffdiff_id'],
'workspace': params['workspace_name']
}])
# Check if workspace has data
if len(s_res) == 0:
self.__LOGGER.info("Workspace did not return any objects")
return returnVal
cuffdiff_dir = script_util2.extract_cuffdiff_data(
self.__LOGGER, self.__SHOCK_URL, self.__SCRATCH, s_res, user_token)
self.__LOGGER.info("Cuffdiff folder = " + cuffdiff_dir)
if (cuffdiff_dir is False):
return returnVal
# Run R script to run cummerbund json and update the cummerbund output json file
# Prepare output object.
outputobject = dict()
# Prepare output plot list
cummerbundplotset = []
# List of plots to generate
plotlist = [{
'file':
"dispersionplot.R",
'title':
"Dispersion plot",
'description':
"Dispersion plot is the quality measure of the data. It estimates deviation from threshold against counts in FPKM."
}, {
'file':
"fpkmscvplot.R",
'title':
"Genes CV plot",
'description':
"The squared coefficient of variation plot is a normalized measure of cross-replicate variability that can be useful for evaluating the quality of RNA-seq data."
}, {
'file':
"isoformscvplot.R",
'title':
"Isoform CV plot",
'description':
"The squared coefficient of variation plot is a normalized measure of cross-replicate variability that can be useful for evaluating the quality of RNA-seq data.Differences in CV2 can result in lower numbers of differentially expressed isoforms due to a higher degree of variability between replicate fpkm estimates."
}, {
'file':
"densityplot.R",
'title':
"Density plot",
'description':
"The density plot shows the distribution of FPKM scores across samples"
}, {
'file':
"csdensityrepplot.R",
'title':
"Replicates density plot",
'description':
"The replicates density plot shows the distribution of FPKM scores across sample replicates"
}, {
'file':
"boxplot.R",
'title':
"Box plots",
'description':
"The box plots show the FPKM distribution across samples."
}, {
'file':
"boxrepplot.R",
'title':
"Box plots of replicates",
'description':
"The box plots of replicates show the FPKM distribution across sample replicates."
}, {
'file':
"pairwisescatterplots.R",
'title':
"Pairwise scatter plots",
'description':
"The scatterplots show differences in gene expression between two samples. If two samples are identical, all genes will fall on the mid-line."
}, {
'file':
"volcanomatrixplot.R",
'title':
"Volcano matrix plots",
'description':
"Volcano matrix plot is a scatter plot that also identifies differentially expressed genes (by color) between samples based on log2 fold change cut off."
}, {
'file':
"pcaplot.R",
'title':
"PCA plot",
'description':
"Principal Component Analysis (PCA) is an informative approach for dimensionality reduction for exploring teh relationship between sample conditions."
}, {
'file':
"pcarepplot.R",
'title':
"PCA plot including replicates",
'description':
"Principal Component Analysis (PCA) is an informative approach for dimensionality reduction for exploring teh relationship between sample conditions including replicates."
}, {
'file':
"mdsplot.R",
'title':
"Multi-dimensional scaling plot",
'description':
"Multi-dimensional scaling plots are similar to PCA plots and useful for determining the major sources of variation in the dataset. "
}, {
'file':
"mdsrepplot.R",
'title':
"Multi-dimensional scaling plot including replicates",
'description':
"Multi-dimensional scaling plot including replicates are similar to PCA plots and useful for determining the major sources of variation in the dataset with replicates. These can be useful to determine any systematic bias that may be present between conditions."
}]
#TODO.. Giving Rplot.pdf
# { 'file': "dendrogramplot.R",
# 'title': "Dendrogram",
# 'description': "Dendrogram based on the JS (Jensen-Shannon divergence) distance" },
#
# { 'file': "dendrogramrepplot.R",
# 'title': "Dendrogram including replicates",
# 'description': "Dendrogram including replicates based on the JS (Jensen-Shannon divergence) distance" },
# Iterate through the plotlist and generate the images and json files.
for plot in plotlist:
status = script_util2.rplotandupload(
self.__LOGGER, self.__SCRATCH, self.__RSCRIPTS, plot['file'],
self.__SHOCK_URL, self.__HS_URL, user_token, cummerbundplotset,
plot['title'], plot['description'], cuffdiff_dir)
if status == False:
self.__LOGGER.info(
"Problem generating image and json file - " + plot["file"])
# Populate the output object
outputobject['cummerbundplotSet'] = cummerbundplotset
#TODO: Need to figure out how to get rnaseq experiment id
outputobject['rnaseq_experiment_id'] = "rnaseq_experiment_id"
outputobject['cuffdiff_input_id'] = params['ws_cuffdiff_id']
res = ws_client.save_objects({
"workspace":
params['workspace_name'],
"objects": [{
"type": "KBaseRNASeq.cummerbund_output",
"data": outputobject,
"name": params["ws_cummerbund_output"]
}]
})
#END generate_cummerbund_plots
# At some point might do deeper type checking...
if not isinstance(returnVal, basestring):
raise ValueError('Method generate_cummerbund_plots return value ' +
'returnVal is not type basestring as required.')
