# Parameters
data_name = "KDNY;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_223-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_223-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 19:30:22,500 [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	Kidney(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	200603	140321	8.9682	104649434	24593043	0.235	10374464	0.0992	42918556	0.4102
rep2	200603	140321	15.4059	23694000	4350531	0.1837	2443775	0.1032	9676433	0.4086

Metric	Value
auPRC	0.5502
Calibrated Recall at 50% FDR	0.248
Number of Positive Examples in Test Data	133263
Number of Negative Examples in Test Data	7937588
Imbalance Ratio in Test Data	0.0165
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 3814 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 3546 SequenceContrib ScoresHyp_Contrib Scores	Hnf4g, Nr1h3, Rxra, Hnf4a, Nr2f6, Nr2c2, Rxrb, Ppara, Nr2f1, Pparg, Nr4a2, Nr2c1, Nr5a2, Rara, Rarg, Rarb, Nr5a1, Nr2e3, Nr2f2, Esrra, Esrrb
metacluster_1/pattern_2 # seqlets: 2920 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Sp1, Klf3, E2f4, Klf6, Klf7, Egr1, Klf4, Klf8, Klf1, Klf12, Zbtb17, Egr2, Sp5, E2f1, Zfp281, Klf5, Zfx, Wt1, Egr3, Ptf1a
metacluster_1/pattern_3 # seqlets: 1994 SequenceContrib ScoresHyp_Contrib Scores	Hnf1b, Hnf1a
metacluster_1/pattern_4 # seqlets: 1911 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_1/pattern_5 # seqlets: 1771 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Elk1, Gabpa, Elk4, Fli1, Elk3, Etv5, Etv2, Etv4, Fev, Etv1, Etv6, Elf2, Etv3, XP_911724.4, Spi1, Elf1, Elf4, Elf5, Ehf, Spib, Spdef, Elf3, Spic, Irf8, Irf4
metacluster_1/pattern_6 # seqlets: 1058 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Pbx3, Foxi1
metacluster_1/pattern_7 # seqlets: 1033 SequenceContrib ScoresHyp_Contrib Scores	Tfe3, Usf1, Tfeb, Usf2, Arntl, Npas2, Mitf, Clock, Bhlhe40, Arnt, Tfec, Srebf1, Mlx, Bhlhe41, Creb3l2, Xbp1, Hey2, Max, Srebf2, Myc, Tcfl5, Mlxip, Arnt2, Mycn, Hes1, Hes2, Hes5, Epas1
metacluster_1/pattern_8 # seqlets: 849 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_9 # seqlets: 703 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf7, Atf1, Creb5, Atf2, Jdp2, Crem, Mafb, Jun, Nfil3, Tef, Dbp, Fosl1, Gmeb2, Atf3, Junb, Cebpb, Hlf
metacluster_1/pattern_10 # seqlets: 488 SequenceContrib ScoresHyp_Contrib Scores	Bach2, Mafk, Nfe2l2, Nfe2, Maff, Mafa, Mafg, Bach1, Maf, Fosl2, Batf, Fosb, Jund, Fos, Cic
metacluster_1/pattern_11 # seqlets: 398 SequenceContrib ScoresHyp_Contrib Scores	Tead2, Tead1, Tead4
metacluster_1/pattern_12 # seqlets: 394 SequenceContrib ScoresHyp_Contrib Scores	Pou5f1, Sox2, Nanog, Cebpg, Cebpd, Cebpe, Pou2f2, Cebpa, Pou3f3, Ddit3, Atf4
metacluster_1/pattern_13 # seqlets: 366 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_1/pattern_14 # seqlets: 266 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_15 # seqlets: 248 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_16 # seqlets: 221 SequenceContrib ScoresHyp_Contrib Scores	Pax5, Pax6
metacluster_1/pattern_17 # seqlets: 210 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf7, Stat1, Prdm1, Stat2, Irf9, Irf5, Irf3, Batf3
metacluster_1/pattern_18 # seqlets: 198 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_19 # seqlets: 148 SequenceContrib ScoresHyp_Contrib Scores	Hoxa9, Cdx4, Evx1, Meis1, Hoxc9, Pdx1, Hoxb4, Pbx2, Hoxb7, Hoxa2, Hoxa10, Cdx1, Hoxb8
metacluster_1/pattern_20 # seqlets: 115 SequenceContrib ScoresHyp_Contrib Scores	Rfx1, Rfx2, Rfx3, Rfx4, Rfx6, Rfx7
metacluster_1/pattern_21 # seqlets: 104 SequenceContrib ScoresHyp_Contrib Scores	Grhl2, Tcfcp2l1
metacluster_1/pattern_22 # seqlets: 76 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_23 # seqlets: 73 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_24 # seqlets: 62 SequenceContrib ScoresHyp_Contrib Scores	Foxg1, Foxc1, Foxc2, Foxd3, Foxa3, Foxa1, Foxk1, Foxb1, Foxl1, Foxj3, Foxa2, Foxp2, Foxj2, Gm5294, Foxo1, Foxo3, Foxd1, Foxp1, Foxl2, Foxm1, Sry, Foxo4