def plot_sctr(df, col1, col2, path, title, xlab, ylab, coop_x, coop_y):
plt.clf()
ax = plt.axes()
df['label_x'] = df['label_x'].replace({'cooperative': coop_x})
coop_df = df[df["label_y"] == "cooperative"]
arr.plot_classified_labels(df,
col1=col1,
col2=col2,
labelcol="label_x",
title=title,
xlab=xlab,
ylab=ylab,
labelnames=[coop_x, "independent", "anticoop"],
axes=ax)
x, y = np.log(coop_df[col1].values), np.log(coop_df[col2].values)
ax.scatter(x, y, color="blue", s=1, label=coop_y)
ax.legend(loc="lower right")
plt.savefig(path)
def plot_coop(df, namemap, lo1, lo2, lb, suffix):
dfnm = get_selected_nm(df, namemap)
oris = {"o1": lo1, "o2": lo2, "both": lb}
# lbnm = lb[lb["label"] != "fail_cutoff"][["Name"]].drop_duplicates()
for o in ["o1", "o2", "both"]:
ax = plt.axes()
arr.plot_classified_labels(oris[o],
col1="indiv_median",
col2="two_median",
log=True,
xlab="log(m1-m3+m2-m3)",
ylab="log(wt-m3)",
path="labeled_log_%s.png" % o,
title="Cooperative plot, %s" % o,
axes=ax)
wtavail = oris[o].merge(dfnm[["Name"]])
ax.scatter(np.log(wtavail["indiv_median"]),
np.log(wtavail["two_median"]),
color="cyan",
s=1,
label="wt_selected")
plt.savefig("in_ori_%s_%s.png" % (o, suffix))
plt.clf()
# pickle.dump( two, open( "twosites.p", "wb" ) )
# # indiv = pickle.load( open( "indivsum.p", "rb" ) )
# # two = pickle.load( open( "twosites.p", "rb" ) )
lbled = arr.label_replicas_permutation(indiv, two, arr_df, cutoff=cutoff, pcut=0.01, fdrcor=True)
arr_df["affinity"] = np.log(arr_df["affinity"])
# arr.plot_multi_scatterbox("alltypes.pdf", arr_df, ["wt","m1","m2","m3"], namecol="Name", affcol="affinity", pline=False, allplot=False, fixed_ax=True)
# arr.plot_ori_inconsistency(indiv_df, two_df, log=True, fixed_ax=True)
# import sys
# sys.exit()
for ori in lbled:
lbled[ori].to_csv("lbled_%s.csv"%ori,index=False)
#lbled[ori]["label"] = lbled[ori]["label"].replace({'additive': 'independent',"anticoop":"anticooperative"})
arr.plot_classified_labels(lbled[ori], col1="indiv_median", col2="two_median", log=True, plotnonsignif=False,
xlab="M1-M3+M2-M3", ylab="WT-M3", path="labeled_log_%s.png" % ori, title="Cooperative vs independent binding of Ets1-Ets1",
labelnames=["cooperative","independent","anticooperative"]) #"Cooperative plot, %s" % ori)
print("Count %s" % ori,lbled[ori]["label"].value_counts())
lbled_both = lbled["o1"][["Name", "label", "indiv_median", "two_median"]].merge(lbled["o2"][["Name", "label", "indiv_median", 'two_median']], on="Name", suffixes=("_o1", "_o2"))
lbled_both["indiv_median"] = (lbled_both["indiv_median_o1"] + lbled_both["indiv_median_o2"]) / 2
lbled_both["two_median"] = (lbled_both["two_median_o1"] + lbled_both["two_median_o2"]) / 2
lbled_both["label"] = lbled_both.apply(lambda x: assign_label(x["label_o1"], x["label_o2"]), axis=1)
print(lbled_both)
lbled_both.to_csv("lbled_both.csv", index=False)
print("Count both ", lbled_both["label"].value_counts())
lbled_both["label"] = lbled_both["label"].replace({'additive': 'independent',"anticoop":"anticooperative"})
arr.plot_classified_labels(lbled_both, col1="indiv_median", col2="two_median", log=True, plotnonsignif=False,
