def plot_total_bp(parser, args, tot_bp_per_pore):
"""
Plot the pore performance
"""
import math
r = robjects.r
r.library("ggplot2")
grdevices = importr("grDevices")
flowcell_layout = minion_flowcell_layout()
pore_values = []
for pore in flowcell_layout:
if pore in tot_bp_per_pore:
pore_values.append(math.log10(tot_bp_per_pore[pore]))
else:
pore_values.append(0)
# make a data frame of the lists
d = {
"rownum": robjects.IntVector(range(1, 17) * 32),
"colnum": robjects.IntVector(sorted(range(1, 33) * 16)),
"log10_tot_bp": robjects.IntVector(pore_values),
"labels": robjects.IntVector(flowcell_layout),
}
df = robjects.DataFrame(d)
gp = gg.ggplot(df)
pp = (
gp
+ gg.aes_string(y="factor(rownum, rev(rownum))", x="factor(colnum)")
+ gg.geom_point(gg.aes_string(color="log10_tot_bp"), size=7)
+ gg.geom_text(gg.aes_string(label="labels"), colour="white", size=2)
+ gg.scale_colour_gradient2(low="black", mid="black", high="red")
+ gg.coord_fixed(ratio=1.4)
+ gg.labs(x=gg.NULL, y=gg.NULL)
)
if args.saveas is not None:
plot_file = args.saveas
if plot_file.endswith(".pdf"):
grdevices.pdf(plot_file, width=11, height=8.5)
elif plot_file.endswith(".png"):
grdevices.png(plot_file, width=11, height=8.5, units="in", res=300)
else:
logger.error("Unrecognized extension for %s!" % (plot_file))
sys.exit()
pp.plot()
grdevices.dev_off()
else:
pp.plot()
# keep the plot open until user hits enter
print ("Type enter to exit.")
raw_input()
def plot_total_bp(parser, args, tot_bp_per_pore):
"""
Plot the pore performance
"""
import math
r = robjects.r
r.library("ggplot2")
grdevices = importr('grDevices')
flowcell_layout = minion_flowcell_layout()
pore_values = []
for pore in flowcell_layout:
if pore in tot_bp_per_pore:
pore_values.append(math.log10(tot_bp_per_pore[pore]))
else:
pore_values.append(0)
# make a data frame of the lists
d = {'rownum': robjects.IntVector(range(1,17)*32),
'colnum': robjects.IntVector(sorted(range(1,33)*16)),
'log10_tot_bp': robjects.IntVector(pore_values),
'labels': robjects.IntVector(flowcell_layout)
}
df = robjects.DataFrame(d)
gp = gg.ggplot(df)
pp = gp + gg.aes_string(y = 'factor(rownum, rev(rownum))', \
x = 'factor(colnum)') \
+ gg.geom_point(gg.aes_string(color='log10_tot_bp'), size = 7) \
+ gg.geom_text(gg.aes_string(label ='labels'), colour="white", size = 2) \
+ gg.scale_colour_gradient2(low = "black", mid= "black", high="red") \
+ gg.coord_fixed(ratio=1.4) \
+ gg.labs(x=gg.NULL, y=gg.NULL)
if args.saveas is not None:
plot_file = args.saveas
if plot_file.endswith(".pdf"):
grdevices.pdf(plot_file, width = 11, height = 8.5)
elif plot_file.endswith(".png"):
grdevices.png(plot_file, width = 11, height = 8.5,
units = "in", res = 300)
else:
logger.error("Unrecognized extension for %s!" % (plot_file))
sys.exit()
pp.plot()
grdevices.dev_off()
else:
pp.plot()
# keep the plot open until user hits enter
print('Type enter to exit.')
