# Parameters
data_name = "wES;3rd_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_156-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_156-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 19:14:39,073 [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_3rd 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	254819	172632	11.0765	77606002	17229865	0.2221	8943817	0.1153	33455656	0.4312
rep2	254819	172632	11.7289	70970845	16402610	0.2312	8452533	0.1191	30682132	0.4324

Metric	Value
auPRC	0.6627
Calibrated Recall at 50% FDR	0.191
Number of Positive Examples in Test Data	196482
Number of Negative Examples in Test Data	7874369
Imbalance Ratio in Test Data	0.0243
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 2824 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_1 # seqlets: 2100 SequenceContrib ScoresHyp_Contrib Scores	Sox3, Sox9, Sox4, Sox2, Sox17, Sox6, Nanog, Lef1, Foxd1, Tcf7, Sox12, Sry
metacluster_0/pattern_2 # seqlets: 1811 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Sp1, Klf3, Klf6, Sp4, Klf15, Klf1, Wt1, Maz, Sp5, Zfx, Egr1, Zbtb17, Klf7, E2f4, Klf4, Egr2, Klf8, Klf12, Klf5, Zfp281, Usf2, Rela, Tfap2c, E2f1, Nr1h4, Mxi1, E2f7, E2f6, Egr3, Tfap2b
metacluster_0/pattern_3 # seqlets: 1609 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_4 # seqlets: 1280 SequenceContrib ScoresHyp_Contrib Scores	Zfp740, Sall4, Bcl6, Srebf2, Zscan10
metacluster_0/pattern_5 # seqlets: 947 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx1, Rfx4, Rfx6, Rfx7
metacluster_0/pattern_6 # seqlets: 880 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead2, Tead1
metacluster_0/pattern_7 # seqlets: 807 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_0/pattern_8 # seqlets: 802 SequenceContrib ScoresHyp_Contrib Scores	Zic3, Zic2, Zic1
metacluster_0/pattern_9 # seqlets: 762 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_10 # seqlets: 684 SequenceContrib ScoresHyp_Contrib Scores	Tcf3, Ascl1, Myog, Ascl2, Ptf1a, Myod1, Tcf12, Atoh1, Tcf7l1, Bhlha15, Myf5, Tal1, Lyl1, Olig2, Nhlh2, Tcf4, Tgif1, Tcf21, Myf6, Twist1, Neurod2, Neurod1, Neurog2, Meis2, Figla, Snai1, Snai2, Msc, Meis3, Tfap4, Pknox2, Nhlh1
metacluster_0/pattern_11 # seqlets: 593 SequenceContrib ScoresHyp_Contrib Scores	Tfap2a, Prdm16, Ebf1
metacluster_0/pattern_12 # seqlets: 592 SequenceContrib ScoresHyp_Contrib Scores	Otx2, Crx, Pitx3, Pitx1, Pitx2, Gsc, Dmbx1, Otx1, Q8VHG7_MOUSE, Obox5, Obox1, Obox3
metacluster_0/pattern_13 # seqlets: 547 SequenceContrib ScoresHyp_Contrib Scores	Foxd3, Foxj3, Foxa2, Foxc1, Foxj1, Foxc2, Foxj2, Foxa3, Foxa1, Gm5294, Foxo3, Foxp2, Foxb1, Foxk1, Foxl1, Foxg1, Foxp1, Foxo4, Foxl2, Foxq1, Foxm1, Foxo1
metacluster_0/pattern_14 # seqlets: 395 SequenceContrib ScoresHyp_Contrib Scores	Nr2f2, Nr2c1, Nr1h3, Nr4a2, Nr2f1, Rarb, Nr2c2, Nr2f6, Rarg, Pparg, Nr1i2, Vdr, Rara, Ppara, Nr1i3, Rxra, Rxrb, Nr4a1
metacluster_0/pattern_15 # seqlets: 330 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elk1, Fli1, Elk4, Ets1, Erg, Elk3, Etv5, Etv4, Etv1, Fev, Etv6, Elf1, Etv3, XP_911724.4, Etv2, Spi1, Elf4, Elf5, Elf2, Ehf, Spdef, Spib, Spic, Elf3
metacluster_0/pattern_16 # seqlets: 312 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_17 # seqlets: 273 SequenceContrib ScoresHyp_Contrib Scores	Hnf4g, Hnf4a, Nr2e3, Rxrg, Nr5a2, Tcf7l2, Insm1, Nr5a1, Esrrb
metacluster_0/pattern_18 # seqlets: 227 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfec, Tfeb, Mitf, Arntl, Srebf1, Tfe3, Bhlhe40, Clock, Mlx, Arnt, Npas2, Creb3l2, Tcfl5, Atf1, Xbp1, Bhlhe41, Mycn, Max, Mlxip, Hes1, Myc, Hlf
metacluster_0/pattern_19 # seqlets: 222 SequenceContrib ScoresHyp_Contrib Scores	Pbx1, Pknox1, Tgif2, Meis1
metacluster_0/pattern_20 # seqlets: 183 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Pou5f1, Pou2f1
metacluster_0/pattern_21 # seqlets: 173 SequenceContrib ScoresHyp_Contrib Scores	Lhx3, Lhx4, Lhx1, Lhx5, Prrx2, Uncx, Shox2, Vsx1, Arx, Pax6, Alx1, Lhx8, Lhx2, Alx3, Alx4, Lhx9, Prop1, Lmx1a, Rhox6, Pou1f1, Lmx1b, Lbx2, En1, Esx1, Hoxc5, Otp, Cphx1, Msx1, Rax, Lhx6, Msx3, Sebox, Phox2b, Dbx1, Pou3f4, Tlx2, Prrx1, Hlx, Phox2a, Pax4, Vsx2, Dbx2, Meox2, Isx, Gbx1, Arid3a, Arid3b, Gbx2, Emx2, En2, Hoxa1, Isl2, Duxbl1, Hoxc6, Nkx1-2, Mnx1, Hoxd3, Hoxa3, Pdx1, Vax2, Pou3f2, Isl1, Vax1, Dlx5, Hoxd1, Noto, Hoxc9, Gsx2, Pou4f3, Hnf1a, Evx2, Nobox, Hoxa2, Pou3f1, Hnf1b, Msx2, Hoxb4, Evx1, Nkx6-3, Dlx3, Hoxb5, Pou2f3
metacluster_0/pattern_22 # seqlets: 155 SequenceContrib ScoresHyp_Contrib Scores	Neurog1
metacluster_0/pattern_23 # seqlets: 139 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_24 # seqlets: 130 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Atf7, Crem, Jdp2, Creb5, Atf3, Fosl2, Fosl1
metacluster_0/pattern_25 # seqlets: 110 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_0/pattern_26 # seqlets: 99 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_0/pattern_27 # seqlets: 71 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_28 # seqlets: 64 SequenceContrib ScoresHyp_Contrib Scores	Bach2, Nfe2l2, Nfe2, Bach1, Jund, Mafa, Junb, Fos, Fosb, Mafk, Maff, Jun, Maf, Batf
metacluster_0/pattern_29 # seqlets: 52 SequenceContrib ScoresHyp_Contrib Scores	Pax5
metacluster_0/pattern_30 # seqlets: 47 SequenceContrib ScoresHyp_Contrib Scores