# Parameters
data_name = "prePLSM_B;A;GEO"
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_138-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_138-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 19:11:16,677 [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	Pre-PB
Cell Group	B cells
Experiment Name	ATAC
Experiment Group	GEO

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	143684	110569	17.3414	32240553	10078846	0.3128	6628772	0.2057	11997754	0.3723
rep2	143684	110569	14.953	35166312	10008583	0.2848	6071045	0.1727	14319007	0.4074

Metric	Value
auPRC	0.5913
Calibrated Recall at 50% FDR	0.198
Number of Positive Examples in Test Data	120867
Number of Negative Examples in Test Data	7949984
Imbalance Ratio in Test Data	0.015
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 6502 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 5250 SequenceContrib ScoresHyp_Contrib Scores	Spi1, Spib, Ets1, Erg, Irf8, Etv6, Etv2, Irf4, Gabpa, Elk1, Elf1, Ehf, Elf3, Spic, Etv4, Etv3, Fli1, XP_911724.4, Elk4, Elf4, Elf2, Elk3, Etv5, Etv1, Prdm1, Elf5, Irf3, Irf2, Irf1, Fev, Spdef
metacluster_1/pattern_2 # seqlets: 3325 SequenceContrib ScoresHyp_Contrib Scores	Irf7, Stat2, Stat1, Irf9, Batf3, Irf5
metacluster_1/pattern_3 # seqlets: 2768 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf7, Klf6, Klf4, Klf8, Klf1, Klf12, Egr1, Zbtb17, Egr2, E2f1, Sp5, Klf5, Zfp281, Zfx, Egr3, Zfp740, Zbtb1
metacluster_1/pattern_4 # seqlets: 1838 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_5 # seqlets: 1044 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_6 # seqlets: 685 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_7 # seqlets: 659 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Atf7, Atf1, Crem, Usf2, Jdp2, Creb5, Atf3, Fosl2, Jun, Nfil3, Fosl1
metacluster_1/pattern_8 # seqlets: 544 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2
metacluster_1/pattern_9 # seqlets: 500 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Zfp42, Wt1, Mxi1, Maz
metacluster_1/pattern_10 # seqlets: 456 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfe3, Arntl, Tfec, Tfeb, Mitf, Srebf1, Bhlhe40, Clock, Mlx, Arnt, Srebf2, Npas2, Tcfl5, Creb3l2, Bhlhe41, Max, Mycn, Hlf, Myc, Dbp, Mlxip, Xbp1, Rarg
metacluster_1/pattern_11 # seqlets: 455 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6, Sox2, Pou5f1
metacluster_1/pattern_12 # seqlets: 415 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_13 # seqlets: 412 SequenceContrib ScoresHyp_Contrib Scores	Batf, Fosb, Jund, Junb, Fos, Bach2, Nfe2, Nfe2l2, Mafk, Mafb, Mafa
metacluster_1/pattern_14 # seqlets: 344 SequenceContrib ScoresHyp_Contrib Scores	Hnf1b, Hnf1a
metacluster_1/pattern_15 # seqlets: 312 SequenceContrib ScoresHyp_Contrib Scores	Nfkb2, Nfkb1, Rela, Relb, Rel
metacluster_1/pattern_16 # seqlets: 224 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_17 # seqlets: 197 SequenceContrib ScoresHyp_Contrib Scores	Ebf1, Prdm16
metacluster_1/pattern_18 # seqlets: 185 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_19 # seqlets: 181 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_20 # seqlets: 146 SequenceContrib ScoresHyp_Contrib Scores	Lyl1, Olig2, Myog, Tal1, Ptf1a, Tcf3, Ascl2, Ascl1, Myod1, Myf6, Bhlha15, Tcf21, Twist1, Nhlh1, Atoh1, Myf5, Tcf12, Figla, Myb, Tcf7l1, Foxo1, Tcf4
metacluster_1/pattern_21 # seqlets: 136 SequenceContrib ScoresHyp_Contrib Scores