raw_input()
def plot_similarity_matrix(self, item_type, image_file, title):
'''Plot similarities of crawls (overlap of unique items)
as heat map matrix'''
data = defaultdict(dict)
n = 1
for crawl1 in self.similarity[item_type]:
for crawl2 in self.similarity[item_type][crawl1]:
similarity = self.similarity[item_type][crawl1][crawl2]
data['crawl1'][n] = MonthlyCrawl.short_name(crawl1)
data['crawl2'][n] = MonthlyCrawl.short_name(crawl2)
data['similarity'][n] = similarity
data['sim_rounded'][n] = similarity # to be rounded
n += 1
data = pandas.DataFrame(data)
print(data)
# select median of similarity values as midpoint of similarity scale
midpoint = data['similarity'].median()
decimals = 3
textsize = 2
minshown = .0005
if (data['similarity'].max()-data['similarity'].min()) > .2:
decimals = 2
textsize = 2.8
minshown = .005
data['sim_rounded'] = data['sim_rounded'].apply(
lambda x: ('{0:.'+str(decimals)+'f}').format(x).lstrip('0')
if x >= minshown else '0')
print('Median of similarities for', item_type, '=', midpoint)
matrix_size = len(self.similarity[item_type])
if matrix_size > self.MAX_MATRIX_SIZE:
n = 0
for crawl1 in sorted(self.similarity[item_type], reverse=True):
short_name = MonthlyCrawl.short_name(crawl1)
if n > self.MAX_MATRIX_SIZE:
data = data[data['crawl1'] != short_name]
data = data[data['crawl2'] != short_name]
n += 1
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x='crawl2', y='crawl1',
fill='similarity', label='sim_rounded') \
+ ggplot2.geom_tile(color="white") \
+ ggplot2.scale_fill_gradient2(low="red", high="blue", mid="white",
midpoint=midpoint, space="Lab") \
+ GGPLOT2_THEME \
+ ggplot2.coord_fixed() \
+ ggplot2.theme(**{'axis.text.x':
ggplot2.element_text(angle=45,
vjust=1, hjust=1)}) \
+ ggplot2.labs(title=title, x='', y='') \
+ ggplot2.geom_text(color='black', size=textsize)
img_path = os.path.join(PLOTDIR, image_file)
p.save(img_path)
return p
def main():
'''
maine
'''
# Command Line Stuff...
myCommandLine = CommandLine()
outdir = myCommandLine.args['outDir']
group1 = myCommandLine.args['group1']
group2 = myCommandLine.args['group2']
batch = myCommandLine.args['batch']
matrix = myCommandLine.args['matrix']
prefix = myCommandLine.args['prefix']
formula = myCommandLine.args['formula']
print("running DESEQ2 %s" % prefix, file=sys.stderr)
# make the quant DF
quantDF = pd.read_table(matrix, header=0, sep='\t', index_col=0)
df = pandas2ri.py2ri(quantDF)
# import formula
formulaDF = pd.read_csv(formula,header=0, sep="\t",index_col=0)
sampleTable = pandas2ri.py2ri(formulaDF)
if "batch" in list(formulaDF):
design = Formula("~ batch + condition")
else:
design = Formula("~ condition")
# import DESeq2
from rpy2.robjects.packages import importr
import rpy2.robjects.lib.ggplot2 as ggplot2
methods = importr('methods')
deseq = importr('DESeq2')
grdevices = importr('grDevices')
qqman = importr('qqman')
### RUN DESEQ2 ###
R.assign('df', df)
R.assign('sampleTable', sampleTable)
R.assign('design',design)
R('dds <- DESeqDataSetFromMatrix(countData = df, colData = sampleTable, design = design)')
