def makePlots(truthFile, predFile, method, outBase, measure):
if measure == "tpm":
trueColName = "TPM_truth"
predColName = "TPM_{}".format(method)
elif measure == "num_reads":
trueColName = "NumReads_truth"
predColName = "NumReads_{}".format(method)
# Load the data; first the predicitons
p = None
if method == "salmon":
p = ParsingUtils.readSalmon(predFile, '_{}'.format(method))
elif method == "kallisto":
p = ParsingUtils.readKallisto(predFile, '_{}'.format(method))
elif method == "express":
p = ParsingUtils.readExpress(predFile, '_{}'.format(method))
# Now the ground truth
g = ParsingUtils.readProFile(truthFile, '_truth')
# Convert to TPM
g["TPM_truth"] = 1000000.0 * (g["ExpFrac_truth"] / g["ExpFrac_truth"].sum())
# Flux sim thinks paired-end = 2 reads . . . sigh
g["NumReads_truth"] = g["SeqNum_truth"] * 0.5
# Filter out low TPM
AnalysisUtils.filterValues("TPM_truth", g, 0.01)
AnalysisUtils.filterValues("TPM_{}".format(method), p, 0.01)
AnalysisUtils.filterValues("NumReads_truth", g, 1.0)
AnalysisUtils.filterValues("NumReads_{}".format(method), p, 1.0)
# merge dataframes
m = g.join(p)
setPlotProperties()
makeCorrPlot(trueColName, predColName, m, outBase, method, measure)
makeRelDiffPlot(trueColName, predColName, m, outBase, method, measure)
makeRelErrorPlot(trueColName, predColName, m, outBase, method, measure)
def makeTable(methodDict, outpath, outfile, measure, annotPath):
import pandas as pd
import seaborn as sns
import ParsingUtils
import AnalysisUtils
dframes = []
for k, v in methodDict.items():
if k.upper().startswith('SALMON'):
d = ParsingUtils.readSalmon(v, '_{}'.format(k))
elif k.upper().startswith('KALLISTO'):
d = ParsingUtils.readKallisto(v, '_{}'.format(k))
elif k.upper().startswith('EXPRESS'):
d = ParsingUtils.readExpress(v, '_{}'.format(k))
elif k.upper() == 'SAILFISH':
d = ParsingUtils.readSailfish(v, '_{}'.format(k))
elif k.upper() == 'SAILFISH (QUASI)':
d = ParsingUtils.readSalmon(v, '_{}'.format(k))
elif k.upper().startswith('TRUTH'):
suffix = '_{}'.format(k)
d = ParsingUtils.readProFile(v, suffix)
d["TPM{}".format(suffix)] = 1000000.0 * (d["ExpFrac{}".format(suffix)] / d["ExpFrac{}".format(suffix)].sum())
# Flux sim thinks paired-end = 2 reads . . . sinh
d["NumReads{}".format(suffix)] = d["SeqNum{}".format(suffix)] * 0.5
# Add this dataframe to the list
dframes.append(d)
M = dframes[0].join(dframes[1:])
# Filter eXpress results
minVal = np.inf
for mn in set(methodDict.keys()) - set(["Truth", "eXpress"]):
newMin = M.loc[M["{}_{}".format(measure, mn)]>0, "{}_{}".format(measure,mn)].min()
minVal = min(minVal, newMin)
print("filtering eXpress results < {} {}".format(minVal, measure))
AnalysisUtils.filterValues("{}_{}".format(measure, "eXpress"), M, minVal)
org = outfile.split('/')[-1].split('_')[0]
print("org = {}".format(org))
if org == 'human':
plotStratifiedDiffs(M, methodDict, annotPath, outpath, measure)
mrdName = 'abs. mean rel. diff.'
corrName = 'Spearman corr.'
propName = 'Proportionality corr.'
tpefName = 'TP error fraction'
tpMedErrorName = 'TP median per. error'
res = pd.DataFrame(data={ m : {tpMedErrorName : np.nan, tpefName : np.nan, mrdName : np.nan, corrName : np.nan, propName : np.nan} for m in (methodDict.keys() - set('Truth'))})
import scipy as sp
import scipy.stats
for k in methodDict:
if k.upper() != "TRUTH":
c = sp.stats.spearmanr(M["{}_Truth".format(measure)], M["{}_{}".format(measure, k)])[0]
res[k][corrName] = c
mrd, _ = AnalysisUtils.relDiff("{}_Truth".format(measure), "{}_{}".format(measure, k), M)
res[k][mrdName] = mrd["relDiff"].abs().mean()
pc = AnalysisUtils.proportionalityCorrelation("{}_Truth".format(measure), "{}_{}".format(measure, k), M)
res[k][propName] = pc
tpind = M[M["{}_Truth".format(measure)] >= 1]
y = tpind["{}_{}".format(measure, k)]
x = tpind["{}_Truth".format(measure)]
ef = 10.0
re = (y - x) / x
are = 100.0 * (y - x).abs() / x
tpef = len(are[are > ef]) / float(len(are))
res[k][tpefName] = tpef
res[k][tpMedErrorName] = re.median()
res.drop('Truth', axis=1, inplace=True)
print(res)
res.to_csv(outfile+".csv")
with open(outfile, 'w') as ofile:
ofile.write(res.to_latex(float_format=lambda x: "{0:.2f}".format(x)))
print("wrote {}".format(outpath))
