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
"EGAN00002143462.sample",
"EGAN00002143463.sample",
"EGAN00002143464.sample",
"EGAN00002143465.sample",
"EGAN00002143466.sample",
],
)
# - Imports
ddir = pkg_resources.resource_filename("data", "organoids/bme2/")
dreports = pkg_resources.resource_filename("notebooks", "bme/reports/")
ss = pd.read_excel(f"{ddir}/{organoids['samplesheet']}",
index_col=1).query("organoid == 'COLO-027'")
counts = CRISPRDataSet(organoids, ddir=ddir)
# -
samples = list(set(ss.index).intersection(ss.index))
palette = ss.set_index("name")["palette"]
# - Fold-changes
fc = (counts.counts.remove_low_counts(
counts.plasmids).norm_rpm().foldchange(counts.plasmids))
fc_gene = fc.groupby(counts.lib.reindex(fc.index)["Gene"]).mean()
fc_gene_scaled = ReadCounts(fc_gene).scale()
# -
fc_gene_scaled.rename(columns=ss["name"]).round(5).to_excel(
import pandas as pd
import pkg_resources
import matplotlib.pyplot as plt
from crispy.CRISPRData import CRISPRDataSet
from minlib.Utils import project_score_sample_map, density_interpolate, downsample_sgrnas
LOG = logging.getLogger("Crispy")
DPATH = pkg_resources.resource_filename("crispy", "data/")
RPATH = pkg_resources.resource_filename("notebooks", "minlib/reports/")
# Project Score samples acquired with Kosuke_Yusa v1.1 library
#
ky = CRISPRDataSet("Yusa_v1.1")
ky_smap = project_score_sample_map()
ky_counts = ky.counts.remove_low_counts(ky.plasmids)
# Downsample number of sgRNAs per gene
#
ds_scores = downsample_sgrnas(
ky_counts, ky.lib, ky_smap, [1, 2, 3, 4, 5, 100], n_iters=10
)
ds_scores.to_excel(f"{RPATH}/YusaDownsample_AROCs.xlsx", index=False)
# Plot
#
import logging
import numpy as np
import pandas as pd
import pkg_resources
from crispy.CRISPRData import CRISPRDataSet, Library
from minlib.Utils import define_sgrnas_sets, estimate_ks
LOG = logging.getLogger("Crispy")
DPATH = pkg_resources.resource_filename("crispy", "data/")
RPATH = pkg_resources.resource_filename("notebooks", "minlib/reports/")
# Project Score KY v1.1
#
ky = CRISPRDataSet("Yusa_v1.1")
ky_fc = ky.counts.remove_low_counts(ky.plasmids).norm_rpm().foldchange(
ky.plasmids)
ky_gsets = define_sgrnas_sets(ky.lib, ky_fc, add_controls=True)
ky_ks = estimate_ks(ky_fc, ky_gsets["nontargeting"]["fc"])
# DepMap 19Q2 Avana
#
avana = CRISPRDataSet("Avana_DepMap19Q2")
avana_fc = (avana.counts.remove_low_counts(
avana.plasmids).norm_rpm().foldchange(avana.plasmids))
avana_gsets = define_sgrnas_sets(avana.lib,
avana_fc,
dataset_name="Avana_DepMap19Q2",
add_controls=True)
from natsort import natsorted
from crispy.QCPlot import QCplot
from scipy.stats import spearmanr
from minlib.Utils import replicates_correlation
from crispy.CRISPRData import CRISPRDataSet, Library
LOG = logging.getLogger("Crispy")
DPATH = pkg_resources.resource_filename("crispy", "data/")
RPATH = pkg_resources.resource_filename("notebooks", "minlib/reports/")
# Project Score samples acquired with Kosuke_Yusa v1.1 library
#
ky = CRISPRDataSet("KM12_coverage")
ky_counts = ky.counts.remove_low_counts(ky.plasmids)
ky_ss = pd.read_excel(
f"{DPATH}/crispr_manifests/KM12_coverage_samplesheet.xlsx", index_col="sample"
)
ky_ss["name"] = [f"{c}x ({e})" for e, c in ky_ss[["experiment", "coverage"]].values]