# return the results
return [returnVal]
def generate_cummerbund_plot2(self, ctx, cummerbundstatParams):
"""
:param cummerbundstatParams: instance of type "cummerbundstatParams"
-> structure: parameter "workspace" of String, parameter
"ws_cuffdiff_id" of type "ws_cuffdiff_id" (@id ws
KBaseRNASeq.RNASeqCuffdiffdifferentialExpression), parameter
"ws_cummerbund_output" of type "ws_cummerbund_output" (@id ws
KBaseRNASeq.cummerbund_output), parameter "ws_diffstat_output" of
type "ws_diffstat_output" (Differential stat workspace id)
:returns: instance of type "ws_cummerbund_output" (@id ws
KBaseRNASeq.cummerbund_output)
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN generate_cummerbund_plot2
params = cummerbundstatParams
returnVal = params['ws_cummerbund_output']
#Set up workspace client
user_token = ctx['token']
ws_client = Workspace(url=self.__WS_URL, token=user_token)
#Read the input cuffdiff workspace object json file and get filehandle for cuffdiff tar file
s_res = ws_client.get_objects([{
'name' : params['ws_cuffdiff_id'],
'workspace' : params['workspace']
}])
print "Getting genome info"
genome_ref = s_res[0]['data']['genome_id']
#genome_ref = '2702/6/2'
#genome_ref = '2702/26/1'
#genome_ref = '2229/21/10'
print genome_ref
gaapi = GenomeAnnotationAPI(self.callbackURL, token=user_token)
genome = gaapi.get_genome_v1({"genomes": [{"ref": genome_ref}],
"included_fields": ["scientific_name"],
"included_feature_fields": ["id", "function", "type"
]})["genomes"][0]["data"]
genome_dict = {}
features = genome['features']
for feature in features:
id = feature['id']
try:
function = feature['function']
if not function:
function = 'Unknown'
except:
function = 'Unknown'
genome_dict[id] = function
# Check if workspace has data
if len(s_res) == 0:
self.__LOGGER.info("Workspace did not return any objects")
return returnVal
cuffdiff_dir = script_util2.extract_cuffdiff_data (self.__LOGGER, self.__SHOCK_URL, self.__SCRATCH, s_res, user_token)
self.__LOGGER.info("Cuffdiff folder = " + cuffdiff_dir)
if (cuffdiff_dir is False):
return returnVal
# Run R script to run cummerbund json and update the cummerbund output json file
# Prepare output object.
outputobject=dict()
# Prepare output plot list
cummerbundplotset=[]
# List of plots to generate
plotlist = [
{ 'file': "dispersionplot.R",
'title': "Dispersion plot",
'description': "Dispersion plot is the quality measure of the data. It estimates deviation from threshold against counts in FPKM." },
{ 'file': "fpkmscvplot.R",
'title': "Genes CV plot",
'description': "The squared coefficient of variation plot is a normalized measure of cross-replicate variability that can be useful for evaluating the quality of RNA-seq data." },
{ 'file': "isoformscvplot.R",
'title': "Isoform CV plot",
'description': "The squared coefficient of variation plot is a normalized measure of cross-replicate variability that can be useful for evaluating the quality of RNA-seq data.Differences in CV2 can result in lower numbers of differentially expressed isoforms due to a higher degree of variability between replicate fpkm estimates." },
{ 'file': "densityplot.R",
'title': "Density plot",
'description': "The density plot shows the distribution of FPKM scores across samples" },
{ 'file': "csdensityrepplot.R",
'title': "Replicates density plot",
'description': "The replicates density plot shows the distribution of FPKM scores across sample replicates" },
{ 'file': "boxplot.R",
'title': "Box plots",
'description': "The box plots show the FPKM distribution across samples." },
{ 'file': "boxrepplot.R",
'title': "Box plots of replicates",
'description': "The box plots of replicates show the FPKM distribution across sample replicates." },
{ 'file': "pairwisescatterplots.R",
'title': "Pairwise scatter plots",
'description': "The scatterplots show differences in gene expression between two samples. If two samples are identical, all genes will fall on the mid-line." },
{ 'file': "volcanomatrixplot.R",
'title': "Volcano matrix plots",
'description': "Volcano matrix plot is a scatter plot that also identifies differentially expressed genes (by color) between samples based on log2 fold change cut off." },
{ 'file': "pcaplot.R",
'title': "PCA plot",
'description': "Principal Component Analysis (PCA) is an informative approach for dimensionality reduction for exploring teh relationship between sample conditions." },
{ 'file': "pcarepplot.R",
'title': "PCA plot including replicates",
'description': "Principal Component Analysis (PCA) is an informative approach for dimensionality reduction for exploring teh relationship between sample conditions including replicates." },
{ 'file': "mdsplot.R",
'title': "Multi-dimensional scaling plot",
'description': "Multi-dimensional scaling plots are similar to PCA plots and useful for determining the major sources of variation in the dataset. " },
{ 'file': "mdsrepplot.R",
'title': "Multi-dimensional scaling plot including replicates",
'description': "Multi-dimensional scaling plot including replicates are similar to PCA plots and useful for determining the major sources of variation in the dataset with replicates. These can be useful to determine any systematic bias that may be present between conditions." }
]