R('dds <- DESeq(dds)')
R('name <- grep("condition", resultsNames(dds), value=TRUE)')
###
###
# Get Results and shrinkage values
res = R('results(dds, name=name)')
resLFC = R('lfcShrink(dds, coef=name)')
vsd = R('vst(dds,blind=FALSE)')
resdf = robjects.r['as.data.frame'](res)
reslfc = robjects.r['as.data.frame'](resLFC)
dds = R('dds')
### Plotting section ###
# plot MA and PC stats for the user
plotMA = robjects.r['plotMA']
plotDisp = robjects.r['plotDispEsts']
plotPCA = robjects.r['plotPCA']
plotQQ = robjects.r['qq']
# get pca data
if "batch" in list(formulaDF):
pcaData = plotPCA(vsd, intgroup=robjects.StrVector(("condition", "batch")), returnData=robjects.r['T'])
percentVar = robjects.r['attr'](pcaData, "percentVar")
else:
print(vsd)
pcaData = plotPCA(vsd, intgroup="condition", returnData=robjects.r['T'])
percentVar = robjects.r['attr'](pcaData, "percentVar")
# arrange
data_folder = os.path.join(os.getcwd(), outdir)
qcOut = os.path.join(data_folder, "%s_QCplots_%s_v_%s.pdf" % (prefix,group1,group2))
grdevices.pdf(file=qcOut)
x = "PC1: %s" % int(percentVar[0]*100) + "%% variance"
y = "PC2: %s" % int(percentVar[1]*100) + "%% variance"
if "batch" in list(formulaDF):
pp = ggplot2.ggplot(pcaData) + \
ggplot2.aes_string(x="PC1", y="PC2", color="condition", shape="batch") + \
ggplot2.geom_point(size=3) + \
robjects.r['xlab'](x) + \
robjects.r['ylab'](y) + \
ggplot2.theme_classic() + \
ggplot2.coord_fixed()
else:
pp = ggplot2.ggplot(pcaData) + \
ggplot2.aes_string(x="PC1", y="PC2", color="condition") + \
ggplot2.geom_point(size=3) + \
robjects.r['xlab'](x) + \
robjects.r['ylab'](y) + \
ggplot2.theme_classic() + \
ggplot2.coord_fixed()
pp.plot()
plotMA(res, ylim=robjects.IntVector((-3,3)), main="MA-plot results")
plotMA(resLFC, ylim=robjects.IntVector((-3,3)), main="MA-plot LFCSrhinkage")
plotQQ(reslfc.rx2('pvalue'), main="LFCSrhinkage pvalue QQ")
hh = ggplot2.ggplot(resdf) + \
ggplot2.aes_string(x="pvalue") + \
ggplot2.geom_histogram() + \
ggplot2.theme_classic() + \
ggplot2.ggtitle("pvalue distribution")
hh.plot()
plotDisp(dds, main="Dispersion Estimates")
grdevices.dev_off()
data_folder = os.path.join(os.getcwd(), outdir)
lfcOut = os.path.join(data_folder, "%s_%s_v_%s_deseq2_results_shrinkage.tsv" % (prefix,group1,group2))
resOut = os.path.join(data_folder, "%s_%s_v_%s_deseq2_results.tsv" % (prefix,group1,group2))
robjects.r['write.table'](reslfc, file=lfcOut, quote=False, sep="\t")
robjects.r['write.table'](resdf, file=resOut, quote=False, sep="\t")
def main():
'''
maine
'''
# Command Line Stuff...
myCommandLine = CommandLine()
outdir = myCommandLine.args['outDir']
group1 = myCommandLine.args['group1']
group2 = myCommandLine.args['group2']
batch = myCommandLine.args['batch']
matrix = myCommandLine.args['matrix']
prefix = myCommandLine.args['prefix']
formula = myCommandLine.args['formula']
# make the quant DF
quantDF = pd.read_table(matrix, header=0, sep='\t', index_col=0)
df = pandas2ri.py2ri(quantDF)
#print(df.head())
# import formula
formulaDF = pd.read_csv(formula,header=0, sep="\t",index_col=0)
