# Parameters
data_name = "ENDRM_ESD;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_149-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_149-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 19:13:24,498 [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	ES_derived Definitive Endoderm
Cell Group	Cancer or Immortalized cells
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	160378	104327	8.7431	63663067	6597843	0.1037	5524322	0.0868	22045535	0.3464
rep2	160378	104327	7.6392	84169366	8687990	0.1032	6728956	0.08	29254511	0.3476

Metric	Value
auPRC	0.6679
Calibrated Recall at 50% FDR	0.25
Number of Positive Examples in Test Data	104839
Number of Negative Examples in Test Data	7966012
Imbalance Ratio in Test Data	0.013
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 3180 SequenceContrib ScoresHyp_Contrib Scores	Sp3, Sp2, Klf3, Sp1, Sp4, Klf6, Klf15, Zfx, Klf1, Wt1, Maz, Sp5, Egr1, Zbtb17, E2f4, Klf5, Klf4, Klf7, Klf8, Egr2, Klf12, Zfp281, Usf2, Tfap2c, E2f1, Rela, Ctcfl, Mxi1, E2f7, Sall4, Rfx1
metacluster_1/pattern_1 # seqlets: 3168 SequenceContrib ScoresHyp_Contrib Scores	Ctcf
metacluster_1/pattern_2 # seqlets: 2525 SequenceContrib ScoresHyp_Contrib Scores	Zic3, Zic2, Zic1
metacluster_1/pattern_3 # seqlets: 2259 SequenceContrib ScoresHyp_Contrib Scores	Zfp335, Myc
metacluster_1/pattern_4 # seqlets: 1695 SequenceContrib ScoresHyp_Contrib Scores	Pou5f1, Nanog, Pou2f2, Sox2, Pou2f1
metacluster_1/pattern_5 # seqlets: 1463 SequenceContrib ScoresHyp_Contrib Scores	Sox4, Sox3, Sox6, Sry, Sox12, Sox14, Sox7, Sox17, Sox8, Sox18, Sox11, Lef1, Sox21, Sox5, Sox10, Sox15, Sox9, Sox30
metacluster_1/pattern_6 # seqlets: 1137 SequenceContrib ScoresHyp_Contrib Scores	Foxa1, Foxa2, Foxm1, Foxd1, Foxa3, Foxc1, Foxd3, Foxb1, Foxc2, Foxl1, Foxj2, Foxg1, Foxk1, Foxl2, Foxp2, Foxj3, Gm5294, Foxo1, Foxp1, Foxo3, Foxj1, Foxq1
metacluster_1/pattern_7 # seqlets: 963 SequenceContrib ScoresHyp_Contrib Scores	Otx2, Crx, Pitx3, Pitx2, Pitx1, Obox1, Dmbx1, Otx1, Q8VHG7_MOUSE, Obox5, Obox3, Gsc, Obox6
metacluster_1/pattern_8 # seqlets: 844 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_9 # seqlets: 734 SequenceContrib ScoresHyp_Contrib Scores	Atf1, Atf7, Creb1, Atf2, Creb5, Jdp2, Crem, Tfec, Srebf1, Bhlhe40, Usf1, Mitf, Rxrb, Tfe3, Mlx, Tfeb, Srebf2, Dbp, Arntl, Creb3l2, Hlf, Nfil3, Atf3, Jun, Clock, Tef, Xbp1, Mafb
metacluster_1/pattern_10 # seqlets: 619 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_11 # seqlets: 477 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx6, Rfx7
metacluster_1/pattern_12 # seqlets: 435 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_1/pattern_13 # seqlets: 407 SequenceContrib ScoresHyp_Contrib Scores	Gata2, Tal1, Gata1, Gata4, Gata6, Gata3, Gata5, Mecom
metacluster_1/pattern_14 # seqlets: 352 SequenceContrib ScoresHyp_Contrib Scores	Fosl2, Fosb, Batf, Junb, Fosl1, Jund, Fos, Bach2, Mafk, Nfe2, Nfe2l2, Bach1, Mafg, Mafa, Maff, Maf, Nfatc1
metacluster_1/pattern_15 # seqlets: 331 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elk1, Ets1, Fli1, Erg, Elk4, Elf1, Etv2, Etv1, Elk3, Etv4, Etv5, Ehf, Etv3, Etv6, XP_911724.4, Fev, Elf4, Elf2, Elf5, Elf3, Spdef, Spi1, Nkx2-2
metacluster_1/pattern_16 # seqlets: 279 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_17 # seqlets: 229 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead2, Tead1
metacluster_1/pattern_18 # seqlets: 170 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_19 # seqlets: 117 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_1/pattern_20 # seqlets: 51 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_21 # seqlets: 47 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_22 # seqlets: 47 SequenceContrib ScoresHyp_Contrib Scores	Grhl2
metacluster_1/pattern_23 # seqlets: 39 SequenceContrib ScoresHyp_Contrib Scores