# Parameters
data_name = "wES;RTN;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_235-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_235-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 19:33:22,672 [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 retina(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	211534	145771	11.9454	79534550	14919171	0.1876	10138437	0.1275	30420450	0.3826
rep2	211534	145771	7.7652	167475968	NA	NA	NA	NA	NA	NA

Metric	Value
auPRC	0.6772
Calibrated Recall at 50% FDR	0.154
Number of Positive Examples in Test Data	155919
Number of Negative Examples in Test Data	7914932
Imbalance Ratio in Test Data	0.0193
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 3096 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_1 # seqlets: 1891 SequenceContrib ScoresHyp_Contrib Scores	Lhx9, Lhx2, Prrx2, Shox2, Arx, Rax, Emx2, Lbx2, Alx1, Vsx2, Uncx, Alx4, Lhx8, Gbx1, En2, Pax6, Rhox6, Nkx1-2, Vsx1, Pou1f1, Gbx2, Evx1, Vax2, Gsx2, Nkx1-1, Alx3, Msx3, Nobox, Lhx4, Lhx3, Vax1, Lhx6, Noto, Hoxa1, Pdx1, Sebox, Pax7, Prop1, En1, Hoxa2, Hoxd3, Mnx1, Hoxb3, Prrx1, Hoxa3, Msx1, Otp, Pou2f2, Hoxa5, Hoxc5, Phox2b, Hoxd1, Esx1, Pou2f3, Pax4, Phox2a, Bsx, Msx2, Lmx1b, Pou3f2, Hoxb5, Pou3f1, Isx, Lmx1a, Barhl2, Meox1, Barhl1, Evx2, Nkx6-3, Hoxb4, Dlx5, Barx1, Isl1, Lhx1, Pou6f1, Pou2f1, Nkx6-1, Lhx5, Dlx2, Dbx2, Hoxc6, Isl2, Hlx, Barx2, Duxbl1, Dlx4, Pou3f4, Hoxb6, Hoxa4, Hoxa7, Dlx1, Hoxa6, Dlx3, Dbx1, Pou4f3, Tlx2, Hnf1b, Meox2, Hoxc10, Hoxb7, Hoxc4, Nanog, Hnf1a, Twist1, Hoxc8, Nkx3-2, A1JVI6_MOUSE, Arid3b, Hmx2, Hoxd13, Hmbox1, Hoxa13, Hoxc13, Nkx3-1, Hoxc9, Hoxb13
metacluster_0/pattern_2 # seqlets: 1483 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp4, Sp3, Klf3, Sp1, E2f4, Klf6, Klf7, Klf4, Klf1, Klf8, Klf12, Egr1, Zbtb17, E2f1, Egr2, Zfx, Klf5, Zfp281, Sp5
metacluster_0/pattern_3 # seqlets: 1249 SequenceContrib ScoresHyp_Contrib Scores	Atoh1, Neurod2, Olig2, Neurog2, Ptf1a, Neurod1, Bhlha15, Lyl1, Ascl1, Tal1, Ascl2, Myog, Tcf12, Myod1, Tcf21, Msc, Bhlhe22, Tcf3, Neurog1, Myf5, Tfap4, Msgn1, Myf6, Snai1, Tcf4, Figla, Myb, Tcf7l1, Snai2, Tgif1
metacluster_0/pattern_4 # seqlets: 1184 SequenceContrib ScoresHyp_Contrib Scores	Mxi1, Usf2, Rfx1
metacluster_0/pattern_5 # seqlets: 1157 SequenceContrib ScoresHyp_Contrib Scores	Sox4, Sox3, Sox2, Sox9, Sox17, Sox6, Lef1, Sox12, Tcf7, Foxd1
metacluster_0/pattern_6 # seqlets: 828 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Pbx3, Foxi1
metacluster_0/pattern_7 # seqlets: 821 SequenceContrib ScoresHyp_Contrib Scores	Maz, Wt1, Klf15, Zfp740, Rela, Sall4, Bcl6
metacluster_0/pattern_8 # seqlets: 720 SequenceContrib ScoresHyp_Contrib Scores	Nrf1, Zic3
metacluster_0/pattern_9 # seqlets: 672 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx4, Rfx6, Rfx7
metacluster_0/pattern_10 # seqlets: 660 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elf1, Elk1, Fli1, Elk4, Elk3, Erg, Ets1, Elf5, Etv5, Fev, Etv1, Elf2, Etv4, Etv6, Elf4, Ehf, XP_911724.4, Etv3, Elf3, Etv2, Spi1, Spdef, Spic
metacluster_0/pattern_11 # seqlets: 417 SequenceContrib ScoresHyp_Contrib Scores	Pax5
metacluster_0/pattern_12 # seqlets: 362 SequenceContrib ScoresHyp_Contrib Scores	Mbd2, Tfap2b
metacluster_0/pattern_13 # seqlets: 351 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_14 # seqlets: 346 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_0/pattern_15 # seqlets: 306 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_16 # seqlets: 285 SequenceContrib ScoresHyp_Contrib Scores	Ebf1, Prdm16
metacluster_0/pattern_17 # seqlets: 271 SequenceContrib ScoresHyp_Contrib Scores	Rorc, Pparg, Rora, Nr1d2
metacluster_0/pattern_18 # seqlets: 251 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf7, Atf2, Jdp2, Creb5, Crem, Atf1, Mafb, Atf3, Fosl2, Tfe3, Nfil3, Fosl1
metacluster_0/pattern_19 # seqlets: 218 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_20 # seqlets: 216 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfec, Tfeb, Arntl, Srebf1, Mitf, Bhlhe40, Clock, Arnt, Mlx, Srebf2, Npas2, Creb3l2, Tcfl5, Max, Bhlhe41, Six1, Mycn, Myc, Nr1h4, Hlf, Xbp1, Rxrg, Mlxip
metacluster_0/pattern_21 # seqlets: 202 SequenceContrib ScoresHyp_Contrib Scores	Tfap2c
metacluster_0/pattern_22 # seqlets: 201 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_23 # seqlets: 179 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_24 # seqlets: 164 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_25 # seqlets: 107 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_26 # seqlets: 105 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_0/pattern_27 # seqlets: 98 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead2, Tead1
metacluster_0/pattern_28 # seqlets: 80 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_29 # seqlets: 76 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_0/pattern_30 # seqlets: 65 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_31 # seqlets: 41 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_32 # seqlets: 37 SequenceContrib ScoresHyp_Contrib Scores