sampleTable = pandas2ri.py2ri(formulaDF)
if "batch" in list(formulaDF):
design = Formula("~ batch + condition")
else:
design = Formula("~ condition")
#print(sampleTable)
# import DESeq2
from rpy2.robjects.packages import importr
import rpy2.robjects.lib.ggplot2 as ggplot2
methods = importr('methods')
deseq = importr('DESeq2')
grdevices = importr('grDevices')
qqman = importr('qqman')
dds = deseq.DESeqDataSetFromMatrix(countData = df,
colData = sampleTable,
design = design)
dds = deseq.DESeq(dds)
cont = robjects.r["grep"]("condition",robjects.r['resultsNames'](dds),value=True)
#print(cont)
# get results; orient the results for groupA vs B
res = deseq.results(dds, name=cont)
# results with shrinkage
resLFC = deseq.lfcShrink(dds, coef=cont, type="apeglm")
resdf = robjects.r['as.data.frame'](res)
R.assign('res', res)
reslfc = robjects.r['as.data.frame'](resLFC)
# plot MA and PC stats for the user
plotMA = robjects.r['plotMA']
plotDisp = robjects.r['plotDispEsts']
plotPCA = robjects.r['plotPCA']
plotQQ = robjects.r['qq']
vsd = robjects.r['vst'](dds, blind=robjects.r['F'])
# get pca data
if "batch" in list(formulaDF):
pcaData = plotPCA(vsd, intgroup=robjects.StrVector(("condition", "batch")), returnData=robjects.r['T'])
percentVar = robjects.r['attr'](pcaData, "percentVar")
else:
print(vsd)
pcaData = plotPCA(vsd, intgroup="condition", returnData=robjects.r['T'])
percentVar = robjects.r['attr'](pcaData, "percentVar")
# arrange
grdevices.pdf(file="./%s/%s_QCplots_%s_v_%s.pdf" % (outdir,prefix,group1,group2))
x = "PC1: %s" % int(percentVar[0]*100) + "%% variance"
y = "PC2: %s" % int(percentVar[1]*100) + "%% variance"
if "batch" in list(formulaDF):
pp = ggplot2.ggplot(pcaData) + \
ggplot2.aes_string(x="PC1", y="PC2", color="condition", shape="batch") + \
ggplot2.geom_point(size=3) + \
robjects.r['xlab'](x) + \
robjects.r['ylab'](y) + \
ggplot2.theme_classic() + \
ggplot2.coord_fixed()
pp.plot()
else:
pp = ggplot2.ggplot(pcaData) + \
ggplot2.aes_string(x="PC1", y="PC2", color="condition") + \
ggplot2.geom_point(size=3) + \
robjects.r['xlab'](x) + \
robjects.r['ylab'](y) + \
ggplot2.theme_classic() + \
ggplot2.coord_fixed()
pp.plot()
plotMA(res, ylim=robjects.IntVector((-3,3)), main="MA-plot results")
#plotMA(res, main="MA-plot results")
plotMA(resLFC, ylim=robjects.IntVector((-3,3)), main="MA-plot LFCSrrhinkage")
#plotMA(resLFC, main="MA-plot LFCSrrhinkage")
plotQQ(resdf.rx2('pvalue'), main="pvalue QQ")
plotQQ(reslfc.rx2('pvalue'), main="LFCSrhinkage pvalue QQ")
hh = ggplot2.ggplot(resdf) + \
ggplot2.aes_string(x="pvalue") + \
ggplot2.geom_histogram() + \
ggplot2.theme_classic()
hh.plot()
plotDisp(dds, main="Dispersion Estimates")
grdevices.dev_off()
lfcOut = "./%s/%s_%s_v_%s_deseq2_results_shrinkage.tsv" % (outdir,prefix,group1,group2)
resOut = "./%s/%s_%s_v_%s_deseq2_results.tsv" % (outdir,prefix,group1,group2)
robjects.r['write.table'](reslfc, file=lfcOut, quote=False, sep="\t")
robjects.r['write.table'](resdf, file=resOut, quote=False, sep="\t")
def main():
'''
maine
'''
