# Parameters
data_name = "CH12_QNTPLE;A;CL"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
tomtom_report_root = "http://mitra.stanford.edu/kundaje/msharmin/report/tomtom_outs/cells"
task_dir = "task_90-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_90-naivegw/NaiveauPRC.txt"
homer_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_scans"
reportfile = "/mnt/lab_data/kundaje/msharmin/annotations/filtering samples_MS2.xlsx"
sheetname = "filter23"

from matlas.reports import display_metadata

load data from labcluster

Using TensorFlow backend.
2019-08-30 19:00:20,148 [WARNING] git-lfs not installed

display_metadata(data_name, perf_file, reportfile, sheetname)

from matlas.reports import display_paiwise_pattern_comparison
from matlas.reports import display_denovo_patterns

display_denovo_patterns(data_name, modisco_root=modisco_root)

TF-MoDISco is using the TensorFlow backend.

display_paiwise_pattern_comparison(data_name, modisco_root, homer_root)

MetaData Name	Description
Cell type	ch12 with quintuple mt
Cell Group	Cancer or Immortalized cells
Experiment Name	ATAC
Experiment Group	Casellas Lab

replicate	Naïve overlap peaks	IDR peaks	TSS enrichment (< 8 is very poor <10 is low)	Final number of unique mapping, dup-filtered, chrM filtered reads	Number of reads in called peak regions	Fraction of reads in called peak regions	Number of reads in promoter regions	Fraction of reads in promoter regions	Number of reads in enhancer regions	Fraction of reads in enhancer regions
rep1	82059	54250	12.4137	28786451	3351292	0.1165	3090304	0.1074	9900239	0.3442
rep2	82059	54250	17.6827	18380175	2495446	0.1359	2436201	0.1327	6120059	0.3333

Metric	Value
auPRC	0.5918
Calibrated Recall at 50% FDR	0.205
Number of Positive Examples in Test Data	60313
Number of Negative Examples in Test Data	8010538
Imbalance Ratio in Test Data	0.0075
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 4552 SequenceContrib ScoresHyp_Contrib Scores	Etv6, Ets1, Gabpa, Elk1, Fli1, Spi1, Erg, Spib, Etv3, Etv2, Elf1, Elk4, XP_911724.4, Elk3, Etv5, Elf4, Spic, Etv4, Etv1, Elf2, Irf4, Irf8, Ehf, Elf5, Elf3, Fev, Spdef, Irf2, Prdm1, Irf3, Irf1
metacluster_1/pattern_1 # seqlets: 4441 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_2 # seqlets: 3466 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp1, Sp3, Klf3, Sp4, Zfx, Klf6, Wt1, Zbtb17, Klf15, Klf1, Sp5, Maz, Egr1, Zfp281, Usf2, Klf5, E2f4, Klf4, Klf7, Egr2, Klf12, Klf8, Mxi1, Tfap2c, Rfx1, Nr1h4, Ptf1a, Tfap2b, Nhlh1, E2f1
metacluster_1/pattern_3 # seqlets: 1901 SequenceContrib ScoresHyp_Contrib Scores	Nfkb2, Nfkb1, Rela, Relb, Rel
metacluster_1/pattern_4 # seqlets: 1626 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_5 # seqlets: 1267 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_6 # seqlets: 930 SequenceContrib ScoresHyp_Contrib Scores	Zscan10, Irf7, Stat1, Stat2
metacluster_1/pattern_7 # seqlets: 867 SequenceContrib ScoresHyp_Contrib Scores	Batf3, Irf9, Irf5
metacluster_1/pattern_8 # seqlets: 832 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_1/pattern_9 # seqlets: 794 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Atf7, Crem, Atf1, Jdp2, Creb5, Atf3, Jun, Usf1, Fosl2, Nfil3, Hlf, Rxrb
metacluster_1/pattern_10 # seqlets: 693 SequenceContrib ScoresHyp_Contrib Scores	Tfeb, Tfec, Arntl, Mitf, Tfe3, Srebf1, Bhlhe40, Clock, Mlx, Arnt, Npas2, Creb3l2, Srebf2, Tcfl5, Bhlhe41, Xbp1, Hes1, Mlxip, Max, Mycn, Arnt2, Dbp
metacluster_1/pattern_11 # seqlets: 690 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Pou2f1
metacluster_1/pattern_12 # seqlets: 670 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_1/pattern_13 # seqlets: 594 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_14 # seqlets: 593 SequenceContrib ScoresHyp_Contrib Scores	Mef2a, Mef2c, Mef2d
metacluster_1/pattern_15 # seqlets: 532 SequenceContrib ScoresHyp_Contrib Scores	Tfap2a, Hes7, Rarg
metacluster_1/pattern_16 # seqlets: 483 SequenceContrib ScoresHyp_Contrib Scores	Batf, Nfe2l2, Nfe2, Bach2, Bach1, Fos, Jund, Mafk, Fosl1, Fosb, Mafb, Junb, Mafa, Mafg, Maff, Maf
metacluster_1/pattern_17 # seqlets: 205 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_18 # seqlets: 87 SequenceContrib ScoresHyp_Contrib Scores	Ebf1
metacluster_1/pattern_19 # seqlets: 76 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_20 # seqlets: 56 SequenceContrib ScoresHyp_Contrib Scores