# Iterate through the plotlist and generate the images and json files.
for plot in plotlist:
status = script_util2.rplotandupload(self.__LOGGER, self.__SCRATCH, self.__RSCRIPTS,
plot['file'], self.__SHOCK_URL, self.__HS_URL, user_token,
cummerbundplotset, plot['title'], plot['description'], cuffdiff_dir)
if status == False:
self.__LOGGER.info("Problem generating image and json file - " + plot["file"])
# Populate the output object
outputobject['cummerbundplotSet'] = cummerbundplotset
#TODO: Need to figure out how to get rnaseq experiment id
outputobject['rnaseq_experiment_id'] = "rnaseq_experiment_id"
outputobject['cuffdiff_input_id'] = params['ws_cuffdiff_id']
res = ws_client.save_objects({
"workspace":params['workspace'],
"objects": [{
"type":"KBaseRNASeq.cummerbund_output",
"data":outputobject,
"name":params["ws_cummerbund_output"]}]
})
infile = join(cuffdiff_dir, "gene_exp.diff")
outfile = join(cuffdiff_dir, "gene_exp_diff.out")
x=v.volcano_plot_data_parse_and_upload(infile,outfile, genome_dict)
with open(outfile) as f:
statdata = json.load(f)
res = ws_client.save_objects({
"workspace":params['workspace'],
"objects": [{
"type":"KBaseRNASeq.DifferentialExpressionStat",
"data":statdata,
"name":params["ws_diffstat_output"]}]
})
#END generate_cummerbund_plot2
# At some point might do deeper type checking...
if not isinstance(returnVal, basestring):
raise ValueError('Method generate_cummerbund_plot2 return value ' +
'returnVal is not type basestring as required.')
# return the results
return [returnVal]
def generate_cummerbund_plot2(self, ctx, cummerbundstatParams):
"""
:param cummerbundstatParams: instance of type "cummerbundstatParams"
-> structure: parameter "workspace" of String, parameter
"ws_cuffdiff_id" of type "ws_cuffdiff_id" (@id ws
KBaseRNASeq.RNASeqCuffdiffdifferentialExpression), parameter
"ws_cummerbund_output" of type "ws_cummerbund_output" (@id ws
KBaseRNASeq.cummerbund_output), parameter "ws_diffstat_output" of
type "ws_diffstat_output" (Differential stat workspace id)
:returns: instance of type "ws_cummerbund_output" (@id ws
KBaseRNASeq.cummerbund_output)
"""
# ctx is the context object
# return variables are: returnVal
#BEGIN generate_cummerbund_plot2
params = cummerbundstatParams
returnVal = params['ws_cummerbund_output']
# Set up workspace client
user_token = ctx['token']
ws_client = Workspace(url=self.__WS_URL, token=user_token)
# Read the input cuffdiff workspace object json file and get filehandle for cuffdiff tar file
s_res = ws_client.get_objects([{
'name': params['ws_cuffdiff_id'],
'workspace': params['workspace']
}])
print "Getting genome info"
genome_ref = s_res[0]['data']['genome_id']
# genome_ref = '2702/6/2'
# genome_ref = '2702/26/1'
# genome_ref = '2229/21/10'
print genome_ref
gaapi = GenomeAnnotationAPI(self.callbackURL, token=user_token)
genome = gaapi.get_genome_v1({"genomes": [{"ref": genome_ref}],
"included_fields": ["scientific_name"],
"included_feature_fields": ["id", "function", "type"
]})["genomes"][0]["data"]
genome_dict = {}
features = genome['features']
for feature in features:
id = feature['id']
try:
function = feature['function']
if not function:
function = 'Unknown'
except:
function = 'Unknown'
genome_dict[id] = function
# Check if workspace has data
if len(s_res) == 0:
self.__LOGGER.info("Workspace did not return any objects")
return returnVal
cuffdiff_dir = script_util2.extract_cuffdiff_data(self.__LOGGER, self.__SHOCK_URL,
self.__SCRATCH, s_res, user_token)
self.__LOGGER.info("Cuffdiff folder = " + cuffdiff_dir)
if (cuffdiff_dir is False):