# Command Line Stuff...
myCommandLine = CommandLine()
outdir = "diffExpOut"
group1 = myCommandLine.args['group1']
group2 = myCommandLine.args['group2']
batch = myCommandLine.args['batch']
matrix = myCommandLine.args['matrix']
prefix = "flair_diffexp"
# make the quant DF
quantDF = pd.read_table(matrix, header=0, sep='\t')
quantDF = quantDF.set_index('ids')
df = pandas2ri.py2ri(quantDF)
# now make the formula
with open(matrix) as l:
header = next(l).rstrip().split()[1:]
formula = [[x, x.split("_")[1], x.split("_")[-1]] for x in header]
formulaDF = pd.DataFrame(formula)
formulaDF.columns = ['sampleName', 'condition', 'batch']
formulaDF = formulaDF.set_index('sampleName')
sampleTable = pandas2ri.py2ri(formulaDF)
design = Formula("~ batch + condition")
print(sampleTable)
# import DESeq2
from rpy2.robjects.packages import importr
import rpy2.robjects.lib.ggplot2 as ggplot2
methods = importr('methods')
deseq = importr('DESeq2')
grdevices = importr('grDevices')
qqman = importr('qqman')
dds = deseq.DESeqDataSetFromMatrix(countData=df,
colData=sampleTable,
design=design)
dds = deseq.DESeq(dds)
cont = robjects.r["grep"]("condition",
robjects.r['resultsNames'](dds),
value="TRUE")
# get results; orient the results for groupA vs B
res = deseq.results(dds, name=cont)
# results with shrinkage
resLFC = deseq.lfcShrink(dds, coef=cont, type="apeglm")
resdf = robjects.r['as.data.frame'](res)
R.assign('res', res)
R('write.table(res, file="testres.tsv", quote=FALSE, col.names=NA)')
reslfc = robjects.r['as.data.frame'](resLFC)
# plot MA and PC stats for the user
plotMA = robjects.r['plotMA']
plotDisp = robjects.r['plotDispEsts']
plotPCA = robjects.r['plotPCA']
plotQQ = robjects.r['qq']
vsd = robjects.r['vst'](dds, blind=robjects.r['F'])
# get pca data
pcaData = plotPCA(vsd,
intgroup=robjects.StrVector(("condition", "batch")),
returnData=robjects.r['T'])
percentVar = robjects.r['attr'](pcaData, "percentVar")
# arrange
grdevices.pdf(file="./%s/%s_%s_vs_%s_%s_cutoff_plots.pdf" %
(outdir, prefix, group1, group2, str(batch)))
x = "PC1: %s" % int(percentVar[0] * 100) + "%% variance"
y = "PC2: %s" % int(percentVar[1] * 100) + "%% variance"
pp = ggplot2.ggplot(pcaData) + \
ggplot2.aes_string(x="PC1", y="PC2", color="condition", shape="batch") + \
ggplot2.geom_point(size=3) + \
robjects.r['xlab'](x) + \
robjects.r['ylab'](y) + \
ggplot2.theme_classic() + \
ggplot2.coord_fixed()
pp.plot()
plotMA(res, ylim=robjects.IntVector((-3, 3)), main="MA-plot results")
#plotMA(res, main="MA-plot results")
plotMA(resLFC,
ylim=robjects.IntVector((-3, 3)),
main="MA-plot LFCSrrhinkage")
#plotMA(resLFC, main="MA-plot LFCSrrhinkage")
plotQQ(resdf.rx2('pvalue'), main="pvalue QQ")
plotQQ(reslfc.rx2('pvalue'), main="LFCSrhinkage pvalue QQ")
hh = ggplot2.ggplot(resdf) + \
ggplot2.aes_string(x="pvalue") + \
ggplot2.geom_histogram() + \
ggplot2.theme_classic()
hh.plot()
plotDisp(dds, main="Dispersion Estimates")
grdevices.dev_off()
lfcOut = "./%s/%s_%s_deseq2_results_LFC.tsv" % (outdir, prefix, str(batch))
resOut = "./%s/%s_%s_deseq2_results.tsv" % (outdir, prefix, str(batch))
robjects.r['write.table'](reslfc, file=lfcOut, quote=False, sep="\t")
robjects.r['write.table'](resdf, file=resOut, quote=False, sep="\t")
sys.exit(1)
reslsf = pandas2ri.ri2py(reslfc)
res = pandas2ri.ri2py(resdf)
reslsf.to_csv("./%s/%s_%s_deseq2_results_LFC.tsv" %
(outdir, prefix, str(batch)),
sep='\t')
res.to_csv("./%s/%s_%s_deseq2_results.tsv" % (outdir, prefix, str(batch)),
sep='\t')
def main():
'''
maine
'''