xlab="M1-M3+M2-M3", ylab="WT-M3", path="labeled_log_both.png", title="Cooperative vs independent binding of Ets1-Ets1",
labelnames=["cooperative","independent","anticooperative"])
# too low statistical power, can't do fdr correction
# lbled["p_coop"] = sm.fdrcorrection(lbled["p_coop"])[1]
# lbled["p_anti"] = sm.fdrcorrection(lbled["p_anti"])[1]
#print(lbled.groupby("p_coop").count())
lbled["label"] = lbled.apply(
lambda x: "cooperative" if x["p_coop"] < p_default else "ambiguous"
if x["p_coop"] < p_ambiguous else "anticoop"
if x["p_anti"] < p_default else "additive",
axis=1)
df_lbled = median_df.merge(lbled, on="Name")
below_cut["label"] = "below_cutoff"
df_lbled = df_lbled.append(below_cut, ignore_index=True)
olist.append(df_lbled)
arr.plot_classified_labels(df_lbled,
path="%s_normalized.png" % ori,
title="Cooperative plot, orientation %s" %
ori,
xlab=ch_x,
ylab=ch_y)
# write the labeled probes to csv
df_wori = df_genomics[0][df_genomics[0]["ori"] == ori][[
"Name", "Sequence", "ets_pos", "runx_pos", "ori"
]].drop_duplicates()
#signif_label = df_lbled.loc[df_lbled["label"] != "below_cutoff",["Name","label","p_coop"]].drop_duplicates()
lbled = df_lbled[["Name", "label", "p_coop"]].drop_duplicates()
df_comb \
.rename(columns={"Alexa488Adjusted_x":"ch1", "Alexa488Adjusted_y": "ch2"}) \
.merge(lbled, on=["Name"]) \
.merge(df_wori, on=["Name"]) \
.to_csv("probes_labeled_%s.csv" % ori, index=False, float_format='%.4f')
both_ori = olist[0].merge(olist[1], on=["Name"], suffixes=("_er", "_re"))
both_ori.to_csv("%s/both_%s_%s.csv" % (baseoutpath, maintf, cooptf),
index=False)
plot_pval(both_ori, "%s/pval.png" % baseoutpath)
print(
"Number of distinct names, above cutoff, after orientation joining %d"
% both_ori[both_ori["label"] != "below_cutoff"]["Name"].nunique())
both_ori_plt = both_ori[["Name", "intensity_x", "intensity_y", "label"]]
both_ori_plt.to_csv("%s/both_ori_plt_%s_%s.csv" %
(baseoutpath, maintf, cooptf),
index=False)
arr.plot_classified_labels(
both_ori_plt,
path="%s/both_normalized_%s_%s.png" % (baseoutpath, maintf, cooptf),
col1="intensity_x",
col2="intensity_y",
title=both_title,
xlab=ch_x,
ylab=ch_y,
plotnonsignif=False,
labelnames=["cooperative", "independent", "anticoop"])
print("Count per label", both_ori_plt[["label",
"Name"]].groupby("label").count())
# we use sequence where ets1 is on the left for simplicity
name_info = df_m[df_m["ori"] == "er"][[
"Name", "Sequence",
"%s_pos" % maintf,
"%s_start" % maintf,
"%s_pos" % cooptf,
"%s_start" % cooptf, "ori"
(k, ori, 'm2')] - 2 * median_dict[(k, ori, 'm3')]
rowdict['two_median'] = median_dict[(k, ori, 'wt')] - median_dict[
(k, ori, 'm3')]
rowdict['Name'] = k
orilbls.append(rowdict)
#print(orilbls)
labeled_dict[ori] = pd.DataFrame(orilbls)
labeled_dict[ori]['p'] = sm.fdrcorrection(labeled_dict[ori]['p'])[1]
labeled_dict[ori]['label'] = labeled_dict[ori].apply(
lambda row: assign_class(row['p'], row['label']), axis=1)
print(ori, labeled_dict[ori]["label"].value_counts())
arr.plot_classified_labels(labeled_dict[ori],
col1="indiv_median",
col2="two_median",
log=True,
xlab="log(wt-m3)",
ylab="log(m1-m3+m2-m3)",
