def _plt_distr(dat,
col,
title='',
splitBy_pfill=True,
pfill='label',
independentpdf=False,
fname='xdistr.pdf'):
df = dat[dat[pfill] != 'NA'] ## remove invalid pairs
n = len(df)
df = {
col: robjects.FloatVector(list(df[col])),
pfill: robjects.StrVector(list(df[pfill]))
}
df = robjects.DataFrame(df)
pp = ggplot2.ggplot(df) + \
ggplot2.ggtitle('%s [Total = %s]' % (title, n))
## Plot1: counts
if splitBy_pfill:
p1 = pp + ggplot2.aes_string(x=col, fill=pfill)
else:
p1 = pp + ggplot2.aes_string(x=col)
## Plot2: density
if splitBy_pfill:
p2 = pp + ggplot2.aes_string(x=col, fill=pfill, y='..density..')
else:
p2 = pp + ggplot2.aes_string(x=col, y='..density..')
p2 = p2 + ggplot2.geom_density(alpha=.5, origin=-500)
if col == 'distance':
p1 = p1 + \
ggplot2.geom_histogram(binwidth=1000, alpha=.5, position='identity', origin=-500) + \
ggplot2.xlim(-1000, 51000)
p2 = p2 + \
ggplot2.geom_histogram(binwidth=1000, alpha=.33, position='identity', origin=-500) + \
ggplot2.xlim(-1000, 51000)
else:
p1 = p1 + \
ggplot2.geom_histogram(alpha=.5, position='identity')
p2 = p2 + \
ggplot2.geom_histogram(alpha=.33, position='identity')
if col == 'correlation':
p1 = p1 + ggplot2.xlim(-1.1, 1.1)
p2 = p2 + ggplot2.xlim(-1.1, 1.1)
if independentpdf:
grdevices = importr('grDevices')
grdevices.pdf(file=fname)
p1.plot()
p2.plot()
grdevices.dev_off()
else:
p1.plot()
p2.plot()
return
def plot_hist(sizes, args):
"""
Use rpy2 to plot a histogram of the read sizes
"""
r = robjects.r
r.library("ggplot2")
grdevices = importr('grDevices')
sizes = robjects.IntVector([s for s in sizes \
if s < args.max_length and s > args.min_length])
sizes_min = min(sizes)
sizes_max = max(sizes)
binwidth = (sizes_max - sizes_min) / args.num_bins
d = {'sizes': sizes}
df = robjects.DataFrame(d)
# plot
gp = ggplot2.ggplot(df)
if not args.theme_bw:
pp = gp + ggplot2.aes_string(x='sizes') \
+ ggplot2.geom_histogram(binwidth=binwidth)
else:
pp = gp + ggplot2.aes_string(x='sizes') \
+ ggplot2.geom_histogram(binwidth=binwidth) \
+ ggplot2.theme_bw()
if args.saveas is not None:
plot_file = args.saveas
if plot_file.endswith(".pdf"):
grdevices.pdf(plot_file, width=8.5, height=8.5)
elif plot_file.endswith(".png"):
grdevices.png(plot_file,
width=8.5,
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 histogram(self, dataframe, filename, parm, group, units): with suppress_stdout(): grdevices.png(file=filename, width=512, height=512) data = ggplot2.ggplot(dataframe) aes = ggplot2.aes_string(x=parm,fill = group) geom = ggplot2.geom_histogram(colour="black") labs = ggplot2.labs(x=parm + " " + units) gg = data + aes + geom + labs gg.plot() grdevices.dev_off()
def plot_hist(sizes, args):
"""
Use rpy2 to plot a histogram of the read sizes
"""
r = robjects.r
r.library("ggplot2")
grdevices = importr("grDevices")
sizes = robjects.IntVector([s for s in sizes if s < args.max_length and s > args.min_length])
sizes_min = min(sizes)
sizes_max = max(sizes)
binwidth = (sizes_max - sizes_min) / args.num_bins
d = {"sizes": sizes}
df = robjects.DataFrame(d)
# plot
gp = ggplot2.ggplot(df)
if not args.theme_bw:
pp = gp + ggplot2.aes_string(x="sizes") + ggplot2.geom_histogram(binwidth=binwidth)
else:
pp = gp + ggplot2.aes_string(x="sizes") + ggplot2.geom_histogram(binwidth=binwidth) + ggplot2.theme_bw()
if args.saveas is not None:
plot_file = args.saveas
if plot_file.endswith(".pdf"):
grdevices.pdf(plot_file, width=8.5, height=8.5)
elif plot_file.endswith(".png"):
grdevices.png(plot_file, width=8.5, 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 histogram(self, dataframe, filename, parm, group, units):
with suppress_stdout():
grdevices.png(file=filename, width=512, height=512)
data = ggplot2.ggplot(dataframe)
aes = ggplot2.aes_string(x=parm, fill=group)
geom = ggplot2.geom_histogram(colour="black")
labs = ggplot2.labs(x=parm + " " + units)
gg = data + aes + geom + labs
gg.plot()
grdevices.dev_off()
def rpy2_plotter(anno, clusters, name):
"""Plot genes distribution in clusters using ggplot2 from R."""
