# Parameters
data_name = "wES;WHL_BRN;E14.5;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_253-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_253-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 19:37:07,470 [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	Whole Brain(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	319574	219919	8.4636	208202441	NA	NA	NA	NA	NA	NA
rep2	262168	182314	22.934	20295499	4764941	0.2348	3005932	0.1481	9315329	0.4591

Metric	Value
auPRC	0.6387
Calibrated Recall at 50% FDR	0.225
Number of Positive Examples in Test Data	168638
Number of Negative Examples in Test Data	7902213
Imbalance Ratio in Test Data	0.0209
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 2462 SequenceContrib ScoresHyp_Contrib Scores	Lhx2, Lhx9, Pax6, Vsx2, Shox2, Prrx2, Lbx2, Alx1, Vsx1, Arx, Gbx1, Alx4, Nobox, Hoxa1, Emx2, Uncx, Sebox, Msx3, Lhx6, Gsx2, Gbx2, Lhx8, Rax, Vax2, Hoxd3, Rhox6, Vax1, Lhx4, Lhx3, Nkx1-2, En1, Pou1f1, Hoxa2, En2, Alx3, Evx1, Noto, Hoxa5, Nkx1-1, Pdx1, Hoxa3, Hoxb3, Lmx1a, Nkx6-3, Bsx, Pax7, Hoxc6, Prrx1, Mnx1, Prop1, Hoxb5, Hoxc5, Nkx6-1, Otp, Meox1, Msx1, Msx2, Phox2a, Esx1, Hoxd1, Dlx5, Phox2b, Pax4, Pou3f1, Pou2f2, Barhl2, Lmx1b, Dlx4, Dlx2, Hoxa6, Barhl1, Pou3f2, Meox2, Hoxb4, Dbx1, Hoxa7, Hlx, Hoxb7, Isx, Hoxc10, Tlx2, Lhx5, Duxbl1, Barx1, Pou6f1, Dbx2, Barx2, Dlx1, Hoxc9, Hmx2, Pou2f1, Hoxc8, Evx2, Isl1, Pou2f3, Lhx1, Isl2, Hoxd13, Hoxa4, Nanog, Pou4f3, Dlx3, Nkx3-2, Hnf1b, Nkx3-1, Arid3b, A1JVI6_MOUSE, Hoxa13, Hoxc13, Hnf1a, Hoxb6, Hoxa9, Pou3f4, Hoxd8, Hoxb13, Hoxd10, Hoxa10, Cdx1, Hoxc4, Hoxd9, Hmx1, Hmbox1, Cdx2, Hoxa11, Nkx2-3, Hoxb8, Hoxd11, Hoxb9, Nkx2-6, Nkx2-1
metacluster_1/pattern_1 # seqlets: 2372 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_2 # seqlets: 2114 SequenceContrib ScoresHyp_Contrib Scores	Sp3, Sp1, Sp2, Sp4, Klf3, Zbtb17, Sp5, Klf4, Klf5, Wt1, Klf6, E2f4, Zfp281, Egr1, Klf7, Maz, Klf8, E2f1, Egr2, Klf12, Klf15, Sall4, Srebf2, Klf1, Egr3
metacluster_1/pattern_3 # seqlets: 2036 SequenceContrib ScoresHyp_Contrib Scores	Sox9, Sox3, Sox4, Sox2, Lef1, Sox17, Tcf7l2, Sox6, Tcf7l1, Tcf7, Pou5f1
metacluster_1/pattern_4 # seqlets: 2031 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_1/pattern_5 # seqlets: 1694 SequenceContrib ScoresHyp_Contrib Scores	Ptf1a, Ascl1, Myog, Ascl2, Myod1, Tcf12, Atoh1, Tcf3, Myf6, Bhlha15, Tal1, Snai2, Tgif1, Myf5, Neurod2, Tcf4, Nhlh1, Olig2, Neurod1, Neurog2, Lyl1, Nhlh2
metacluster_1/pattern_6 # seqlets: 1362 SequenceContrib ScoresHyp_Contrib Scores	Bhlhe22, Tcf21, Neurog1, Msc, Msgn1, Twist2
metacluster_1/pattern_7 # seqlets: 1258 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_8 # seqlets: 939 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_9 # seqlets: 911 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx1, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_10 # seqlets: 756 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Jdp2, Creb5, Atf1, Creb1, Crem, Tfec, Srebf1, Mlx, Bhlhe40, Mitf, Atf3, Nfil3, Dbp, Tfe3, Jun, Usf1, Hlf, Tef, Usf2, Creb3l2, Cebpb, Rxrb, Cebpa, Xbp1, Tfeb, Fosl2, Mafb, Arntl, Fosl1, Clock
metacluster_1/pattern_11 # seqlets: 675 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_12 # seqlets: 488 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elk1, Fli1, Elk4, Ets1, Erg, Elk3, Etv5, Fev, Elf1, Etv4, Etv1, Etv6, Etv3, XP_911724.4, Etv2, Elf2, Ehf, Elf5, Spi1, Elf4, Spdef, Elf3, Spic, Spib
metacluster_1/pattern_13 # seqlets: 483 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Pbx3, Foxi1
metacluster_1/pattern_14 # seqlets: 369 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_15 # seqlets: 222 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfx, Zfp42, Mxi1
metacluster_1/pattern_16 # seqlets: 210 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2, Trp63
metacluster_1/pattern_17 # seqlets: 135 SequenceContrib ScoresHyp_Contrib Scores	Sox1
metacluster_1/pattern_18 # seqlets: 109 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_19 # seqlets: 97 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_20 # seqlets: 61 SequenceContrib ScoresHyp_Contrib Scores	Tfap2a, Prdm16, Tfap2e, Sp110, Ebf1, Tfap2b
metacluster_1/pattern_21 # seqlets: 40 SequenceContrib ScoresHyp_Contrib Scores