def precision_recall_curve(values,
true_set=None,
false_set=None,
fdr_thres=0.01,
return_curve=False):
if true_set is None:
true_set = Utils.get_essential_genes(return_series=False)
if false_set is None:
false_set = Utils.get_non_essential_genes(return_series=False)
index_set = true_set.union(false_set)
rank = values[values.index.isin(index_set)]
y_true = rank.index.isin(true_set).astype(int)
ap = average_precision_score(y_true, -rank)
precision, recall, thres = precision_recall_curve(y_true, -rank)
recall_fdr = recall[precision > (1 - fdr_thres)].max()
res = ((ap, recall_fdr, precision, recall, thres) if return_curve else
(ap, recall_fdr))
return res
def aroc_threshold(values,
true_set=None,
false_set=None,
fpr_thres=0.01,
return_curve=False):
if true_set is None:
true_set = Utils.get_essential_genes(return_series=False)
if false_set is None:
false_set = Utils.get_non_essential_genes(return_series=False)
index_set = true_set.union(false_set)
rank = values[values.index.isin(index_set)]
y_true = rank.index.isin(true_set).astype(int)
fpr, tpr, thres = roc_curve(y_true, -rank)
auc_fpr = roc_auc_score(y_true, -rank, max_fpr=fpr_thres)
if fpr_thres is not None:
fc_thres_fpr = -min(thres[fpr <= fpr_thres])
else:
fc_thres_fpr = None
res = ((auc_fpr, fc_thres_fpr, fpr, tpr) if return_curve else
(auc_fpr, fc_thres_fpr))
return res
def define_sgrnas_sets(clib, fc=None, add_controls=True, dataset_name="Yusa_v1"):
sgrna_sets = dict()
# sgRNA essential
sgrnas_essential = Utils.get_essential_genes(return_series=False)
sgrnas_essential = set(clib[clib["Gene"].isin(sgrnas_essential)].index)
sgrnas_essential_fc = (
None if fc is None else fc.reindex(sgrnas_essential).median(1).dropna()
)
sgrna_sets["essential"] = dict(
color="#e6550d", sgrnas=sgrnas_essential, fc=sgrnas_essential_fc
)
# sgRNA non-essential
sgrnas_nonessential = Utils.get_non_essential_genes(return_series=False)
sgrnas_nonessential = set(clib[clib["Gene"].isin(sgrnas_nonessential)].index)
sgrnas_nonessential_fc = (
None if fc is None else fc.reindex(sgrnas_nonessential).median(1).dropna()
)
sgrna_sets["nonessential"] = dict(
color="#3182bd", sgrnas=sgrnas_nonessential, fc=sgrnas_nonessential_fc
)
# sgRNA non-targeting
if add_controls:
if dataset_name in ["Yusa_v1", "Yusa v1", "Yusa_v1.1", "Yusa v1.1", "Sabatini_Lander_AML"]:
sgrnas_control = {i for i in clib.index if i.startswith("CTRL0")}
else:
sgrnas_control = set(
clib[[i.startswith("NO_CURRENT_") for i in clib["Gene"]]].index
)
sgrnas_control_fc = fc.reindex(sgrnas_control).median(1).dropna()
sgrna_sets["nontargeting"] = dict(
color="#31a354",
sgrnas=sgrnas_control,
fc=None if fc is None else sgrnas_control_fc,
)
return sgrna_sets
def project_score_data(sgrnas, subset=None):
ddir = pkg_resources.resource_filename("crispy", "data/")
score_manifest = pd.read_csv(
f"{ddir}/crispr_manifests/project_score_manifest.csv.gz")
s_map = []
for i in score_manifest.index:
s_map.append(
pd.DataFrame(
dict(
model_id=score_manifest.iloc[i]["model_id"],
s_ids=score_manifest.iloc[i]["library"].split(", "),
s_lib=score_manifest.iloc[i]
["experiment_identifier"].split(", "),
)))
s_map = pd.concat(s_map).set_index("s_lib")
if subset is not None:
s_map = s_map[s_map["model_id"].isin(subset)]
score_v1 = CRISPRDataSet("Yusa_v1")
score_v1_fc = score_v1.counts.norm_rpm().foldchange(score_v1.plasmids)
score_v1_fc = score_v1_fc.groupby(s_map["model_id"], axis=1).mean()
score_v11 = CRISPRDataSet("Yusa_v1.1")
score_v11_fc = score_v11.counts.norm_rpm().foldchange(score_v11.plasmids)
score_v11_fc = score_v11_fc.groupby(s_map["model_id"], axis=1).mean()
ess = set(score_v1.lib[score_v1.lib["Gene"].isin(
Utils.get_essential_genes())].index)
ness = set(score_v1.lib[score_v1.lib["Gene"].isin(
Utils.get_non_essential_genes())].index)
score_v1_fc = ReadCounts(score_v1_fc).scale(essential=ess,
non_essential=ness)
score_v11_fc = ReadCounts(score_v11_fc).scale(essential=ess,
non_essential=ness)
score_fc = pd.concat([score_v1_fc.loc[sgrnas], score_v11_fc.loc[sgrnas]],
axis=1).dropna()
return score_fc
def pr_curve(rank, true_set=None, false_set=None, min_events=10):
if true_set is None:
true_set = Utils.get_essential_genes(return_series=False)