pandas2ri.activate()
grdevices = importr('grDevices')
rprint = robjects.globalenv.get("print")
anno = anno.sort_values(by="n_ft", ascending=False)
anno = anno.head(n=10)
category = anno["category"].tolist()
clusters = clusters[clusters["category"].isin(category)]
clusters = pandas2ri.py2ri(clusters)
pp = ggplot2.ggplot(clusters) + ggplot2.aes_string(x="n_features") + ggplot2.geom_histogram(binwidth=1) + ggplot2.facet_wrap(robjects.Formula("~category"), ncol=5) + ggplot2.labs(x="Number of Features", y="Number of Clusters", title="Clusters distribution")
grdevices.pdf(file=name, width=11.692, height=8.267)
rprint(pp)
grdevices.dev_off()
def plot_histogram(fastq_file, plot_filename_png):
"""Plots histogram of length distribution of sequence in fastq_file and
saves to plot_filename_png"""
r = robjects.r
r.library("ggplot2")
grdevices = importr('grDevices')
sizes = []
with open(fastq_file, 'rb') as f:
# skip first line
for _ in itertools.islice(f, 0, 1):
pass
# Get every 4th line with raw sequence letters
fourthlines = itertools.islice(f, 0, None, 4)
for line in fourthlines:
sizes.append(len(line.strip()))
sizes = robjects.IntVector([s for s in sizes])
sizes_min = min(sizes)
sizes_max = max(sizes)
binwidth = (sizes_max - sizes_min) / 20
d = {'sizes' : sizes}
df = robjects.DataFrame(d)
# plot
gp = ggplot2.ggplot(df)
pp = gp + ggplot2.aes_string(x='sizes') \
+ ggplot2.geom_histogram(binwidth=binwidth) \
+ ggplot2.theme_grey() \
+ ggplot2.labs(title =plot_filename_png, \
x = "Size (in nucleotides)", y = "Count")
grdevices.png(plot_filename_png, width = 8.5, height = 8.5,
units = "in", res = 300)
pp.plot()
grdevices.dev_off()
def main():
usage = 'usage: %prog [options] <gtf file> <fpkm tracking>'
parser = OptionParser(usage)
#parser.add_option('-m', dest='fpkm_min', type='float', default=0.25, help='Minimum FPKM [Default: %default]')
(options,args) = parser.parse_args()
if len(args) != 2:
parser.error(usage)
else:
gtf_file = args[0]
fpkm_tracking_file = args[1]
# get genes
genes = set()
for line in open(gtf_file):
a = line.split('\t')
genes.add(gff.gtf_kv(a[8])['gene_id'])
# get expression
cuff = cufflinks.fpkm_tracking(fpkm_tracking_file)
log_fpkms = []
for gene_id in genes:
max_fpkm = max(cuff.gene_expr(gene_id))
if max_fpkm > 0:
log_fpkms.append(math.log(max_fpkm,2))
# construct R data objects
fpkms_r = ro.FloatVector(log_fpkms)
df = ro.DataFrame({'fpkm':fpkms_r})
# construct plot
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='fpkm') + \
ggplot2.geom_histogram(binwidth=0.2)
# save to file
gtf_pre = os.path.splitext(gtf_file)[0]
grdevices.pdf(file='%s_fpkmhist.pdf' % gtf_pre)
gp.plot()
grdevices.dev_off()
def main():
usage = "usage: %prog [options] <gtf file> <fpkm tracking>"
parser = OptionParser(usage)
# parser.add_option('-m', dest='fpkm_min', type='float', default=0.25, help='Minimum FPKM [Default: %default]')
(options, args) = parser.parse_args()
if len(args) != 2:
parser.error(usage)
else:
gtf_file = args[0]
fpkm_tracking_file = args[1]
# get genes
genes = set()
