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)
avana_ks = estimate_ks(avana_fc, avana_gsets["nontargeting"]["fc"])
# CRISPR-Cas9 libraries
# Master library (KosukeYusa v1.1 + Avana + Brunello)
#
master_lib = Library.load_library("MasterLib_v1.csv.gz", set_index=False)
master_lib = master_lib.query("Library == 'KosukeYusa'")
# Project Score samples acquired with Kosuke_Yusa v1.1 library
#
ky = CRISPRDataSet("Yusa_v1.1")
ky_counts = ky.counts.remove_low_counts(ky.plasmids)
ky_fc = ky_counts.norm_rpm().norm_rpm().foldchange(ky.plasmids)
ky_gsets = define_sgrnas_sets(ky.lib, ky_fc, add_controls=True)
ky_gmetrics = pd.concat(
[
ky_fc.median(1).rename("Median"),
master_lib.set_index("sgRNA_ID")[[
"JACKS", "RuleSet2", "FORECAST", "KS"
]],
],
axis=1,
sort=False,
)
# sgRNA metrics scatter plots
#