# Parameters
data_name = "wES;5th_Rhmbmr;E8.5;A;GEO"
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_160-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_160-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 19:15:29,029 [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	embryo_5th rhombomere(E8.5, WT)
Cell Group	ES cells and embryonic tissues
Experiment Name	ATAC
Experiment Group	GEO

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	246770	165567	10.1033	80580630	13784571	0.1711	8221235	0.102	32317717	0.4012
rep2	246770	165567	10.1086	85157340	15969392	0.1876	8961692	0.1053	34681301	0.4074

Metric	Value
auPRC	0.6487
Calibrated Recall at 50% FDR	0.207
Number of Positive Examples in Test Data	164981
Number of Negative Examples in Test Data	7905870
Imbalance Ratio in Test Data	0.0204
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 2463 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_1 # seqlets: 2062 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_2 # seqlets: 1933 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Sp4, Klf3, Sp1, E2f4, Klf7, Klf4, Klf6, Klf8, Klf12, Klf1, Egr1, Zbtb17, E2f1, Egr2, Klf5, Zfx, Zfp281, Sp5, Zfp740, Zbtb1
metacluster_0/pattern_3 # seqlets: 1653 SequenceContrib ScoresHyp_Contrib Scores	Sox3, Sox9, Sox4, Sox2, Sox17, Sox6, Nanog, Lef1, Foxd1, Sox12, Tcf7
metacluster_0/pattern_4 # seqlets: 1180 SequenceContrib ScoresHyp_Contrib Scores	Maz, Wt1, Klf15, Sall4, Srebf2, Bcl6, Rela, Zscan10
metacluster_0/pattern_5 # seqlets: 1146 SequenceContrib ScoresHyp_Contrib Scores	Nr2f6, Nr2c1, Rarb, Nr2f2, Rarg, Rxra, Nr2c2, Nr2f1, Pparg, Nr4a2, Rara, Nr1h3, Ppara, Rxrb, Rxrg, Hnf4a, Nr4a1, Esr1, Nr1i2, Nr5a2, Esrrg, Nr1h2, Esrra, Nr1h4, Thra, Nr2e1, Vdr, Nr1i3
metacluster_0/pattern_6 # seqlets: 923 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx1, Rfx6, Rfx4, Rfx7
metacluster_0/pattern_7 # seqlets: 863 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead2, Tead1
metacluster_0/pattern_8 # seqlets: 769 SequenceContrib ScoresHyp_Contrib Scores	Mafa, Tbx20
metacluster_0/pattern_9 # seqlets: 716 SequenceContrib ScoresHyp_Contrib Scores	Hoxa2, Hoxb4, Pdx1, Hoxa9, Meis1, Hoxc9, Evx1, Cdx4, Hoxb7, Pbx2, Hoxa1, Pbx1, Hoxb8, Pknox1
metacluster_0/pattern_10 # seqlets: 698 SequenceContrib ScoresHyp_Contrib Scores	Elf1, Gabpa, Fli1, Elk1, Elk4, Erg, Ets1, Elk3, Elf5, Fev, Etv5, Ehf, Etv4, Elf2, Etv1, Elf4, Etv6, XP_911724.4, Etv3, Etv2, Elf3, Spi1, Spdef, Spic, Stat3, Stat6, Spib
metacluster_0/pattern_11 # seqlets: 665 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Pbx3, Foxi1
metacluster_0/pattern_12 # seqlets: 596 SequenceContrib ScoresHyp_Contrib Scores	Ptf1a, Ascl2, Ascl1, Tcf3, Atoh1, Myf5, Tcf21, Myog, Bhlha15, Myod1, Olig2, Lyl1, Tcf7l1, Tal1, Tcf12, Tgif1, Meis2, Neurod1, Twist1, Tcf4, Neurod2, Myf6, Nhlh2, Meis3, Msc, Neurog2, Pknox2, Figla, Tfap4, Snai1
metacluster_0/pattern_13 # seqlets: 479 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_0/pattern_14 # seqlets: 464 SequenceContrib ScoresHyp_Contrib Scores	Foxd3, Foxj3, Foxj2, Foxc1, Gm5294, Foxc2, Foxa1, Foxj1, Foxa2, Foxa3, Foxo3, Foxp2, Foxk1, Foxg1, Foxb1, Foxl1, Foxp1, Foxo4, Foxl2, Foxq1, Foxm1, Sry, Foxo1, Sox11, Zfp105
metacluster_0/pattern_15 # seqlets: 430 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf7, Atf2, Crem, Jdp2, Creb5, Atf1, Atf3, Fosl2, Jun, Usf2, Nfil3, Mafb, Tef, Fosl1, Tfe3
metacluster_0/pattern_16 # seqlets: 403 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_17 # seqlets: 345 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfeb, Arntl, Mitf, Clock, Tfec, Srebf1, Arnt, Npas2, Bhlhe40, Mlx, Creb3l2, Mycn, Xbp1, Bhlhe41, Tcfl5, Max, Myc, Mlxip
metacluster_0/pattern_18 # seqlets: 329 SequenceContrib ScoresHyp_Contrib Scores	Hnf1b, Hnf1a
metacluster_0/pattern_19 # seqlets: 250 SequenceContrib ScoresHyp_Contrib Scores	Zic3, Zic2, Zic1
metacluster_0/pattern_20 # seqlets: 205 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Mxi1, Zfp42
metacluster_0/pattern_21 # seqlets: 205 SequenceContrib ScoresHyp_Contrib Scores	Ebf1, Prdm16
metacluster_0/pattern_22 # seqlets: 162 SequenceContrib ScoresHyp_Contrib Scores	Shox2, Lhx8, Arx, Neurog1, Lhx9, Uncx, Msx3, Prrx2, Gbx2, Lhx2, Lhx1, Vsx1, Rax, Lhx3, Nkx1-2, En1, Lbx2, Msx1, Lhx4, Bhlhe22, Lhx5, Alx1, Alx4, Isl1, Alx3, Lhx6, Evx2, Hoxc5, Isl2, Hoxd3, Prop1, Phox2a, Phox2b, Isx, Gbx1, Olig3, Twist2, Dlx5, Rhox6, Lmx1b, Dlx3, Emx2, Hoxb6, Cphx1, Otp, Pax6, Nr3c1, Dbx2, Pou1f1, Vax2, Nobox, Esx1, Hlx
metacluster_0/pattern_23 # seqlets: 158 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_0/pattern_24 # seqlets: 134 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_25 # seqlets: 118 SequenceContrib ScoresHyp_Contrib Scores	Mnx1, Hoxa3, Msx2, Hoxd1, Sebox, Prrx1, Vsx2, Vax1, Nkx1-1, Barhl2, Barhl1, Gsx2, En2, Tlx2, Dbx1, Hoxa5, Lmx1a, Hoxb3, Hmx2, Meox2, Hoxb5, Pax4, Noto, Hmx1, Barx2, Nkx3-1, Pax7, Bsx, Hoxc6, Dlx2, Barx1, Pou3f4, Dlx4, Pou4f3, Meox1, Hoxa6, Nkx6-1, Nkx6-3, Duxbl1, Pou2f1, Hoxa4, Nkx2-6, Nkx3-2, Arid3b, Dlx1, Hoxa7
metacluster_0/pattern_26 # seqlets: 77 SequenceContrib ScoresHyp_Contrib Scores	Gata2, Gata1, Gata6, Gata4, Gata3, Gata5
metacluster_0/pattern_27 # seqlets: 49 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_0/pattern_28 # seqlets: 39 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_29 # seqlets: 45 SequenceContrib ScoresHyp_Contrib Scores