for line in open(gtf_file):
a = line.split("\t")
genes.add(gff.gtf_kv(a[8])["gene_id"])
# get expression
cuff = cufflinks.fpkm_tracking(fpkm_tracking_file)
log_fpkms = []
for gene_id in genes:
max_fpkm = max(cuff.gene_expr(gene_id))
if max_fpkm > 0:
log_fpkms.append(math.log(max_fpkm, 2))
# construct R data objects
fpkms_r = ro.FloatVector(log_fpkms)
df = ro.DataFrame({"fpkm": fpkms_r})
# construct plot
gp = ggplot2.ggplot(df) + ggplot2.aes_string(x="fpkm") + ggplot2.geom_histogram(binwidth=0.2)
# save to file
gtf_pre = os.path.splitext(gtf_file)[0]
grdevices.pdf(file="%s_fpkmhist.pdf" % gtf_pre)
gp.plot()
grdevices.dev_off()
gp = ggplot2.ggplot(mtcars)
pp = gp + \
ggplot2.aes_string(x='factor(cyl)', y='mpg') + \
ggplot2.geom_boxplot()
pp.plot()
#-- ggplot2geomboxplot-end
grdevices.dev_off()
#-- ggplot2geomhistogram-begin
gp = ggplot2.ggplot(mtcars)
pp = gp + \
ggplot2.aes_string(x='wt') + \
ggplot2.geom_histogram()
#pp.plot()
#-- ggplot2geomhistogram-end
grdevices.png('../../_static/graphics_ggplot2geomhistogram.png',
width=900,
height=412,
antialias="subpixel",
type="cairo")
grid.newpage()
grid.viewport(layout=grid.layout(1, 3)).push()
params = (('black', 'black'), ('black', 'white'), ('white', 'black'))
for col_i in range(3):
antialias=ANTIALIAS,
type="cairo")
#-- ggplot2geomboxplot-begin
gp = ggplot2.ggplot(mtcars)
pp = (gp + ggplot2.aes_string(x='factor(cyl)', y='mpg') +
ggplot2.geom_boxplot())
pp.plot()
#-- ggplot2geomboxplot-end
grdevices.dev_off()
#-- ggplot2geomhistogram-begin
gp = ggplot2.ggplot(mtcars)
pp = (gp + ggplot2.aes_string(x='wt') + ggplot2.geom_histogram(bins=30))
#pp.plot()
#-- ggplot2geomhistogram-end
grdevices.png('../../_static/graphics_ggplot2geomhistogram.png',
width=900,
height=412,
antialias=ANTIALIAS,
type="cairo")
grid.newpage()
grid.viewport(layout=grid.layout(1, 3)).push()
params = (('black', 'black'), ('black', 'white'), ('white', 'black'))
for col_i in range(3):
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")
pp = gp + \
ggplot2.aes_string(x='factor(cyl)', y='mpg') + \
ggplot2.geom_boxplot()
pp.plot()
#-- ggplot2geomboxplot-end
grdevices.dev_off()
#-- ggplot2geomhistogram-begin
gp = ggplot2.ggplot(mtcars)
pp = gp + \
ggplot2.aes_string(x='wt') + \
ggplot2.geom_histogram()
#pp.plot()
#-- ggplot2geomhistogram-end
grdevices.png('../../_static/graphics_ggplot2geomhistogram.png',
width = 900, height = 412, antialias="subpixel", type="cairo")
grid.newpage()
grid.viewport(layout=grid.layout(1, 3)).push()
params = (('black', 'black'),
('black', 'white'),
('white', 'black'))
for col_i in range(3):
vp = grid.viewport(**{'layout.pos.col':col_i+1, 'layout.pos.row': 1})
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")
##text_log+="average: "+str(rmean(test23)[0])+end
##text_log+="sum: "+str(rsum(test23)[0])+end
#
#roughbin= round(ma[0]/100)
#bins=round(roughbin/100)*100
#ma2=rmax(ed)
#dataf_subset = dataf.rx(dataf.rx2("contig").ro >= 18, true)
scales = importr('scales')
gp = ggplot2.ggplot(dataf)
#geom_histogram(aes(y = ..density..))
