# Parameters
data_name = "wES;MSDRM;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_243-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_243-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 19:35:02,801 [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	Mesoderm(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	223065	135205	12.641	79596446	15841763	0.1991	9747881	0.1225	34199054	0.4298
rep2	223065	135205	21.8567	38391254	9365640	0.2441	5845734	0.1523	17656752	0.4601

Metric	Value
auPRC	0.6581
Calibrated Recall at 50% FDR	0.193
Number of Positive Examples in Test Data	147593
Number of Negative Examples in Test Data	7923258
Imbalance Ratio in Test Data	0.0183
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 2909 SequenceContrib ScoresHyp_Contrib Scores	Hoxa9, Meis1, Evx1, Cdx4, Hoxc9, Pdx1, Hoxb4, Hoxb7, Pbx2, Hoxa2, Hoxb8, Hoxa10, Cdx1
metacluster_0/pattern_1 # seqlets: 2582 SequenceContrib ScoresHyp_Contrib Scores	Olig2, Neurod1, Atoh1, Tcf21, Twist1, Msc, Neurod2, Neurog2, Lyl1, Ptf1a, Ascl1, Ascl2, Myog, Myf5, Tal1, Tfap4, Bhlha15, Neurog1, Tcf3, Bhlhe22, Myf6, Tcf12, Myod1, Figla, Msgn1, Twist2, Tcf4, Meis2, Snai1, Tgif1
metacluster_0/pattern_2 # seqlets: 2146 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_3 # seqlets: 1595 SequenceContrib ScoresHyp_Contrib Scores	Sox3, Sox9, Sox2, Sox4, Sox17, Sox6, Tcf7
metacluster_0/pattern_4 # seqlets: 1321 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Sp1, Klf3, Sp4, Klf4, Zbtb17, Klf5, Klf6, Sp5, E2f4, Egr1, Klf7, Wt1, Klf8, Klf12, Zfp281, Maz, Egr2, E2f1, Klf15, Srebf2, Sall4, Klf1, Egr3, Zfp740
metacluster_0/pattern_5 # seqlets: 995 SequenceContrib ScoresHyp_Contrib Scores	Hoxa4, Hoxa5, Hoxc5, Hoxa3, Hoxb5, Hoxb3, Hoxd3, Hoxc4, Lhx2, Hoxa6, Vax1, Vax2, Hoxa1, Hoxa7, Lhx9, Hoxc10, Meox1, Nkx6-1, Hoxc8, Gsx2, Hoxd8, Prrx2, Lbx2, Nanog, Nkx6-3, Bsx, Alx1, Shox2, Nobox, Lhx4, Hoxc6, Uncx, Alx4, Barx2, Isl2, Vsx1, Arx, Emx2, Pax6, Msx1, Otp, Pou4f3, Barx1, Msx3, Lmx1a, Gbx1, Nkx1-2, Isx, Noto, Lhx3, Isl1, Evx2, Hoxd10, Lhx6, Hoxb9, Mnx1, Hoxa11, Esx1, Nkx1-1, Sebox, Gbx2, Hoxd9, Pou2f1, Phox2a, Pou1f1, Hlx, Rax, Tlx2, Hoxb6, Dbx1, Meox2, Cdx2, Phox2b, Alx3, Hoxc11, Pou6f1, Hoxd11, Dlx2, Pou3f1, Vsx2, Pou3f2, Lhx8, Rhox6, Lhx5, Arid3b, Dlx4, Prop1, Pou2f2, Hoxd1, Dlx5, En2, Prrx1, Hoxa13, Hoxc12, Hnf1b, Lmx1b, Hoxd13, Barhl1, Dlx1, Hoxc13, Pou2f3, Pou3f4, Lhx1, Hoxb13, Dlx3, Msx2, Pax7, En1, Arid3a, Hmx1, Dbx2, Duxbl1, Hnf1a, Nkx3-2
metacluster_0/pattern_6 # seqlets: 977 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_7 # seqlets: 927 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead2, Tead1
metacluster_0/pattern_8 # seqlets: 918 SequenceContrib ScoresHyp_Contrib Scores	Ebf1, Prdm16
metacluster_0/pattern_9 # seqlets: 903 SequenceContrib ScoresHyp_Contrib Scores	Rela, Bcl6, E2f6, Zscan10
metacluster_0/pattern_10 # seqlets: 802 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Fli1, Elk4, Gabpa, Elk1, Etv2, Etv5, Etv4, Elk3, Fev, Etv1, Etv6, Etv3, XP_911724.4, Elf2, Spi1, Elf1, Elf4, Ehf, Elf5, Spdef, Elf3, Spib, Spic, Irf8, Irf4
metacluster_0/pattern_11 # seqlets: 758 SequenceContrib ScoresHyp_Contrib Scores	Nr2f2, Nr2f6, Rxra, Hnf4a, Rxrb, Nr2c2, Nr1h3, Rarg, Rora, Rara, Nr1i3, Rxrg, Hnf4g, Esr2, Nr2c1, Nr1h4, Rarb, Nr5a2, Nr1i2, Ppara, Esrrg, Nr2f1, Esrrb, Nr4a2, Esrra, Lef1, Tcf7l2
metacluster_0/pattern_12 # seqlets: 743 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx1, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_0/pattern_13 # seqlets: 675 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfya, Nfyc, Pbx3, Foxi1
metacluster_0/pattern_14 # seqlets: 640 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_0/pattern_15 # seqlets: 602 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_16 # seqlets: 402 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfec, Usf2, Tfeb, Tfe3, Mitf, Srebf1, Bhlhe40, Arntl, Mlx, Clock, Arnt, Npas2, Creb3l2, Tcfl5, Atf1, Bhlhe41, Mycn, Max, Myc, Dbp, Mlxip, Hlf, Xbp1, Creb1
metacluster_0/pattern_17 # seqlets: 397 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Creb5, Jdp2, Crem, Nfil3, Jun, Atf3, Mafb, Tef, Cebpb, Cebpa, Fosl1, Fosl2
metacluster_0/pattern_18 # seqlets: 238 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic
metacluster_0/pattern_19 # seqlets: 176 SequenceContrib ScoresHyp_Contrib Scores	Foxd3, Foxj3, Foxj2, Gm5294, Foxc2, Foxc1, Foxd1, Foxj1, Foxa2, Foxa1, Foxa3, Foxk1, Foxo3, Foxg1, Foxl1, Foxp2, Foxb1, Foxo4, Foxp1, Foxl2, Foxq1, Sry, Foxm1, Foxo1, Sox11, Zfp105, Sox21
metacluster_0/pattern_20 # seqlets: 175 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_21 # seqlets: 93 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_0/pattern_22 # seqlets: 82 SequenceContrib ScoresHyp_Contrib Scores	Rest