return returnVal
# Run R script to run cummerbund json and update the cummerbund output json file
# Prepare output object.
outputobject = dict()
# Prepare output plot list
cummerbundplotset = []
# List of plots to generate
plotlist = [
{'file': "dispersionplot.R",
'title': "Dispersion plot",
'description': "Dispersion plot is the quality measure of the data. It estimates deviation from threshold against counts in FPKM."},
{'file': "fpkmscvplot.R",
'title': "Genes CV plot",
'description': "The squared coefficient of variation plot is a normalized measure of cross-replicate variability that can be useful for evaluating the quality of RNA-seq data."},
{'file': "isoformscvplot.R",
'title': "Isoform CV plot",
'description': "The squared coefficient of variation plot is a normalized measure of cross-replicate variability that can be useful for evaluating the quality of RNA-seq data.Differences in CV2 can result in lower numbers of differentially expressed isoforms due to a higher degree of variability between replicate fpkm estimates."},
{'file': "densityplot.R",
'title': "Density plot",
'description': "The density plot shows the distribution of FPKM scores across samples"},
{'file': "csdensityrepplot.R",
'title': "Replicates density plot",
'description': "The replicates density plot shows the distribution of FPKM scores across sample replicates"},
{'file': "boxplot.R",
'title': "Box plots",
'description': "The box plots show the FPKM distribution across samples."},
{'file': "boxrepplot.R",
'title': "Box plots of replicates",
'description': "The box plots of replicates show the FPKM distribution across sample replicates."},
{'file': "pairwisescatterplots.R",
'title': "Pairwise scatter plots",
'description': "The scatterplots show differences in gene expression between two samples. If two samples are identical, all genes will fall on the mid-line."},
{'file': "volcanomatrixplot.R",
'title': "Volcano matrix plots",
'description': "Volcano matrix plot is a scatter plot that also identifies differentially expressed genes (by color) between samples based on log2 fold change cut off."},
{'file': "pcaplot.R",
'title': "PCA plot",
'description': "Principal Component Analysis (PCA) is an informative approach for dimensionality reduction for exploring teh relationship between sample conditions."},
{'file': "pcarepplot.R",
'title': "PCA plot including replicates",
'description': "Principal Component Analysis (PCA) is an informative approach for dimensionality reduction for exploring teh relationship between sample conditions including replicates."},
{'file': "mdsplot.R",
'title': "Multi-dimensional scaling plot",
'description': "Multi-dimensional scaling plots are similar to PCA plots and useful for determining the major sources of variation in the dataset. "},
{'file': "mdsrepplot.R",
'title': "Multi-dimensional scaling plot including replicates",
'description': "Multi-dimensional scaling plot including replicates are similar to PCA plots and useful for determining the major sources of variation in the dataset with replicates. These can be useful to determine any systematic bias that may be present between conditions."}
]
# Iterate through the plotlist and generate the images and json files.
for plot in plotlist:
status = script_util2.rplotandupload(self.__LOGGER, self.__SCRATCH, self.__RSCRIPTS,
plot['file'], self.__SHOCK_URL, self.__HS_URL,
user_token,
cummerbundplotset, plot['title'],
plot['description'], cuffdiff_dir)
if status == False:
self.__LOGGER.info("Problem generating image and json file - " + plot["file"])
# Populate the output object
outputobject['cummerbundplotSet'] = cummerbundplotset
# TODO: Need to figure out how to get rnaseq experiment id
outputobject['rnaseq_experiment_id'] = "rnaseq_experiment_id"
outputobject['cuffdiff_input_id'] = params['ws_cuffdiff_id']
res = ws_client.save_objects({
"workspace": params['workspace'],
"objects": [{
"type": "KBaseRNASeq.cummerbund_output",
"data": outputobject,
"name": params["ws_cummerbund_output"]}]
})
infile = join(cuffdiff_dir, "gene_exp.diff")
outfile = join(cuffdiff_dir, "gene_exp_diff.out")
x = v.volcano_plot_data_parse_and_upload(infile, outfile, genome_dict)
with open(outfile) as f:
statdata = json.load(f)
res = ws_client.save_objects({
"workspace": params['workspace'],
"objects": [{
"type": "KBaseRNASeq.DifferentialExpressionStat",
"data": statdata,
"name": params["ws_diffstat_output"]}]
})
#END generate_cummerbund_plot2
# At some point might do deeper type checking...
if not isinstance(returnVal, basestring):
raise ValueError('Method generate_cummerbund_plot2 return value ' +
'returnVal is not type basestring as required.')
# return the results
return [returnVal]
