# Parameters
data_name = "Hnd_BRN;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_247-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_247-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 19:35:32,576 [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 mouse hindbrain(P0)
Cell Group	Neural Cells and 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	249697	164021	10.1766	142326235	25577355	0.1797	13780738	0.0968	59455460	0.4178
rep2	249697	164021	9.8996	123297728	18290330	0.1484	11286842	0.0916	47000731	0.3813

Metric	Value
auPRC	0.684
Calibrated Recall at 50% FDR	0.193
Number of Positive Examples in Test Data	141568
Number of Negative Examples in Test Data	7929283
Imbalance Ratio in Test Data	0.0175
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 3274 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 2291 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_2 # seqlets: 1799 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_1/pattern_3 # seqlets: 1742 SequenceContrib ScoresHyp_Contrib Scores	Atoh1, Neurod2, Olig2, Neurog2, Neurod1, Ptf1a, Lyl1, Bhlha15, Ascl1, Ascl2, Tal1, Myog, Tcf12, Myod1, Tcf21, Bhlhe22, Msc, Tcf3, Msgn1, Neurog1, Myf5, Myf6, Tfap4, Myb, Snai2, Tcf4, Tgif1, Snai1
metacluster_1/pattern_4 # seqlets: 1451 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Sp1, Klf3, Sp4, Klf6, Klf1, Wt1, E2f4, Klf4, Sp5, Klf7, Klf5, Egr1, Zbtb17, Klf8, Klf12, Zfx, Klf15, Maz, Egr2, Zfp281, E2f1, E2f7, Srebf2
metacluster_1/pattern_5 # seqlets: 1316 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx1, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_6 # seqlets: 1204 SequenceContrib ScoresHyp_Contrib Scores	Pou2f1, Lhx2, Prrx2, Lhx9, Arx, Lbx2, Shox2, Pax6, Uncx, Rhox6, Otp, Alx1, Alx4, Vsx1, Lhx4, Rax, Esx1, Pax7, Prrx1, Lhx8, Alx3, Pou1f1, Pou2f3, Pou3f1, Vsx2, Lhx3, Noto, Prop1, Hoxa2, Nkx1-2, Arid3b, Lhx6, Emx2, Nobox, Hoxc5, En1, Lhx5, Hoxa1, Lmx1a, Pou3f2, Msx3, Pou2f2, Gbx1, En2, Lmx1b, Pax4, Vax2, Phox2a, Phox2b, Nkx6-3, Gsx2, Msx1, Vax1, Hoxd3, Gbx2, Lhx1, Evx1, Pdx1, Nkx6-1, Isx, Hoxd1, Dbx1, Hoxb3, Sebox, Hoxa5, Hoxa3, Nkx1-1, Evx2, Tlx2, Pou4f3, Hlx, Msx2, Hoxc6, Hoxb5, Bsx, Meox1, Mnx1, Dlx5, Phf21a, Dbx2, Hoxd13, Meox2, Hoxb4, Isl2, Pou3f4, Hnf1a, Hnf1b, Pou6f1, Hoxc10, Isl1, Barx1, Barhl2, Dlx4, Hmbox1, Barhl1, Duxbl1, Hoxa6, Hoxb7, Dlx2, Hoxa4, Hoxb6, Dlx3, Hoxa7
metacluster_1/pattern_7 # seqlets: 821 SequenceContrib ScoresHyp_Contrib Scores	Bcl6, Rela, Sall4, Zfp740, E2f6, Zscan10
metacluster_1/pattern_8 # seqlets: 761 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Pbx3, Foxi1
metacluster_1/pattern_9 # seqlets: 712 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_10 # seqlets: 686 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Fli1, Elk1, Elk4, Erg, Ets1, Elf1, Elk3, Etv5, Fev, Etv2, Etv4, Etv1, Etv6, Etv3, XP_911724.4, Elf2, Ehf, Spi1, Elf5, Elf4, Elf3, Spdef, Spib
metacluster_1/pattern_11 # seqlets: 592 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Creb5, Atf1, Creb1, Jdp2, Crem, Jun, Mafb, Nfil3, Dbp, Cebpb, Tef, Hlf, Cebpa, Fosl1, Atf3, Gmeb2, Jund, Srebf1, Rxrb, Tfec, Ddit3, Junb, Fosl2, Cebpd, Atf4, Cebpg, Mlx, Bhlhe40
metacluster_1/pattern_12 # seqlets: 561 SequenceContrib ScoresHyp_Contrib Scores	Sox4, Sox3, Sox9, Sox17, Sox6, Sox2, Nanog, Lef1, Tcf7, Sry, Foxd1, Sox12
metacluster_1/pattern_13 # seqlets: 405 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Usf2, Mxi1
metacluster_1/pattern_14 # seqlets: 315 SequenceContrib ScoresHyp_Contrib Scores	Tfeb, Usf1, Arntl, Mitf, Tfe3, Clock, Arnt, Npas2, Tcfl5, Creb3l2, Bhlhe41, Xbp1, Mlxip, Arnt2
metacluster_1/pattern_15 # seqlets: 304 SequenceContrib ScoresHyp_Contrib Scores	Zic3, Zic2, Zic1
metacluster_1/pattern_16 # seqlets: 263 SequenceContrib ScoresHyp_Contrib Scores	Ebf1, Prdm16
metacluster_1/pattern_17 # seqlets: 204 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_18 # seqlets: 65 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_19 # seqlets: 75 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_20 # seqlets: 43 SequenceContrib ScoresHyp_Contrib Scores