# Parameters
data_name = "ES;E14;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_217-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_217-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 19:29:38,122 [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	mouse embryonic stem cells E14
Cell Group	ES cells and embryonic 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	194220	128137	14.2709	31820369	8002521	0.2516	4692729	0.1476	13505631	0.4247
rep2	194220	128137	9.269	22925543	2544654	0.1111	2308087	0.1008	8925542	0.3897

Metric	Value
auPRC	0.6432
Calibrated Recall at 50% FDR	0.178
Number of Positive Examples in Test Data	139855
Number of Negative Examples in Test Data	7930996
Imbalance Ratio in Test Data	0.0173
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 6575 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 5269 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Klf3, Sp3, Sp1, Klf4, Klf7, Klf8, Klf12, Klf1, Klf6, E2f4, Egr1, Egr2, Klf5, Zbtb17, Zfp281, Sp5, E2f1, Egr3, Sall4, Zfp740, Zfx, Zbtb1
metacluster_1/pattern_2 # seqlets: 1810 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfya, Nfyc, Foxi1, Pbx3
metacluster_1/pattern_3 # seqlets: 1702 SequenceContrib ScoresHyp_Contrib Scores	Pou5f1, Nanog, Sox2, Pou2f2, Lef1, Pou2f1
metacluster_1/pattern_4 # seqlets: 1226 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_5 # seqlets: 1196 SequenceContrib ScoresHyp_Contrib Scores	Sox30, Sox3, Sry, Sox4, Sox6, Sox12, Sox14, Sox5
metacluster_1/pattern_6 # seqlets: 1177 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_7 # seqlets: 840 SequenceContrib ScoresHyp_Contrib Scores	Zic2, Zic3
metacluster_1/pattern_8 # seqlets: 721 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfe3, Tfeb, Usf2, Tfec, Arntl, Srebf1, Mitf, Bhlhe40, Clock, Arnt, Mlx, Srebf2, Npas2, Jdp2, Tcfl5, Hlf, Mycn, Creb5, Max, Bhlhe41, Creb1, Atf7, Myc, Creb3l2, Atf1, Atf2, Xbp1
metacluster_1/pattern_9 # seqlets: 666 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elf1, Elk1, Fli1, Elk4, Elk3, Erg, Ets1, Elf5, Etv5, Fev, Etv1, Etv4, Elf2, Etv6, Elf4, Ehf, XP_911724.4, Etv3, Spi1, Elf3, Etv2, Spdef
metacluster_1/pattern_10 # seqlets: 574 SequenceContrib ScoresHyp_Contrib Scores	Nfe2, Bach2, Nfe2l2, Bach1, Mafk, Mafa, Mafb, Mafg, Maff, Jun, Maf, Atf3, Fosb, Batf, Fosl2, Junb, Fosl1, Jund, Fos
metacluster_1/pattern_11 # seqlets: 457 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_12 # seqlets: 426 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_13 # seqlets: 386 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead2, Tead1
metacluster_1/pattern_14 # seqlets: 364 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx1, Rfx2, Rfx4, Rfx6, Rfx7
metacluster_1/pattern_15 # seqlets: 350 SequenceContrib ScoresHyp_Contrib Scores	Rara, Rxrg, Rxra, Esrrb, Nr5a2, Esrrg, Rarg, Esrra, Nr5a1, Rxrb, Nr2c2, Hnf4g, Nr2f6, Hnf4a, Nr2c1, Nr4a2
metacluster_1/pattern_16 # seqlets: 308 SequenceContrib ScoresHyp_Contrib Scores	Yy1, Taf1, Zfp42
metacluster_1/pattern_17 # seqlets: 275 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_18 # seqlets: 201 SequenceContrib ScoresHyp_Contrib Scores	Stat3, Stat4
metacluster_1/pattern_19 # seqlets: 200 SequenceContrib ScoresHyp_Contrib Scores	Tcfcp2l1, Rora
metacluster_1/pattern_20 # seqlets: 197 SequenceContrib ScoresHyp_Contrib Scores	Crem, Wt1, Mxi1, Nfil3
metacluster_1/pattern_21 # seqlets: 185 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_22 # seqlets: 181 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_1/pattern_23 # seqlets: 176 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_24 # seqlets: 115 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_25 # seqlets: 90 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_26 # seqlets: 78 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_27 # seqlets: 88 SequenceContrib ScoresHyp_Contrib Scores	Grhl2
metacluster_1/pattern_28 # seqlets: 60 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_29 # seqlets: 30 SequenceContrib ScoresHyp_Contrib Scores