# Parameters
data_name = "ILC2_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_111-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_111-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 19:04:54,889 [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	ILC2_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	119396	88308	12.6387	23472356	2409108	0.1027	2249547	0.0959	8002601	0.3412
rep2	119396	88308	15.0858	20844285	6662887	0.3199	4333770	0.2081	8085255	0.3882

Metric	Value
auPRC	0.584
Calibrated Recall at 50% FDR	0.184
Number of Positive Examples in Test Data	97973
Number of Negative Examples in Test Data	7972878
Imbalance Ratio in Test Data	0.0121
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 6262 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 3847 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Fli1, Etv2, Gabpa, Erg, Elk4, Elk1, Etv4, Spi1, Elf1, Sp2, Etv6, Elf3, Sp1, Ehf, Elk3, Etv1, Sp3, Zfx, Fev, Etv5, Sp5, Etv3, XP_911724.4, Wt1, Spib, Maz, Zbtb17, Klf3, Elf4, Elf5, Sp4, Mxi1, Usf2, Prdm1, E2f3, Mbd2, Gata1, Elf2, Tal1, Klf6, Klf15, Ets2, Rfx1
metacluster_1/pattern_2 # seqlets: 3327 SequenceContrib ScoresHyp_Contrib Scores	E2f4, Klf7, Klf4, Klf8, Egr1, Klf1, Klf12, Egr2, E2f1, Zfp281, Klf5, Egr3, Zfp740
metacluster_1/pattern_3 # seqlets: 1637 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_4 # seqlets: 1584 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_5 # seqlets: 1554 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Jdp2, Crem, Atf2, Atf7, Creb5, Atf1, Atf3, Jun, Fosl2, Fosl1
metacluster_1/pattern_6 # seqlets: 1503 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf8, Irf7, Irf4, Stat1, Irf9, Stat2, Irf3, Batf3, Spic
metacluster_1/pattern_7 # seqlets: 926 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_1/pattern_8 # seqlets: 815 SequenceContrib ScoresHyp_Contrib Scores	Fosb, Junb, Fos, Jund, Batf, Bach2, Nfe2l2, Nfe2, Mafa, Mafk, Bach1, Mafb, Mafg, Maf, Maff, Nr1d2, Nfatc1
metacluster_1/pattern_9 # seqlets: 704 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_10 # seqlets: 578 SequenceContrib ScoresHyp_Contrib Scores	Nfkb1, Rela, Nfkb2, Relb, Rel
metacluster_1/pattern_11 # seqlets: 361 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_12 # seqlets: 345 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_13 # seqlets: 341 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfeb, Tfe3, Arntl, Tfec, Mitf, Arnt, Bhlhe40, Clock, Srebf1, Mlx, Srebf2, Npas2, Tcfl5, Nr1h4, Bhlhe41, Creb3l2, Mycn, Rxrg, Hlf, Max, Rxrb
metacluster_1/pattern_14 # seqlets: 326 SequenceContrib ScoresHyp_Contrib Scores	Gata4, Gata2, Gata3, Gata6, Gata5, Mecom
metacluster_1/pattern_15 # seqlets: 318 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_16 # seqlets: 186 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_17 # seqlets: 112 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_18 # seqlets: 91 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Pou2f1
metacluster_1/pattern_19 # seqlets: 78 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic
metacluster_1/pattern_20 # seqlets: 73 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_21 # seqlets: 41 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_22 # seqlets: 48 SequenceContrib ScoresHyp_Contrib Scores