# Parameters
data_name = "ILC2+IL33+IL25;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_106-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_106-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 19:04:22,860 [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+IL33+IL25
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	116228	84281	13.0011	39220034	6427969	0.164	4728331	0.1206	12751109	0.3253
rep2	116228	84281	13.2307	41928394	6715249	0.1602	4607571	0.1099	13357816	0.3187

Metric	Value
auPRC	0.5603
Calibrated Recall at 50% FDR	0.231
Number of Positive Examples in Test Data	97401
Number of Negative Examples in Test Data	7973450
Imbalance Ratio in Test Data	0.0121
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 4466 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Etv4, Fli1, Elk1, Gabpa, Etv2, Elk4, Spi1, Etv5, Elk3, Etv6, Elf2, Fev, Etv3, Etv1, XP_911724.4, Spib, Elf1, Ehf, Elf4, Elf5, Irf8, Irf4, Elf3, Spic, Spdef, Zscan10, Stat3
metacluster_1/pattern_1 # seqlets: 3266 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf6, Klf7, Klf4, Klf8, Klf1, Klf12, Egr1, Zbtb17, Egr2, E2f1, Sp5, Klf5, Zfp281, Zfx, Egr3, Zfp740
metacluster_1/pattern_2 # seqlets: 3159 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_3 # seqlets: 2252 SequenceContrib ScoresHyp_Contrib Scores	Fosl1, Fosb, Atf3, Junb, Jun, Fos, Jund, Fosl2, Jdp2, Batf, Bach2, Nfe2, Nfe2l2, Bach1, Mafa, Mafk
metacluster_1/pattern_4 # seqlets: 1193 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Creb5, Atf7, Atf1, Atf2, Crem, Nfil3, Mafb, Tef, Dbp, Rxrb, Cebpb, Gmeb2, Hlf, Cebpa
metacluster_1/pattern_5 # seqlets: 1115 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_6 # seqlets: 1012 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_7 # seqlets: 1008 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_8 # seqlets: 962 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf7, Stat1, Stat2, Irf9, Prdm1, Batf3, Irf3, Irf5
metacluster_1/pattern_9 # seqlets: 837 SequenceContrib ScoresHyp_Contrib Scores	Gata3, Gata4, Gata2, Gata1, Tal1, Gata6, Mecom, Gata5
metacluster_1/pattern_10 # seqlets: 806 SequenceContrib ScoresHyp_Contrib Scores	Nfkb1, Rela, Nfkb2, Relb, Rel
metacluster_1/pattern_11 # seqlets: 535 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Rfx1, Wt1
metacluster_1/pattern_12 # seqlets: 500 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_13 # seqlets: 387 SequenceContrib ScoresHyp_Contrib Scores	Nr4a2, Rora, Rorc, Esrrg, Nr5a2, Nr4a1, Nr2f6, Rara, Nr2f1, Rarg, Rarb
metacluster_1/pattern_14 # seqlets: 237 SequenceContrib ScoresHyp_Contrib Scores	Usf2, Usf1, Tfeb, Arntl, Mitf, Tfe3, Tfec, Clock, Arnt, Mlx, Srebf1, Mxi1, Bhlhe40, Npas2, Mycn, Myc, Max, Srebf2, Rxrg, Creb3l2, Xbp1, Tcfl5, Bhlhe41, Nr1h4
metacluster_1/pattern_15 # seqlets: 184 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_16 # seqlets: 180 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_17 # seqlets: 147 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Pou5f1, Pou2f1
metacluster_1/pattern_18 # seqlets: 110 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_19 # seqlets: 108 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_1/pattern_20 # seqlets: 98 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_21 # seqlets: 89 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_22 # seqlets: 81 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_23 # seqlets: 70 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_24 # seqlets: 31 SequenceContrib ScoresHyp_Contrib Scores