# Parameters
data_name = "aB;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_137-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_137-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 19:11:11,488 [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	Act B cell
Cell Group	B 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	171004	137135	11.9732	54039089	14343880	0.2655	8072211	0.1494	21135559	0.3913
rep2	171004	137135	8.1664	83443705	15461384	0.1853	9562503	0.1146	31408589	0.3765

Metric	Value
auPRC	0.575
Calibrated Recall at 50% FDR	0.229
Number of Positive Examples in Test Data	134975
Number of Negative Examples in Test Data	7935876
Imbalance Ratio in Test Data	0.0167
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 5908 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 5799 SequenceContrib ScoresHyp_Contrib Scores	Spib, Spi1, Etv2, Etv4, Ets1, Irf8, Irf4, Spic, Erg, Etv6, Ehf, Fli1, Elf3, Etv3, Elk1, Gabpa, XP_911724.4, Elf4, Elf1, Elk4, Elk3, Elf2, Etv1, Etv5, Elf5, Prdm1, Irf3, Irf2, Fev, Spdef, Irf1
metacluster_1/pattern_2 # seqlets: 2208 SequenceContrib ScoresHyp_Contrib Scores	Stat2, Stat1, Irf7, Irf9, Zscan10, Irf5
metacluster_1/pattern_3 # seqlets: 1639 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Sp1, Klf3, E2f4, Klf6, Klf7, Egr1, Klf4, Klf1, Klf8, Klf12, Zbtb17, Egr2, E2f1, Sp5, Zfp281, Zfx, Klf5
metacluster_1/pattern_4 # seqlets: 1341 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_5 # seqlets: 1224 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_6 # seqlets: 1198 SequenceContrib ScoresHyp_Contrib Scores	Batf, Batf3, Jdp2, Jund, Fosb, Atf3, Junb, Bach2, Jun
metacluster_1/pattern_7 # seqlets: 957 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf1, Atf2, Creb5, Creb1, Crem, Dbp, Nfil3, Hlf, Cebpb, Tef, Cebpa, Rxrb, Mafb, Tfec, Srebf1, Gmeb2, Bhlhe40, Cebpd, Creb3l2, Fosl1, Cebpg
metacluster_1/pattern_8 # seqlets: 617 SequenceContrib ScoresHyp_Contrib Scores	Nfkb1, Rela, Nfkb2, Relb, Rel
metacluster_1/pattern_9 # seqlets: 613 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Usf2, Tfeb, Arntl, Mitf, Tfe3, Clock, Mlx, Arnt, Npas2, Srebf2, Tcfl5, Bhlhe41, Xbp1, Arnt2, Max, Mlxip
metacluster_1/pattern_10 # seqlets: 609 SequenceContrib ScoresHyp_Contrib Scores	Hes7, Hes1
metacluster_1/pattern_11 # seqlets: 608 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2
metacluster_1/pattern_12 # seqlets: 584 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx1, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_13 # seqlets: 526 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_14 # seqlets: 491 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Wt1, Maz, Mxi1
metacluster_1/pattern_15 # seqlets: 479 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Cbfb, Runx2, Runx3
metacluster_1/pattern_16 # seqlets: 394 SequenceContrib ScoresHyp_Contrib Scores	Ebf1
metacluster_1/pattern_17 # seqlets: 319 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_18 # seqlets: 303 SequenceContrib ScoresHyp_Contrib Scores	Hnf1b, Hnf1a
metacluster_1/pattern_19 # seqlets: 289 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_20 # seqlets: 229 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_21 # seqlets: 176 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_22 # seqlets: 176 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_23 # seqlets: 150 SequenceContrib ScoresHyp_Contrib Scores	Pax5, Pax6
metacluster_1/pattern_24 # seqlets: 136 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_25 # seqlets: 125 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_26 # seqlets: 39 SequenceContrib ScoresHyp_Contrib Scores	Rest