path="coop_log_%s.png" % ori,
title="Cooperative plot (in log), ori %s" %
ori)
arr.plot_classified_labels(labeled_dict[ori],
col1="indiv_median",
col2="two_median",
log=False,
xlab="wt-m3",
ylab="m1-m3+m2-m3",
path="coop_%s.png" % ori,
title="Cooperative plot, ori %s" % ori)
df_er = labeled_dict['er'][labeled_dict['er']["label"] != "below_cutoff"]
df_re = labeled_dict['re'][labeled_dict['re']["label"] != "below_cutoff"]
# pickle.dump( two, open( "twosites.p", "wb" ) )
# indiv = pickle.load( open( "indivsum.p", "rb" ) )
# two = pickle.load( open( "twosites.p", "rb" ) )
lbled = arr.label_replicas_permutation(indiv,
two,
df,
cutoff=cutoff,
fdrcor=False,
pcut=0.05)
for ori in lbled:
lbled[ori].to_csv("lbled_%s.csv" % ori, index=False)
arr.plot_classified_labels(lbled[ori],
col1="indiv_median",
col2="two_median",
log=True,
xlab="log(m1-m3+m2-m3)",
ylab="log(wt-m3)",
path="labeled_log_%s.png" % ori,
title="Cooperative plot, %s" % ori)
print("Count %s" % ori, lbled[ori]["label"].value_counts())
lbled_both = lbled["o1"][[
"Name", "p", "label", "indiv_median", "two_median"
]].merge(lbled["o2"][["Name", "label", "p", "indiv_median", 'two_median']],
on="Name",
suffixes=("_o1", "_o2"))
lbled_both.to_csv("lbled_both.csv", index=False)
# lbled_both = pd.read_csv("lbled_both.csv")
lbled_both["indiv_median"] = (lbled_both["indiv_median_o1"] +
lbled_both["indiv_median_o2"]) / 2
lbled_both["two_median"] = (lbled_both["two_median_o1"] +
"%s/ch3_ch4/coop_ch3_vs_ch4/tables/probes_labeled_er.csv" %
basepath)[["Name", "ch1", "ch2", "ori"]]
df2_re = pd.read_csv(
"%s/ch3_ch4/coop_ch3_vs_ch4/tables/probes_labeled_re.csv" %
basepath)[["Name", "ch1", "ch2", "ori"]]
df2 = pd.concat([df2_er, df2_re
]).groupby(["Name", "ori"
]).median().reset_index().merge(df2_label,
on="Name")
arr.plot_classified_labels(
df2,
path="aaa.png",
col1="ch1",
col2="ch2",
labelcol="label",
title="Ets_Runx1",
xlab="Ch1",
ylab="Ch2",
labelnames=["cooperative", "independent", "anticoop"],
)
#combine_ch_intensity(df1, df2)
"""
train_ch1 = pd.read_csv("%s/ch1_ch2/training_pwm.tsv" % basepath, sep="\t")
train_ch2 = pd.read_csv("%s/ch3_ch4/training_pwm.tsv" % basepath, sep="\t")
print("Chamber 1-2")
print(df1.groupby("label")["ets_score"].count())
print("Chamber 3-4")
ch34_two = pd.read_csv("%s/ch3_ch4/coop_ch3_vs_ch4/tables/two_df.tsv" %
basepath,
sep="\t")
print(ch12)
print("ch1ch2")
print(ch12["label"].value_counts())
print("ch3ch4")
print(ch34["label"].value_counts())
# plot
ax = plt.axes()
arr.plot_classified_labels(ch12,
title="Cooperative plot, both orientations",
col1="ch1",
col2="ch2",
axes=ax)
coop34_in12 = ch34[ch34["label"] == "cooperative"][["Name"]] \
.merge(ch12, on=["Name"])
x, y = np.log(coop34_in12["ch1"].values), np.log(coop34_in12["ch2"].values)
ax.scatter(x, y, color="cyan", s=3, label="overlap coop ch1ch2 ch3ch4")
ax.legend(loc="lower right")
plt.savefig("overlap.png")
print("Overlap in ch1ch2 and ch3ch4")
probe_overlap = ch12.merge(ch34, on="Name")
match_lbl = probe_overlap[probe_overlap["label_x"] ==
probe_overlap["label_y"]]
print(probe_overlap.shape[0])
print(match_lbl["label_x"].value_counts())