# Parameters
data_name = "Adipose;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_233-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_233-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 19:33:03,037 [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	Adipose tissue
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	120040	74713	8.4684	18395832	2749250	0.1496	1478077	0.0804	8058325	0.4383
rep2	120040	74713	6.4891	21405869	3061423	0.1431	1459835	0.0682	9272048	0.4335

Metric	Value
auPRC	0.4905
Calibrated Recall at 50% FDR	0.274
Number of Positive Examples in Test Data	88896
Number of Negative Examples in Test Data	7981955
Imbalance Ratio in Test Data	0.011
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 3587 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Nfil3, Cebpd, Dbp, Cebpg, Ddit3, Hlf, Tef, Atf4, Cebpe, Atf2, Creb1, Atf1
metacluster_0/pattern_1 # seqlets: 2580 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_2 # seqlets: 2178 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_0/pattern_3 # seqlets: 2175 SequenceContrib ScoresHyp_Contrib Scores	Tfap2a, Tfap2c, Tfap2e, Tfap2b
metacluster_0/pattern_4 # seqlets: 1844 SequenceContrib ScoresHyp_Contrib Scores	Trp73, Trp63, Trp53
metacluster_0/pattern_5 # seqlets: 1533 SequenceContrib ScoresHyp_Contrib Scores	Egr2, Egr3, Egr1, Gli3, Klf1, Gli1, Zbtb17, Zfp281, Klf4
metacluster_0/pattern_6 # seqlets: 1529 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf6, Klf7, Klf8, Klf12, Sp5, E2f1, Klf5
metacluster_0/pattern_7 # seqlets: 1081 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_8 # seqlets: 903 SequenceContrib ScoresHyp_Contrib Scores	Bach2, Jund, Atf3, Fos, Fosl1, Jun, Nfe2l2, Fosb, Junb, Fosl2, Nfe2, Bach1, Jdp2, Batf, Mafk, Mafa, Mafb, Maf, Mafg, Maff
metacluster_0/pattern_9 # seqlets: 813 SequenceContrib ScoresHyp_Contrib Scores	Grhl2
metacluster_0/pattern_10 # seqlets: 768 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_11 # seqlets: 660 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_12 # seqlets: 643 SequenceContrib ScoresHyp_Contrib Scores	Elf1, Gabpa, Elk1, Fli1, Elk4, Elk3, Erg, Ets1, Elf5, Etv5, Fev, Etv1, Etv4, Elf2, Etv6, Elf4, Ehf, Etv3, XP_911724.4, Elf3, Spi1, Etv2, Spdef
metacluster_0/pattern_13 # seqlets: 360 SequenceContrib ScoresHyp_Contrib Scores	Hes7, Hes1
metacluster_0/pattern_14 # seqlets: 354 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_0/pattern_15 # seqlets: 260 SequenceContrib ScoresHyp_Contrib Scores	Pitx2, Pitx3, Q8VHG7_MOUSE, Pitx1, Obox5, Otx1, Otx2, Crx, Dmbx1, Obox3, Obox1, Gsc
metacluster_0/pattern_16 # seqlets: 172 SequenceContrib ScoresHyp_Contrib Scores	Yy1, Taf1, Zfx, Zfp42, Wt1
metacluster_0/pattern_17 # seqlets: 160 SequenceContrib ScoresHyp_Contrib Scores	Usf2, Usf1, Tfe3, Tfeb, Tfec, Arntl, Mitf, Srebf1, Bhlhe40, Clock, Arnt, Mlx, Mxi1, Srebf2, Npas2, Rfx1, Tcfl5, Atf7, Mycn, Bhlhe41, Creb3l2, Mbd2, Rxrg, Max, Tal1, Myc, Crem, Rxrb
metacluster_0/pattern_18 # seqlets: 87 SequenceContrib ScoresHyp_Contrib Scores	Ar, Pgr, Nr3c1
metacluster_0/pattern_19 # seqlets: 83 SequenceContrib ScoresHyp_Contrib Scores	Sox9, Sox10, Sox6, Sox3, Sox2, Sox4, Sox5, Sox12, Sox14, Msgn1, Sox8, Sox7, Sox18, Sox11, Sry, Sox21, Tcf7l2, Sox17, Lef1
metacluster_0/pattern_20 # seqlets: 77 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_0/pattern_21 # seqlets: 54 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_22 # seqlets: 50 SequenceContrib ScoresHyp_Contrib Scores	Hoxc9, Cdx4, Hoxa9, Meis1, Evx1, Hoxb4, Hoxa2, Cdx2, Pdx1, Cdx1, Hoxa10, Hoxa11, Hoxb8, Hoxb9, Hoxa7, Hoxd10, Hoxd8, Hoxc12, Hoxc8
metacluster_0/pattern_23 # seqlets: 50 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_24 # seqlets: 36 SequenceContrib ScoresHyp_Contrib Scores	Gata4, Gata1, Gata3, Gata2