if false_set is None:
false_set = Utils.get_non_essential_genes(return_series=False)
index_set = true_set.union(false_set)
rank = rank[rank.index.isin(index_set)]
if len(rank) == 0:
return np.nan
y_true = rank.index.isin(true_set).astype(int)
if sum(y_true) < min_events:
return np.nan
return roc_auc_score(y_true, -rank)
def scale(self, essential=None, non_essential=None, metric=np.median):
if essential is None:
essential = Utils.get_essential_genes(return_series=False)
if non_essential is None:
non_essential = Utils.get_non_essential_genes(return_series=False)
assert (
len(essential.intersection(self.index)) != 0
), "DataFrame has no index overlapping with essential list"
assert (
len(non_essential.intersection(self.index)) != 0
), "DataFrame has no index overlapping with non essential list"
essential_metric = metric(self.reindex(essential).dropna(), axis=0)
non_essential_metric = metric(self.reindex(non_essential).dropna(), axis=0)
return self.subtract(non_essential_metric).divide(
non_essential_metric - essential_metric
)
def define_controls(
n_genes=3,
cancer_type="Colorectal Carcinoma",
cn_min=1,
cn_max=5,
crisp_min=-0.10,
jacks_thres=0.25,
offtarget=[1, 0, 0],
):
# Samples
samples = set(DataImporter.Sample().samplesheet.query(
f"cancer_type == '{cancer_type}'").index)
# Non-essential genes
ness = Utils.get_non_essential_genes(return_series=False)
ness = ness - set(Utils.get_sanger_essential()["Gene"])
# Non-essential genes sgRNAs
ness_sgrnas = pd.concat(
[
gselection.select_sgrnas(
g, 2, jacks_thres=jacks_thres,
offtarget=offtarget).assign(gene=g) for g in ness
],
ignore_index=True,
).query("Library == 'KosukeYusa'")
ness_sgrnas_fc = project_score_data(ness_sgrnas["sgRNA_ID"], samples)
ness_sgrnas_fc_ds = ness_sgrnas_fc.T.describe().T.dropna()
ness_sgrnas_fc_ds = ness_sgrnas_fc_ds[
ness_sgrnas_fc_ds["25%"] >= crisp_min]
ness_sgrnas_fc_ds["Approved_Symbol"] = (
ness_sgrnas.set_index("sgRNA_ID").loc[ness_sgrnas_fc_ds.index,
"Approved_Symbol"].values)
ness_sgrnas = ness_sgrnas.set_index("sgRNA_ID").loc[
ness_sgrnas_fc_ds.index]
# Import different levels of information
ddir = pkg_resources.resource_filename("crispy", "data/")
cn = DataImporter.CopyNumber(
f"{ddir}/copy_number/cnv_abs_copy_number_picnic_20191101.csv.gz"
).filter(subset=samples)
hgnc = pd.read_csv(f"{DPATH}/protein-coding_gene.txt",
sep="\t",
index_col=1)
# Control genes
controls = ness_sgrnas.groupby("Approved_Symbol")["Library"].count()
controls = list(controls[controls == 2].index)
controls = pd.concat(
[
cn.reindex(controls).dropna().T.describe().T,
hgnc.reindex(controls)["location"],
],
axis=1,
sort=False,
).dropna()
controls = controls.query(f"(min >= {cn_min}) and (max <= {cn_max})")
controls = controls.reset_index().rename(
columns={"index": "Approved_Symbol"})
controls = controls.merge(
ness_sgrnas_fc_ds.reset_index(),
on="Approved_Symbol",
suffixes=("_cn", "_crispr"),
)
control_genes = list(
controls.groupby("Approved_Symbol")["min_crispr"].mean().sort_values(
ascending=False)[:n_genes].index)
controls = controls[controls["Approved_Symbol"].isin(control_genes)]
controls["location"] = hgnc.loc[controls["Approved_Symbol"],
"location"].values
control_guides = gselection.masterlib[
gselection.masterlib["sgRNA_ID"].isin(
controls["sgRNA"])].assign(Confidence="Control")[LIB_COLUMNS]
return control_guides.sort_values("Approved_Symbol")
col_colors=pd.Series(sample_pal)[plot_df.columns].rename("Library"),
row_colors=pd.Series(sample_pal)[plot_df.index].rename("Library"),
cbar_pos=None,
)
plt.savefig(f"{RPATH}/minlibcas9_screens_clustermap_gene_fc.pdf",
bbox_inches="tight")
plt.close("all")
# Recall gene lists
#
gsets_aucs = {}
for n, gset in [
("essential", Utils.get_essential_genes()),
("non-essential", Utils.get_non_essential_genes()),
]:
# Aroc
plt.figure(figsize=(2, 2), dpi=600)
ax = plt.gca()
_, stats_ess = QCplot.plot_cumsum_auc(fc_gene[samples],
gset,
palette=sample_pal,
legend_prop={"size": 4},
ax=ax)
plt.title(f"{n} recall curve")
plt.xlabel("Percent-rank of genes")
plt.ylabel("Cumulative fraction")
plt.grid(True, ls=":", lw=0.1, alpha=1.0, zorder=0, axis="both")
plt.savefig(f"{RPATH}/minlibcas9_screens_roccurves_{n}.pdf",
bbox_inches="tight")