# Parameters
data_name = "Erythroid;Ter119+;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_144-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_144-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 19:11:53,140 [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	Ter119+ Erythroid cells
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	45623	33619	9.5158	47165654	2269105	0.0481	2855225	0.0606	14556630	0.3088
rep2	45623	33619	9.116	51530014	2388041	0.0464	3026133	0.0587	15861839	0.3079

Metric	Value
auPRC	0.6228
Calibrated Recall at 50% FDR	0.212
Number of Positive Examples in Test Data	36430
Number of Negative Examples in Test Data	8034421
Imbalance Ratio in Test Data	0.0045
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 3639 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_1 # seqlets: 2874 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Klf3, Sp4, Sp1, Klf6, Klf4, E2f4, Klf5, Klf7, Sp5, Egr1, Zbtb17, Klf12, Klf8, Egr2, Zfp281, Wt1, Klf1, Maz, E2f1, Srebf2, Klf15, Sall4, Zfp740
metacluster_0/pattern_2 # seqlets: 2387 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elk4, Fli1, Erg, Ets1, Elk1, Elf1, Elk3, Etv1, Etv4, Etv6, Etv5, Etv3, XP_911724.4, Etv2, Elf4, Ehf, Fev, Elf5, Elf2, Spi1, Spdef, Elf3, Spib, Spic, Irf8
metacluster_0/pattern_3 # seqlets: 2074 SequenceContrib ScoresHyp_Contrib Scores	Nfya, Nfyb, Nfyc, Foxi1, Pbx3
metacluster_0/pattern_4 # seqlets: 1695 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_5 # seqlets: 1438 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfx, Zfp42, Mxi1, Usf2, Rfx1
metacluster_0/pattern_6 # seqlets: 1300 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_7 # seqlets: 1142 SequenceContrib ScoresHyp_Contrib Scores	Gata1, Tal1, Gata5, Gata6, Gata4, Gata2, Gata3
metacluster_0/pattern_8 # seqlets: 1050 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_0/pattern_9 # seqlets: 903 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Atf1, Jdp2, Atf7, Crem, Atf3, Creb5, Fosl2, Jun, Fosl1, Hlf, Nfil3, Rxrb, Usf1, Dbp, Tef, Creb3l2
metacluster_0/pattern_10 # seqlets: 791 SequenceContrib ScoresHyp_Contrib Scores	Nfe2, Bach2, Nfe2l2, Bach1, Mafa, Mafk, Mafb, Mafg, Maff, Maf, Fosb, Junb, Jund, Batf, Fos
metacluster_0/pattern_11 # seqlets: 561 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf7, Prdm1, Stat2, Irf9, Irf4, Stat1, Irf3
metacluster_0/pattern_12 # seqlets: 556 SequenceContrib ScoresHyp_Contrib Scores	Tfeb, Arntl, Tfe3, Tfec, Bhlhe40, Mitf, Clock, Srebf1, Arnt, Mlx, Npas2, Tcfl5, Bhlhe41, Myc, Max, Nr1h4, Mycn, Mlxip, Rxrg
metacluster_0/pattern_13 # seqlets: 359 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_0/pattern_14 # seqlets: 93 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Zfp322a, Nfib, Nfic
metacluster_0/pattern_15 # seqlets: 48 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Pou5f1, Pou2f1, Pou3f1, Nanog, Sox2, Pou3f2