# Parameters
data_name = "ILC2;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_108-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_108-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 19:04:27,293 [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	ILC2(WT)
Cell Group	Other Immune 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	125814	96194	15.0497	23960844	6656033	0.278	4184684	0.1748	9597374	0.4008
rep2	125814	96194	17.0949	22004918	4675748	0.2127	3227640	0.1468	8394249	0.3818

Metric	Value
auPRC	0.5957
Calibrated Recall at 50% FDR	0.196
Number of Positive Examples in Test Data	106509
Number of Negative Examples in Test Data	7964342
Imbalance Ratio in Test Data	0.0132
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 6159 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 4469 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Etv4, Fli1, Elk1, Etv2, Gabpa, Elk4, Spi1, Etv5, Elk3, Etv6, Fev, Elf2, Etv1, Etv3, XP_911724.4, Spib, Elf1, Elf4, Ehf, Elf5, Elf3, Irf8, Irf4, Spic, Spdef, Stat3, Zscan10, Stat4
metacluster_1/pattern_2 # seqlets: 2450 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Sp4, Klf3, Klf6, Sp1, Klf1, E2f4, Klf7, Egr1, Klf4, Klf8, Klf12, Klf15, Wt1, Zbtb17, Zfx, Klf5, Zfp281, Maz, Egr2, Sp5, E2f1, E2f7
metacluster_1/pattern_3 # seqlets: 1366 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Creb5, Atf7, Atf2, Jdp2, Atf1, Crem, Jun, Nfil3, Tef, Mafb, Dbp, Fosl1, Atf3, Cebpb, Hlf, Gmeb2, Jund, Cebpa, Junb, Fosl2, Rxrb, Cebpd, Gmeb1, Cebpg
metacluster_1/pattern_4 # seqlets: 1358 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_5 # seqlets: 1115 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_6 # seqlets: 1024 SequenceContrib ScoresHyp_Contrib Scores	Bach2, Bach1, Fos, Batf, Nfe2, Nfe2l2, Fosb, Mafa, Mafk, Mafg
metacluster_1/pattern_7 # seqlets: 982 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Stat1, Prdm1, Irf7, Stat2, Irf3, Irf9, Batf3
metacluster_1/pattern_8 # seqlets: 856 SequenceContrib ScoresHyp_Contrib Scores	Nfkb1, Rela, Nfkb2, Relb, Rel
metacluster_1/pattern_9 # seqlets: 817 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_10 # seqlets: 703 SequenceContrib ScoresHyp_Contrib Scores	Gata3, Gata2, Gata1, Gata4, Gata6, Tal1
metacluster_1/pattern_11 # seqlets: 615 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_12 # seqlets: 609 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Usf2, Tfe3, Tfeb, Arntl, Tfec, Mitf, Clock, Srebf1, Bhlhe40, Arnt, Mlx, Npas2, Srebf2, Mycn, Max, Tcfl5, Myc, Creb3l2, Bhlhe41, Xbp1
metacluster_1/pattern_13 # seqlets: 606 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Zfp42, Mxi1
metacluster_1/pattern_14 # seqlets: 482 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_15 # seqlets: 219 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_16 # seqlets: 213 SequenceContrib ScoresHyp_Contrib Scores	Ets2
metacluster_1/pattern_17 # seqlets: 147 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_18 # seqlets: 128 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_19 # seqlets: 111 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic
metacluster_1/pattern_20 # seqlets: 106 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2
metacluster_1/pattern_21 # seqlets: 95 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_22 # seqlets: 76 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_23 # seqlets: 83 SequenceContrib ScoresHyp_Contrib Scores