# Command Line Stuff...
myCommandLine = CommandLine()
workingdir = myCommandLine.args['workingdir']
outdir = myCommandLine.args['outdir']
group1 = myCommandLine.args['group1']
group2 = myCommandLine.args['group2']
batch = myCommandLine.args['batch']
files = myCommandLine.args['files']
prefix = myCommandLine.args['out_prefix']
sFilter = myCommandLine.args['filter']
makeDir(outdir)
files = checkSamples(files)
df = filesToDF(files, sFilter)
# DO DESEQ2
from rpy2 import robjects
from rpy2.robjects import r, pandas2ri, Formula
from rpy2.robjects.lib import grid
pandas2ri.activate()
# Compile data for data frame
data = list()
for f in files:
if group1 in f:
if batch in f:
data.append((f, group1, '1'))
else:
data.append((f, group1, '2'))
else:
if batch in f:
data.append((f, group2, '1'))
else:
data.append((f, group2, '2'))
# Make the Data Frame
pydf = pd.DataFrame(data)
pydf.columns = ['sampleName', 'condition', 'batch']
pydf = pydf.set_index('sampleName')
# Convert pandas to R data frame.
sampleTable = pandas2ri.py2ri(pydf)
# DESEQ2 part.
# Forumla
design = Formula("~ batch + condition")
# import DESeq2
from rpy2.robjects.packages import importr
import rpy2.robjects.lib.ggplot2 as ggplot2
methods = importr('methods')
deseq = importr('DESeq2')
grdevices = importr('grDevices')
qqman = importr('qqman')
# dds = deseq.DESeqDataSetFromHTSeqCount(sampleTable = sampleTable,
# directory = workingdir,
# design= design)
dds = deseq.DESeqDataSetFromMatrix(countData=df,
colData=sampleTable,
design=design)
dds = deseq.DESeq(dds)
# get results; orient the results for groupA vs B
res = deseq.results(dds,
contrast=robjects.StrVector(
("condition", group2, group1)))
# results with shrinkage
resLFC = deseq.lfcShrink(dds,
coef="condition_%s_vs_%s" % (group2, group1),
type="apeglm")
resdf = robjects.r['as.data.frame'](res)
reslfc = robjects.r['as.data.frame'](resLFC)
# plot MA and PC stats for the user
plotMA = robjects.r['plotMA']
plotDisp = robjects.r['plotDispEsts']
plotPCA = robjects.r['plotPCA']
plotQQ = robjects.r['qq']
vsd = robjects.r['vst'](dds, blind=robjects.r['F'])
# get pca data
pcaData = plotPCA(vsd,
intgroup=robjects.StrVector(("condition", "batch")),
returnData=robjects.r['T'])
percentVar = robjects.r['attr'](pcaData, "percentVar")
# arrange
grdevices.pdf(file="./%s/%s_%s_vs_%s_%s_%s_cutoff_plots.pdf" %
(outdir, prefix, group1, group2, str(batch), sFilter))
x = "PC1: %s" % int(percentVar[0] * 100) + "%% variance"
y = "PC2: %s" % int(percentVar[1] * 100) + "%% variance"
pp = ggplot2.ggplot(pcaData) + \
ggplot2.aes_string(x="PC1", y="PC2", color="condition", shape="batch") + \
ggplot2.geom_point(size=3) + \
robjects.r['xlab'](x) + \
robjects.r['ylab'](y) + \
ggplot2.theme_classic() + \
ggplot2.coord_fixed()
pp.plot()
plotMA(res, ylim=robjects.IntVector((-3, 3)), main="MA-plot results")
#plotMA(res, main="MA-plot results")
plotMA(resLFC,
ylim=robjects.IntVector((-3, 3)),
main="MA-plot LFCSrrhinkage")
#plotMA(resLFC, main="MA-plot LFCSrrhinkage")
plotQQ(resdf.rx2('pvalue'), main="pvalue QQ")
plotQQ(reslfc.rx2('pvalue'), main="LFCSrhinkage pvalue QQ")
hh = ggplot2.ggplot(resdf) + \
ggplot2.aes_string(x="pvalue") + \
ggplot2.geom_histogram() + \
ggplot2.theme_classic()
hh.plot()
plotDisp(dds, main="Dispersion Estimates")
grdevices.dev_off()
reslsf = pandas2ri.ri2py(reslfc)
res = pandas2ri.ri2py(resdf)
reslsf.to_csv("./%s/%s_%s_vs_%s_%s_deseq2_results_LFC.tsv" %
(outdir, prefix, group1, group2, str(batch)),
sep='\t')
reslsf.to_csv("./%s/%s_%s_vs_%s_%s_deseq2_results.tsv" %
(outdir, prefix, group1, group2, str(batch)),
sep='\t')