# ggplot2.geom_density()+\
# pp = gp + ggplot2.aes_string(x='%s(contrrr)') + ggplot2.geom_histogram()+ggplot2.scale_y_sqrt()
bins=10
teest3=robjects.r('theme(axis.text.x=element_text(angle=90))')
pp = gp + \
ggplot2.aes_string(x='Length') + \
ggplot2.geom_histogram()+\
ggplot2.ggtitle("Found IS fragment lengths")+ \
ggplot2.scale_x_continuous(name="fragment lengths, bin="+str(bins),breaks=scales.pretty_breaks(20)) +\
ggplot2.scale_y_continuous(labels=scales.comma,name="Count",breaks=scales.pretty_breaks(10))+ \
teest3
pp.plot()
robjects.r.ggsave("/Users/security/science/dna_subj_hist.pdf")
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')
def _plt_percountr(dat, independentpdf=False, fname='xpercount.pdf'):
def _filt_dat(dat, item, getlabel=True):
df = pd.DataFrame(dat[item].value_counts())
df.columns = ['count']
if getlabel:
df['label'] = [
list(dat[dat[item] == i]['label'])[0] for i in df.index
]
n = len(df)
mx = max(df['count'])
return df, n, mx
dat = dat[dat['label'] != 'NA']
## NUMBER OF MIRNA PER TSS
df, n, mx = _filt_dat(dat, 'tss', False)
df = {'count': robjects.IntVector(df['count'])}
df = robjects.DataFrame(df)
pt = ggplot2.ggplot(df) + \
ggplot2.geom_histogram(binwidth=1, origin=-.5, alpha=.5, position="identity") + \
ggplot2.xlim(-.5, mx+1) + \
ggplot2.aes_string(x='count') + \
ggplot2.ggtitle('TSS [Total = %s]' % n) + \
ggplot2.labs(x='Number of miRNA per TSS (max = %s)' % mx)
pt_den = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='count', y='..density..') + \
ggplot2.geom_density(binwidth=1, alpha=.5, origin=-.5) + \
ggplot2.geom_histogram(binwidth=1, alpha=.33, position='identity', origin=-.5) + \
ggplot2.ggtitle('TSS [Total = %s]' % n) + \
ggplot2.labs(x='Number of miRNA per TSS (max = %s)' % mx)
## NUMBER OF TSS PER MIRNA
df, n, mx = _filt_dat(dat, 'mirna')
df = {
'count': robjects.IntVector(df['count']),
'label': robjects.StrVector(df['label'])
}
df = robjects.DataFrame(df)
_pm = ggplot2.ggplot(df) + \
ggplot2.geom_histogram(binwidth=1, origin=-.5, alpha=.5, position="identity") + \
ggplot2.xlim(-.5, mx+1) + \
ggplot2.ggtitle('miRNA [Total = %s]' % n)
_pm_den = ggplot2.ggplot(df) + \
ggplot2.geom_density(binwidth=1, alpha=.5, origin=-.5) + \
ggplot2.geom_histogram(binwidth=1, alpha=.33, position='identity', origin=-.5) + \
ggplot2.ggtitle('miRNA [Total = %s]' % n)
## not split by label
pm = _pm + ggplot2.aes_string(x='count')
pm_den = _pm_den + ggplot2.aes_string(x='count', y='..density..')
## split by label
pms = _pm + ggplot2.aes_string(x='count', fill='label')
pm_dens = _pm_den + ggplot2.aes_string(
x='count', fill='label', y='..density..')
## add xlabelling (need to be added after aes_string)
_xlab = ggplot2.labs(x='Number of TSS per miRNA (max = %s)' % mx)
pm += _xlab
pm_den += _xlab
pms += _xlab
pm_dens += _xlab
if independentpdf:
grdevices = importr('grDevices')
grdevices.pdf(fname)
pt.plot()
pt_den.plot()
pm.plot()
pm_den.plot()
pms.plot()
pm_dens.plot()
grdevices.dev_off()
else:
pt.plot()
pt_den.plot()
pm.plot()
pm_den.plot()
pms.plot()
pm_dens.plot()
return
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')
