# Parameters
data_name = "wES;limb;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_257-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_257-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 19:38:33,110 [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	mixed embryonic mouse limb(E11.5)
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	226433	156045	6.7951	174399423	NA	NA	NA	NA	NA	NA
rep2	226433	156045	9.5655	113243454	19356599	0.171	11666780	0.103	43459593	0.3838

Metric	Value
auPRC	0.6701
Calibrated Recall at 50% FDR	0.196
Number of Positive Examples in Test Data	134282
Number of Negative Examples in Test Data	7936569
Imbalance Ratio in Test Data	0.0166
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 3047 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_1 # seqlets: 2073 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_2 # seqlets: 1769 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Sp1, Sp4, Klf3, Klf4, E2f4, Klf6, Zbtb17, Klf7, Klf5, Sp5, Egr1, Klf8, Klf12, Egr2, Wt1, Zfp281, Klf1, Maz, E2f1, Klf15, Srebf2, Egr3, Zfp740, Sall4
metacluster_0/pattern_3 # seqlets: 1639 SequenceContrib ScoresHyp_Contrib Scores	Lhx2, Lhx9, Hoxa1, Lbx2, Gsx2, Pax6, Vax2, Hoxa5, Hoxa3, Shox2, Vsx1, Vax1, Nobox, Hoxd3, Hoxc5, Emx2, Prrx2, Hoxb3, Alx1, Msx3, Arx, Hoxb5, Nkx6-3, Evx1, Lhx6, Alx4, Gbx2, Gbx1, Pdx1, Hoxa2, Vsx2, Bsx, Nkx1-2, Nkx6-1, Uncx, En1, Meox1, Sebox, En2, Nkx1-1, Lhx8, Hoxc6, Lhx3, Rax, Hoxa6, Rhox6, Hoxb7, Hoxb4, Lhx4, Hoxc10, Mnx1, Dlx5, Pou1f1, Lmx1a, Meox2, Hoxc8, Hoxa7, Alx3, Noto, Hoxd1, Msx2, Dlx4, Msx1, Prop1, Dlx2, Otp, Prrx1, Barx1, Pax7, Hoxa4, Hoxd8, Hoxa9, Barx2, Nanog, Hoxb6, Dlx1, Barhl1, Pou2f2, Pou6f1, Hoxa10, Pou3f1, Pou3f2, Isl1, Esx1, Hoxc9, Hoxd10, Hoxd13, Pax4, Hoxa13, Hoxc13, Cdx1, Isl2, Hlx, Barhl2, Dbx1, Hoxb13, Hoxb8, Hoxc4, Phox2a, Phox2b, Dlx3, Isx, Duxbl1, Tlx2, Lmx1b, Dbx2, Hmx2, Hoxd9, Hoxa11, Pou4f3, Nkx3-2, Lhx5, Hoxd11, Hoxb9, Pou2f1, Cdx2, Hoxc11, Pou2f3, Nkx3-1, Hmx1, Lhx1, Evx2, A1JVI6_MOUSE, Pou3f4, Hoxc12, Hnf1b, Arid3b, Nkx2-3, Hnf1a, Nkx2-1, Nkx2-6, Hmbox1, Nkx2-5, Arid3a
metacluster_0/pattern_4 # seqlets: 1375 SequenceContrib ScoresHyp_Contrib Scores	Fli1, Erg, Ets1, Gabpa, Elk1, Elk4, Etv5, Elk3, Etv2, Etv4, Fev, Etv6, Etv1, XP_911724.4, Etv3, Elf1, Elf2, Spi1, Elf4, Ehf, Elf5, Spdef, Elf3, Spib, Spic
metacluster_0/pattern_5 # seqlets: 1354 SequenceContrib ScoresHyp_Contrib Scores	Meis1, Cdx4, Pbx1
metacluster_0/pattern_6 # seqlets: 1157 SequenceContrib ScoresHyp_Contrib Scores	Twist1, Olig2, Atoh1, Ascl1, Tal1, Ptf1a, Ascl2, Msc, Myf5, Tcf12, Myod1, Tcf21, Neurod1, Bhlha15, Lyl1, Myog, Neurog1, Neurod2, Bhlhe22, Tcf3, Tcf7l1, Tfap4, Tcf4, Figla, Neurog2, Myf6, Snai1, Tgif1, Nhlh2, Twist2
metacluster_0/pattern_7 # seqlets: 952 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_8 # seqlets: 871 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_0/pattern_9 # seqlets: 836 SequenceContrib ScoresHyp_Contrib Scores	Rela, Bcl6, E2f6
metacluster_0/pattern_10 # seqlets: 674 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Pbx3, Foxi1
metacluster_0/pattern_11 # seqlets: 660 SequenceContrib ScoresHyp_Contrib Scores	Rfx1, Rfx2, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_0/pattern_12 # seqlets: 613 SequenceContrib ScoresHyp_Contrib Scores	Sox9, Sox3, Sox17, Sox4, Sox10, Sox2, Sox6
metacluster_0/pattern_13 # seqlets: 601 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_14 # seqlets: 515 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead2, Tead1
metacluster_0/pattern_15 # seqlets: 456 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfx, Mxi1, Zfp42, Usf2
metacluster_0/pattern_16 # seqlets: 345 SequenceContrib ScoresHyp_Contrib Scores	Tcf7l2, Lef1, Tcf7, Nr2f6, Nr2c2, Rxra
metacluster_0/pattern_17 # seqlets: 310 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_18 # seqlets: 273 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Atf7, Crem, Atf1, Jdp2, Creb5, Atf3, Usf1, Jun, Fosl2
metacluster_0/pattern_19 # seqlets: 261 SequenceContrib ScoresHyp_Contrib Scores	Tfe3, Tfeb, Arntl, Tfec, Mitf, Clock, Srebf1, Arnt, Bhlhe40, Mlx, Npas2, Mycn, Myc, Max, Creb3l2, Tcfl5, Rxrg, Bhlhe41, Rxrb, Xbp1
metacluster_0/pattern_20 # seqlets: 204 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_21 # seqlets: 157 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic
metacluster_0/pattern_22 # seqlets: 142 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_0/pattern_23 # seqlets: 63 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_24 # seqlets: 47 SequenceContrib ScoresHyp_Contrib Scores