# Parameters
data_name = "KDNY;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_222-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_222-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 (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	266660	187208	7.6326	168465251	NA	NA	NA	NA	NA	NA
rep2	331666	227156	7.3972	178440198	NA	NA	NA	NA	NA	NA

Metric	Value
auPRC	0.628
Calibrated Recall at 50% FDR	0.242
Number of Positive Examples in Test Data	162348
Number of Negative Examples in Test Data	1838873
Imbalance Ratio in Test Data	0.0811
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 3460 SequenceContrib ScoresHyp_Contrib Scores	Sp1, Sp3, Sp4, Zbtb17, Sp2, Klf3, E2f4, Egr1, Sp5, Klf6, Zfp281, Klf7, Klf8, Egr2, Wt1, Klf12, Maz, Klf15, E2f1, Klf5, Klf4, Klf1, Sall4, Zfp740, Nhlh1, Egr3, Ptf1a, E2f7
metacluster_1/pattern_1 # seqlets: 3271 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_2 # seqlets: 2465 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Etv4, Etv2, Fli1, Elk4, Gabpa, Elk1, Etv5, Etv6, Elk3, Spi1, Elf2, Fev, Etv3, XP_911724.4, Etv1, Spib, Elf1, Elf4, Ehf, Elf5, Elf3, Spic, Spdef, Irf8, Irf4, Zscan10, Stat6
metacluster_1/pattern_3 # seqlets: 1691 SequenceContrib ScoresHyp_Contrib Scores	Cdx4, Evx1, Hoxa9, Meis1, Hoxc9, Pdx1, Hoxb4, Hoxb7, Hoxa10, Hoxa2, Hoxb8, Cdx1, Pbx2, Cdx2, Hoxd13
metacluster_1/pattern_4 # seqlets: 1555 SequenceContrib ScoresHyp_Contrib Scores	Nfic, Nfia, Nfib
metacluster_1/pattern_5 # seqlets: 1426 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead2, Tead1
metacluster_1/pattern_6 # seqlets: 1263 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_1/pattern_7 # seqlets: 1149 SequenceContrib ScoresHyp_Contrib Scores	Foxd3, Foxj3, Gm5294, Foxj2, Foxc1, Foxd1, Foxc2, Foxo4, Foxj1, Foxk1, Foxo3, Foxp2, Foxa3, Foxa2, Foxl1, Foxa1, Foxg1, Sry, Foxl2, Foxq1, Foxp1, Foxb1, Sox11, Foxo1, Sox21, Zfp105, Foxm1, Sox3, Sox18, Sox7
metacluster_1/pattern_8 # seqlets: 1124 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_9 # seqlets: 977 SequenceContrib ScoresHyp_Contrib Scores	Twist1, Olig2, Tal1, Lyl1, Tcf3, Myog, Figla, Tcf21, Tfap4, Atoh1, Ascl2, Myf5, Tcf12, Neurod1, Snai1, Msc, Myf6, Tgif1, Bhlha15, Ascl1, Tcf4, Neurod2
metacluster_1/pattern_10 # seqlets: 649 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Creb5, Creb1, Jdp2, Crem, Atf1, Cebpb, Nfil3, Dbp, Jun, Cebpa, Tef, Hlf, Ddit3, Fosl1, Gmeb2, Mafb, Atf4, Cebpd, Atf3, Jund, Cebpg, Junb, Fosl2, Srebf1, Tfec, Esr2, Rora, Mlx, XP_002726925.1
metacluster_1/pattern_11 # seqlets: 600 SequenceContrib ScoresHyp_Contrib Scores	Batf, Fosb, Fos, Bach2, Bach1, Nfe2l2, Nfe2, Mafk, Mafa
metacluster_1/pattern_12 # seqlets: 553 SequenceContrib ScoresHyp_Contrib Scores	Hnf1b, Hnf1a
metacluster_1/pattern_13 # seqlets: 494 SequenceContrib ScoresHyp_Contrib Scores	Hes7, Hes1
metacluster_1/pattern_14 # seqlets: 434 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Pbx3, Foxi1
metacluster_1/pattern_15 # seqlets: 383 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Usf2, Tfeb, Arntl, Mitf, Tfe3, Bhlhe40, Clock, Arnt, Npas2, Creb3l2, Srebf2, Tcfl5, Xbp1, Bhlhe41, Mycn, Max, Mlxip, Myc
metacluster_1/pattern_16 # seqlets: 350 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx1, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_17 # seqlets: 314 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_18 # seqlets: 272 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfx, Zfp42, Mxi1
metacluster_1/pattern_19 # seqlets: 179 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_20 # seqlets: 126 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf7, Prdm1, Stat2, Irf9, Stat1, Irf3
metacluster_1/pattern_21 # seqlets: 111 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_22 # seqlets: 55 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_23 # seqlets: 51 SequenceContrib ScoresHyp_Contrib Scores	Nr2f6, Rxra, Nr2c2, Rxrb, Nr2e3, Nr2f1, Tcf7, Nr2f2, Nr4a2, Hnf4g, Hnf4a, Rarb, Pparg, Nr2e1, Nr2c1, Nr1h3, Rara, Lef1, Tcf7l2, Ppara, Nr5a2, Esrra, Esrrg, Rarg