ky_ss["rep_name"] = [f"{n} (Rep{r})" for n, r in ky_ss[["name", "replicate"]].values]
# KY v1.1 library
#
ky_lib = Library.load_library("MasterLib_v1.csv.gz").query("Library == 'KosukeYusa'")
ky_lib = ky_lib[ky_lib.index.isin(ky_counts.index)]
ky_lib_fc = ky_counts.loc[ky_lib.index].norm_rpm().foldchange(ky.plasmids)
ky_lib_gene = ky_lib_fc.groupby(ky_lib["Approved_Symbol"]).mean()
ky_lib_gene_avg = ky_lib_gene.groupby(ky_ss["name"], axis=1).mean()
ml_lib = Library.load_library(ml_lib_name).query("Library == 'KosukeYusa'")
ml_lib = ml_lib.loc[[i for i in ml_lib.index if not i.startswith("CTRL0")]]
libraries = dict(
All=dict(
name="All",
lib=Library.load_library("MasterLib_v1.csv.gz").query(
"Library == 'KosukeYusa'"),
),
Minimal=dict(name="Minimal", lib=ml_lib),
)
# HT-29 CRISPR-Cas9 + Dabrafenib timecourse (Day 8, 10, 14, 18 and 21)
#
dabraf_data = CRISPRDataSet("HT29_Dabraf")
dabraf_count = dabraf_data.counts.remove_low_counts(dabraf_data.plasmids)
dabraf_ss = pd.read_csv(
f"{DPATH}/crispr_manifests/HT29_Dabraf_samplesheet.csv.gz",
index_col="sample")
# Export data
#
minlibcas9 = Library.load_library(ml_lib_name)
kylib = Library.load_library("MasterLib_v1.csv.gz").query(
"Library == 'KosukeYusa'")
data_export = dabraf_data.counts.copy()
data_export.insert(0, "MinLibCas9_guide",
data_export.index.isin(minlibcas9.index))
],
axis=1,
sort=False,
)
rawcounts = rawcounts.loc[:, ~rawcounts.columns.duplicated(keep="last")]
rawcounts.to_csv(f"{SPATH}/MinLibCas9_rawcounts.csv.gz", compression="gzip")
rawcounts.to_excel(f"{RPATH}/MinLibCas9_rawcounts.xlsx")
mlib_dataset = dict(
name="MinLibCas9_Screens",
read_counts="MinLibCas9_rawcounts.csv.gz",
library="MinLibCas9.csv.gz",
plasmids=["MHG_library_v1"],
)
mlib_data = CRISPRDataSet(mlib_dataset, ddir=SPATH)
mlib_count = mlib_data.counts.remove_low_counts(mlib_data.plasmids)
mlib_count.index = [
i if i.startswith("CTRL") else i.split(".")[0] for i in mlib_count.index
]
mlib_fc_sgrna = mlib_count.norm_rpm().foldchange(mlib_data.plasmids)
mlib_fc_gene = mlib_fc_sgrna.groupby(mlib["Approved_Symbol"]).mean()
# Project Score samples acquired with Kosuke_Yusa v1.1 library
#
ky = CRISPRDataSet("Yusa_v1.1")
ky_smap = project_score_sample_map()
ky_smap = ky_smap[[i.startswith("HT29") for i in ky_smap.index]]
import seaborn as sns
import matplotlib.pyplot as plt
from math import sqrt
from crispy.QCPlot import QCplot
from scipy.stats import spearmanr
from sklearn.metrics import mean_squared_error
from crispy.CRISPRData import CRISPRDataSet, Library
LOG = logging.getLogger("Crispy")
DPATH = pkg_resources.resource_filename("crispy", "data/")
RPATH = pkg_resources.resource_filename("notebooks", "minlib/reports/")
# CRISPR-Cas9 screens in 2 colorectal cancer organoids
#
org_data = CRISPRDataSet("Organoids")
org_count = org_data.counts.remove_low_counts(org_data.plasmids)
# Libraries
#
NGUIDES, REMOVE_DISCORDANT = 2, True
ml_lib_name = (
f"MinimalLib_top{NGUIDES}{'_disconcordant' if REMOVE_DISCORDANT else ''}.csv.gz"
)
ml_lib = Library.load_library(ml_lib_name).query("Library == 'KosukeYusa'")
ml_lib = ml_lib.loc[[i for i in ml_lib.index if not i.startswith("CTRL0")]]
libraries = dict(
All=dict(
name="All",