# Parameters
data_name = "ILC3_AbxGRMFree;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_112-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_112-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 19:05:28,129 [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	ILC3_AbxGermFree
Cell Group	Other Immune 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	129986	103738	13.5265	23566898	3953903	0.1679	3074458	0.1306	8341960	0.3542
rep2	129986	103738	16.3446	22661367	10099210	0.446	5829083	0.2574	9620935	0.4249

Metric	Value
auPRC	0.5876
Calibrated Recall at 50% FDR	0.207
Number of Positive Examples in Test Data	116871
Number of Negative Examples in Test Data	7953980
Imbalance Ratio in Test Data	0.0145
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 5156 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 4708 SequenceContrib ScoresHyp_Contrib Scores	Erg, Ets1, Elk1, Etv2, Etv4, Fli1, Gabpa, Elk4, Etv5, Etv6, Elf2, Spi1, Elk3, Fev, XP_911724.4, Etv3, Spib, Ehf, Etv1, Elf1, Elf3, Stat4, Elf4, Irf8, Ets2, Irf4, Elf5, Spdef, Stat3
metacluster_1/pattern_2 # seqlets: 2396 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp4, Sp3, Sp1, Klf3, E2f4, Klf4, Klf6, Sp5, Egr1, Klf7, Zbtb17, Klf5, Wt1, Klf8, Klf12, Egr2, Klf1, Maz, Zfp281, E2f1, Klf15, Egr3
metacluster_1/pattern_3 # seqlets: 1540 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_4 # seqlets: 1391 SequenceContrib ScoresHyp_Contrib Scores	Nfkb1, Rela, Relb, Nfkb2, Rel
metacluster_1/pattern_5 # seqlets: 1307 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Stat1, Irf7, Prdm1, Stat2, Irf9, Irf3, Batf3, Irf5
metacluster_1/pattern_6 # seqlets: 1215 SequenceContrib ScoresHyp_Contrib Scores	Rorc, Rora, Pparg, Ppara, Nr1d2, Esr2, Nr1d1
metacluster_1/pattern_7 # seqlets: 1135 SequenceContrib ScoresHyp_Contrib Scores	Fosl2, Jun, Fos, Jund, Fosl1, Batf, Junb, Fosb, Atf3, Jdp2, Bach2, Bach1, Nfe2l2, Nfe2, Mafa, Mafk, Mafb
metacluster_1/pattern_8 # seqlets: 991 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Foxi1, Nfyc, Nfya, Pbx3
metacluster_1/pattern_9 # seqlets: 946 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Creb5, Atf7, Atf2, Atf1, Crem, Nfil3, Tef, Dbp, Rxrb, Gmeb2, Cebpb, Hlf, Cebpa
metacluster_1/pattern_10 # seqlets: 738 SequenceContrib ScoresHyp_Contrib Scores	Nrf1, Zfx
metacluster_1/pattern_11 # seqlets: 680 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_12 # seqlets: 614 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_13 # seqlets: 590 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Rfx1
metacluster_1/pattern_14 # seqlets: 576 SequenceContrib ScoresHyp_Contrib Scores	Zic3, Mxi1
metacluster_1/pattern_15 # seqlets: 501 SequenceContrib ScoresHyp_Contrib Scores	Hes7, Hes1
metacluster_1/pattern_16 # seqlets: 325 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_17 # seqlets: 298 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic
metacluster_1/pattern_18 # seqlets: 251 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Usf2, Arntl, Tfeb, Tfe3, Clock, Tfec, Mitf, Arnt, Bhlhe40, Srebf1, Npas2, Mlx, Srebf2, Creb3l2, Mycn, Tcfl5, Max, Rxrg, Myc, Bhlhe41, Xbp1
metacluster_1/pattern_19 # seqlets: 232 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_20 # seqlets: 182 SequenceContrib ScoresHyp_Contrib Scores