# Parameters
data_name = "Mammary;A;CL"
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_58-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_58-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 18:53:06,375 [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	Mammary tissue
Cell Group	Other Tissues
Experiment Name	ATAC
Experiment Group	Casellas Lab

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	67951	35799	7.8519	14580227	516737	0.0355	1100752	0.0756	4879976	0.3351
rep2	67951	35799	6.7582	35160853	1476217	0.042	2423212	0.069	11746475	0.3343

Metric	Value
auPRC	0.6427
Calibrated Recall at 50% FDR	0.189
Number of Positive Examples in Test Data	41634
Number of Negative Examples in Test Data	8029217
Imbalance Ratio in Test Data	0.0052
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 3181 SequenceContrib ScoresHyp_Contrib Scores	Fli1, Gabpa, Elk4, Sp2, Erg, Sp3, Ets1, Elf1, Sp1, Zfx, Elk1, Fev, Elk3, Etv4, Etv1, Usf2, Mxi1, Ehf, Etv5, Klf3, Etv2, Elf5, Etv6, Etv3, XP_911724.4, Zbtb17, Wt1, Elf3, Elf4, Mbd2, E2f3, Rfx1, Elf2, Ctcfl, Klf6, Nr1h4, Spdef, Mecp2, Sp4
metacluster_0/pattern_1 # seqlets: 2529 SequenceContrib ScoresHyp_Contrib Scores	E2f4, Egr1, Klf7, Klf4, Klf8, Klf12, Klf1, Sp5, Egr2
metacluster_0/pattern_2 # seqlets: 1754 SequenceContrib ScoresHyp_Contrib Scores	Klf5, Zfp281, E2f1, Maz, Srebf2, Klf15, Sall4, Zbtb1
metacluster_0/pattern_3 # seqlets: 1645 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_4 # seqlets: 1530 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_5 # seqlets: 1496 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_0/pattern_6 # seqlets: 1478 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf1, Creb5, Jdp2, Atf7, Crem, Atf2, Tfe3, Tfec, Srebf1, Rxrb, Usf1, Tfeb, Bhlhe40, Arntl, Mlx, Mitf, Xbp1, Clock, Tef, Nfil3, Atf3, Jun, Mafb, Creb3l2, Dbp
metacluster_0/pattern_7 # seqlets: 1281 SequenceContrib ScoresHyp_Contrib Scores	Ctcf
metacluster_0/pattern_8 # seqlets: 1205 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_0/pattern_9 # seqlets: 790 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_0/pattern_10 # seqlets: 720 SequenceContrib ScoresHyp_Contrib Scores	Sox9, Sox10, Sox2, Sox3, Sox6, Sox17, Sox4, Sox12
metacluster_0/pattern_11 # seqlets: 504 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Hlf, Cebpd, Cebpg, Ddit3, Atf4, Cebpe, Pou3f3, Pou5f1
metacluster_0/pattern_12 # seqlets: 501 SequenceContrib ScoresHyp_Contrib Scores	Zfp335
metacluster_0/pattern_13 # seqlets: 298 SequenceContrib ScoresHyp_Contrib Scores	Grhl2, Tcfcp2l1
metacluster_0/pattern_14 # seqlets: 224 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_0/pattern_15 # seqlets: 222 SequenceContrib ScoresHyp_Contrib Scores	Irf7, Irf8, Irf9, Irf4, Stat2, Prdm1, Irf1, Irf5, Irf2, Stat1, Irf6, Irf3
metacluster_0/pattern_16 # seqlets: 194 SequenceContrib ScoresHyp_Contrib Scores	Junb, Fosl2, Fosl1, Fos, Jund, Fosb, Batf, Bach2, Bach1, Nfe2, Nfe2l2, Mafa
metacluster_0/pattern_17 # seqlets: 121 SequenceContrib ScoresHyp_Contrib Scores	Tead2, Tead4, Tead1
metacluster_0/pattern_18 # seqlets: 47 SequenceContrib ScoresHyp_Contrib Scores	Rela, Nfkb1, Relb, Nfkb2
metacluster_0/pattern_19 # seqlets: 43 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_20 # seqlets: 34 SequenceContrib ScoresHyp_Contrib Scores