# Parameters
data_name = "STMCH;P0;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_264-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_264-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 19:39:54,306 [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	stomach(P0)
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	174433	121637	6.4419	120853885	10636266	0.088	7502125	0.0621	41576855	0.3441
rep2	181904	121637	5.6203	163088440	NA	NA	NA	NA	NA	NA

Metric	Value
auPRC	0.5673
Calibrated Recall at 50% FDR	0.242
Number of Positive Examples in Test Data	82943
Number of Negative Examples in Test Data	7987908
Imbalance Ratio in Test Data	0.0103
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 4282 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 2420 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp1, Sp3, Sp2, Klf3, Klf6, Zbtb17, E2f4, Klf7, Egr1, Klf8, E2f1, Klf12, Sp5, Klf5, Klf1, Egr2, Klf4, Klf15, Maz, Zfp281, Wt1, Sall4, E2f7
metacluster_1/pattern_2 # seqlets: 2223 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_3 # seqlets: 2216 SequenceContrib ScoresHyp_Contrib Scores	Ehf, Elf1, Elf5, Elf2, Etv4, Elf3, Gabpa, Elk4, Ets1, Erg, Elk1, Etv2, Elf4, Etv6, Elk3, Fli1, Fev, Etv3, XP_911724.4, Spdef, Etv1, Etv5, Spic, Spi1, Spib, Irf8, Irf4
metacluster_1/pattern_4 # seqlets: 1367 SequenceContrib ScoresHyp_Contrib Scores	Foxm1, Foxa2, Foxa1, Foxd1, Foxa3, Foxd3, Foxc1, Foxc2, Foxb1, Foxj2, Foxl1, Foxl2, Foxg1, Foxk1, Foxp2, Gm5294, Foxj3, Foxo1, Foxo3, Foxp1, Foxj1, Foxq1, Foxo4
metacluster_1/pattern_5 # seqlets: 1130 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Creb5, Jdp2, Creb1, Crem, Atf1, Dbp, Cebpb, Nfil3, Hlf, Cebpa, Jun, Tef, Atf3, Fosl1, Gmeb2, Cebpd, Ddit3, Mafb, Atf4, Jund, Cebpg, Fosl2, Tfec, Srebf1, Junb, Mlx, Esr2, Rxrb, Rora, Creb3l2, XP_002726925.1
metacluster_1/pattern_6 # seqlets: 1070 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_1/pattern_7 # seqlets: 1046 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_8 # seqlets: 972 SequenceContrib ScoresHyp_Contrib Scores	Nrf1, Zfx
metacluster_1/pattern_9 # seqlets: 870 SequenceContrib ScoresHyp_Contrib Scores	Fos, Fosb, Batf, Bach2, Nfe2l2, Nfe2, Bach1, Mafa
metacluster_1/pattern_10 # seqlets: 861 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_11 # seqlets: 679 SequenceContrib ScoresHyp_Contrib Scores	Hnf4a, Hnf4g, Nr1h3, Rxra, Nr2f6, Nr2c2, Nr2f1, Ppara, Rarg, Rara, Rarb, Pparg
metacluster_1/pattern_12 # seqlets: 606 SequenceContrib ScoresHyp_Contrib Scores	Grhl2
metacluster_1/pattern_13 # seqlets: 542 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf7, Irf2, Stat2, Irf9, Irf5, Stat1, Irf3, Irf6, Prdm1
metacluster_1/pattern_14 # seqlets: 483 SequenceContrib ScoresHyp_Contrib Scores	Hnf1b, Hnf1a
metacluster_1/pattern_15 # seqlets: 463 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Usf2, Tfeb, Arntl, Tfe3, Mitf, Clock, Arnt, Bhlhe40, Npas2, Tcfl5, Srebf2, Xbp1, Mycn, Max, Bhlhe41, Myc, Mlxip, Hes1
metacluster_1/pattern_16 # seqlets: 426 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_17 # seqlets: 375 SequenceContrib ScoresHyp_Contrib Scores	Gata4, Tal1, Gata2, Gata3, Gata1, Gata6, Mecom, Gata5
metacluster_1/pattern_18 # seqlets: 360 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx1, Rfx4, Rfx7, Rfx6, Sox2, Pou5f1
metacluster_1/pattern_19 # seqlets: 260 SequenceContrib ScoresHyp_Contrib Scores	Tead2, Tead4, Tead1
metacluster_1/pattern_20 # seqlets: 238 SequenceContrib ScoresHyp_Contrib Scores	Yy1, Taf1, Zfp42
metacluster_1/pattern_21 # seqlets: 144 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33, Mxi1
metacluster_1/pattern_22 # seqlets: 127 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_23 # seqlets: 76 SequenceContrib ScoresHyp_Contrib Scores	Rest