# Parameters
data_name = "Spleen;8wks;D;En"
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_266-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_266-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 19:40:08,862 [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	spleen(adult-8wks)
Cell Group	Other Tissues
Experiment Name	DHS
Experiment Group	ENCODE

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	76835	51010	22.7051	20603317	4762494	0.2313	3616808	0.1757	7416247	0.3602
rep2	76835	51010	18.1624	25015661	4062839	0.1625	3432306	0.1373	8888148	0.3555

Metric	Value
auPRC	0.5814
Calibrated Recall at 50% FDR	0.22
Number of Positive Examples in Test Data	65465
Number of Negative Examples in Test Data	8005386
Imbalance Ratio in Test Data	0.0081
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 7552 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 7449 SequenceContrib ScoresHyp_Contrib Scores	Spib, Spi1, Etv2, Irf4, Irf8, Ets1, Spic, Etv4, Etv6, Erg, Ehf, Elf3, Fli1, Gabpa, Etv3, Elk1, XP_911724.4, Elf1, Elf4, Elk4, Elf2, Elk3, Etv1, Etv5, Elf5, Irf3, Prdm1, Irf2, Fev, Irf1, Spdef
metacluster_1/pattern_2 # seqlets: 2547 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf6, Klf7, Klf4, Klf1, Klf8, Klf12, Egr1, Zbtb17, Egr2, E2f1, Klf5, Sp5, Zfp281, Zfp740, Zfx, Zbtb1, Egr3
metacluster_1/pattern_3 # seqlets: 1668 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_4 # seqlets: 1440 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf7, Atf2, Jdp2, Crem, Creb5, Atf1, Jun, Atf3, Fosl2
metacluster_1/pattern_5 # seqlets: 1132 SequenceContrib ScoresHyp_Contrib Scores	Stat2, Stat1, Irf7, Irf9, Irf5
metacluster_1/pattern_6 # seqlets: 1090 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Foxi1, Nfyc, Nfya, Pbx3
metacluster_1/pattern_7 # seqlets: 908 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfec, Tfeb, Arntl, Usf2, Mitf, Bhlhe40, Srebf1, Tfe3, Mlx, Clock, Arnt, Npas2, Srebf2, Tcfl5, Creb3l2, Bhlhe41, Hlf, Dbp, Xbp1, Mlxip, Arnt2
metacluster_1/pattern_8 # seqlets: 684 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_9 # seqlets: 626 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Rfx1, Wt1, Maz
metacluster_1/pattern_10 # seqlets: 568 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_11 # seqlets: 459 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_12 # seqlets: 440 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb
metacluster_1/pattern_13 # seqlets: 393 SequenceContrib ScoresHyp_Contrib Scores	Nfkb2, Nfkb1, Rela, Relb, Rel
metacluster_1/pattern_14 # seqlets: 314 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2
metacluster_1/pattern_15 # seqlets: 192 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_16 # seqlets: 137 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_17 # seqlets: 132 SequenceContrib ScoresHyp_Contrib Scores	Jund, Fosl1, Junb, Fosb, Fos, Batf, Mafa, Bach2, Nr1d2
metacluster_1/pattern_18 # seqlets: 83 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_19 # seqlets: 40 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic