# Parameters
data_name = "SKLTL_Muscle;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_265-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_265-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 19:40:04,210 [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	skeletal muscle tissue(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	146772	90992	9.6676	78235884	12789824	0.1635	7545954	0.0965	32196938	0.4116
rep2	146772	90992	13.8174	24083036	3672633	0.1526	2709130	0.1126	9777976	0.4063

Metric	Value
auPRC	0.5371
Calibrated Recall at 50% FDR	0.269
Number of Positive Examples in Test Data	98235
Number of Negative Examples in Test Data	7972616
Imbalance Ratio in Test Data	0.0122
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 3192 SequenceContrib ScoresHyp_Contrib Scores	Sp5, Sp1, Wt1, Sp2, Sp3, Zbtb17, Maz, Klf3, Sp4, Klf5, Zfp281, Klf15, Egr1, Klf4, Klf1, Klf7, Klf6, Mxi1, Egr2, Klf8, Klf12, E2f4, Rela, E2f1, Zfx, Sall4, E2f6, Ctcfl, Fli1, Egr3, E2f7, Gata1, Usf2, Zfp740, Tfap2b, E2f3, Srebf2
metacluster_1/pattern_1 # seqlets: 2696 SequenceContrib ScoresHyp_Contrib Scores	Ctcf
metacluster_1/pattern_2 # seqlets: 1995 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_1/pattern_3 # seqlets: 1949 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Ets1, Erg, Elk1, Etv6, Elk4, Elk3, Etv3, XP_911724.4, Etv1, Etv4, Etv5, Etv2, Elf4, Elf1, Spi1, Elf2, Spib, Ehf, Elf5, Spic, Fev, Elf3, Irf4, Spdef, Irf8, Irf2
metacluster_1/pattern_4 # seqlets: 1849 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_5 # seqlets: 1473 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Creb1, Atf2, Creb5, Jdp2, Atf1, Crem, Mafb, Nfil3, Jun, Rxrb, Tef, Atf3, Dbp, Fosl1
metacluster_1/pattern_6 # seqlets: 1239 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Hlf, Cebpd, Cebpg, Ddit3, Atf4, Cebpe, Pou3f3, Pou5f1, Sox2
metacluster_1/pattern_7 # seqlets: 1051 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_8 # seqlets: 910 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_9 # seqlets: 847 SequenceContrib ScoresHyp_Contrib Scores	Fosb, Junb, Bach2, Fosl2, Fos, Jund, Nfe2l2, Nfe2, Batf, Bach1, Mafk, Mafg, Mafa, Maf, Maff
metacluster_1/pattern_10 # seqlets: 797 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_1/pattern_11 # seqlets: 722 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfec, Tfeb, Srebf1, Mitf, Arntl, Tfe3, Bhlhe40, Mlx, Clock, Arnt, Npas2, Creb3l2, Tcfl5, Bhlhe41, Xbp1, Max, Mycn, Mlxip, Arnt2
metacluster_1/pattern_12 # seqlets: 556 SequenceContrib ScoresHyp_Contrib Scores	Myog, Ascl2, Tcf21, Tal1, Myf5, Tcf12, Myod1, Ptf1a, Tcf3, Ascl1, Myf6, Atoh1, Olig2, Tcf7l1, Bhlha15, Neurod2, Neurod1, Neurog2, Tgif1, Lyl1, Msc, Nhlh2, Tcf4, Tfap4, Meis2, Snai2
metacluster_1/pattern_13 # seqlets: 523 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_1/pattern_14 # seqlets: 356 SequenceContrib ScoresHyp_Contrib Scores	Ebf1, Prdm16
metacluster_1/pattern_15 # seqlets: 343 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_16 # seqlets: 128 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_17 # seqlets: 127 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx1, Rfx2, Rfx4, Rfx6, Rfx7
metacluster_1/pattern_18 # seqlets: 104 SequenceContrib ScoresHyp_Contrib Scores	Pgr, Nr3c1, Ar, Esr1
metacluster_1/pattern_19 # seqlets: 84 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_20 # seqlets: 77 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_21 # seqlets: 47 SequenceContrib ScoresHyp_Contrib Scores