# Parameters
data_name = "ROD_PHT_RCPTR_RTN;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_151-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_151-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 19:13:44,671 [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	WT rod photoreceptors,retina
Cell Group	Neural Cells and 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	114373	93937	17.7255	32340084	9922794	0.307	8149326	0.2521	11612219	0.3592
rep2	114373	93937	18.2174	30511208	9603997	0.3149	7859807	0.2577	11004043	0.3608

Metric	Value
auPRC	0.6111
Calibrated Recall at 50% FDR	0.175
Number of Positive Examples in Test Data	95251
Number of Negative Examples in Test Data	7975600
Imbalance Ratio in Test Data	0.0118
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 7919 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_1 # seqlets: 3082 SequenceContrib ScoresHyp_Contrib Scores	Crx, Otx2, Otx1, Dmbx1, Pax7, Obox3, Obox6, Pitx1, Obox1, Pitx3, Gsc, Vsx2
metacluster_0/pattern_2 # seqlets: 1756 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Sp4, Sp1, Klf3, Klf6, E2f4, Klf4, Sp5, Egr1, Zbtb17, Klf7, Klf5, Egr2, Klf8, Klf12, Wt1, Zfp281, Maz, Klf1, E2f1, Klf15, Egr3
metacluster_0/pattern_3 # seqlets: 1730 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Fli1, Ets1, Elk4, Elf1, Elk3, Erg, Elk1, Etv4, Etv1, Fev, Etv5, Ehf, Etv2, Etv3, Etv6, XP_911724.4, Elf5, Elf4, Elf2, Elf3, Spdef, Spi1, Mbd2, E2f3
metacluster_0/pattern_4 # seqlets: 1710 SequenceContrib ScoresHyp_Contrib Scores	Nrf1, Zfx
metacluster_0/pattern_5 # seqlets: 1539 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_6 # seqlets: 1015 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_7 # seqlets: 840 SequenceContrib ScoresHyp_Contrib Scores	Hes7, Hes1
metacluster_0/pattern_8 # seqlets: 814 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_9 # seqlets: 798 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Mxi1
metacluster_0/pattern_10 # seqlets: 622 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Usf2, Atf2, Atf1, Atf7, Jdp2, Crem, Creb5, Atf3, Usf1, Rfx1, Fosl2, Hlf
metacluster_0/pattern_11 # seqlets: 558 SequenceContrib ScoresHyp_Contrib Scores	Tfe3, Tfeb, Arntl, Tfec, Mitf, Clock, Srebf1, Bhlhe40, Arnt, Mlx, Npas2, Srebf2, Tcfl5, Mycn, Max, Creb3l2, Bhlhe41, Myc, Xbp1
metacluster_0/pattern_12 # seqlets: 309 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_13 # seqlets: 255 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_0/pattern_14 # seqlets: 159 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2
metacluster_0/pattern_15 # seqlets: 150 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_16 # seqlets: 100 SequenceContrib ScoresHyp_Contrib Scores	Tfap2b, Tfap2c
metacluster_0/pattern_17 # seqlets: 99 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6, Nr1h4
metacluster_0/pattern_18 # seqlets: 88 SequenceContrib ScoresHyp_Contrib Scores	Stat4
metacluster_0/pattern_19 # seqlets: 85 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_20 # seqlets: 49 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_21 # seqlets: 46 SequenceContrib ScoresHyp_Contrib Scores	Stat1, Stat2, Irf1, Irf2, Irf3, Irf4, Irf8, Spib, Irf7, Prdm1, Irf5, Irf9, Rela, Irf6