# Parameters
data_name = "wES;LVR;E11.5;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_225-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_225-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 19:30:49,042 [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	Liver(E14.5)
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	86429	50597	15.8503	32048018	4011287	0.1252	3993082	0.1247	11747021	0.3667
rep2	86429	50597	15.4017	30545341	4637723	0.1519	4338846	0.1421	11030209	0.3613

Metric	Value
auPRC	0.5917
Calibrated Recall at 50% FDR	0.183
Number of Positive Examples in Test Data	62305
Number of Negative Examples in Test Data	8008546
Imbalance Ratio in Test Data	0.0077
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 7174 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 3859 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Klf3, Sp3, Sp1, Klf4, Klf7, Klf12, Klf8, E2f4, Klf1, Klf6, Egr1, Egr2, Klf5, Zbtb17, E2f1, Zfp740, Zfp281, Sp5, Egr3, Zfx, Zbtb1, Sall4
metacluster_1/pattern_2 # seqlets: 1779 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_3 # seqlets: 1711 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elk1, Fli1, Elk4, Ets1, Erg, Elf1, Etv5, Elk3, Etv2, Fev, Etv4, Etv1, Etv6, Elf2, Etv3, XP_911724.4, Ehf, Spi1, Elf4, Elf5, Elf3, Spdef, Spib
metacluster_1/pattern_4 # seqlets: 1528 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_5 # seqlets: 1071 SequenceContrib ScoresHyp_Contrib Scores	Tal1, Gata1, Gata5, Gata6, Gata4, Gata2, Gata3
metacluster_1/pattern_6 # seqlets: 916 SequenceContrib ScoresHyp_Contrib Scores	Gli3
metacluster_1/pattern_7 # seqlets: 835 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Wt1, Maz, Usf2, Mxi1
metacluster_1/pattern_8 # seqlets: 755 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_9 # seqlets: 667 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpd, Cebpa, Cebpg, Cebpe, Dbp, Nfil3, Hlf, Tef, Atf4, Ddit3, Jun, Jdp2, Creb1, Gmeb2, Jund, Atf2, Atf7, Crem, Atf1, Fosl1
metacluster_1/pattern_10 # seqlets: 594 SequenceContrib ScoresHyp_Contrib Scores	Creb5, Atf3, Fosl2, Usf1, Rfx1, Rxrb
metacluster_1/pattern_11 # seqlets: 560 SequenceContrib ScoresHyp_Contrib Scores	Tfe3, Tfec, Arntl, Tfeb, Mitf, Bhlhe40, Srebf1, Clock, Arnt, Mlx, Srebf2, Npas2, Tcfl5, Bhlhe41, Mycn, Max, Creb3l2, Rxrg, Myc, Mlxip
metacluster_1/pattern_12 # seqlets: 555 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_13 # seqlets: 553 SequenceContrib ScoresHyp_Contrib Scores	Nfe2, Nfe2l2, Bach2, Bach1, Mafk, Mafa, Mafb, Mafg, Maff, Maf, Fosb, Junb, Batf, Fos
metacluster_1/pattern_14 # seqlets: 372 SequenceContrib ScoresHyp_Contrib Scores	Hnf1b, Hnf1a
metacluster_1/pattern_15 # seqlets: 324 SequenceContrib ScoresHyp_Contrib Scores	Nr2f6, Rxra, Nr2c2, Nr1h3, Ppara, Nr2f1, Hnf4g, Pparg, Hnf4a, Nr2e3, Nr4a2, Nr5a2, Nr2c1, Nr5a1, Esrrb, Rara, Esrra, Rarg
metacluster_1/pattern_16 # seqlets: 250 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_17 # seqlets: 235 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_18 # seqlets: 181 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_19 # seqlets: 163 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_20 # seqlets: 144 SequenceContrib ScoresHyp_Contrib Scores	Mbd2
metacluster_1/pattern_21 # seqlets: 134 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfic, Nfib
metacluster_1/pattern_22 # seqlets: 122 SequenceContrib ScoresHyp_Contrib Scores	Stat2, Stat1, Irf1, Irf2, Irf4, Irf5, Irf7, Irf9, Prdm1, Irf8, Irf3, Irf6