# Parameters
data_name = "NTRPHL;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_97-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_97-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 19:01:53,248 [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	Neutrophils(wt)
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	55808	34115	5.7693	60712105	1741510	0.0287	2778797	0.0458	19003981	0.3131
rep2	55808	34115	5.4203	68221410	1940338	0.0284	3156179	0.0463	21738311	0.3187

Metric	Value
auPRC	0.5895
Calibrated Recall at 50% FDR	0.253
Number of Positive Examples in Test Data	32094
Number of Negative Examples in Test Data	8038757
Imbalance Ratio in Test Data	0.004
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 3799 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Etv6, Elk1, Fli1, Ets1, Erg, Elk4, Etv3, Elk3, XP_911724.4, Spi1, Spib, Etv1, Etv4, Etv5, Elf4, Spic, Elf1, Elf2, Irf4, Etv2, Irf8, Ehf, Elf5, Fev, Elf3, Spdef, Irf2, Prdm1, Irf1
metacluster_0/pattern_1 # seqlets: 3409 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Klf3, Sp1, Sp4, Klf6, Klf1, Wt1, E2f4, Sp5, Klf4, Egr1, Klf7, Klf8, Klf12, Klf5, Zfx, Maz, Zbtb17, Egr2, Klf15, Zfp281, E2f1, E2f7
metacluster_0/pattern_2 # seqlets: 2655 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_3 # seqlets: 2457 SequenceContrib ScoresHyp_Contrib Scores	Cebpa, Cebpb, Cebpd, Nfil3, Dbp, Hlf, Ddit3, Atf4, Cebpg, Cebpe, Tef
metacluster_0/pattern_4 # seqlets: 1593 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_5 # seqlets: 1512 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_6 # seqlets: 1453 SequenceContrib ScoresHyp_Contrib Scores	Yy1, Taf1, Rfx1, Zfp42, Usf2, Mxi1
metacluster_0/pattern_7 # seqlets: 1444 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Creb5, Atf7, Jdp2, Atf2, Atf1, Crem, Jun, Mafb, Fosl1, Atf3, Gmeb2, Jund, Rxrb, Junb, Fosl2, Esr2, Gmeb1
metacluster_0/pattern_8 # seqlets: 692 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_9 # seqlets: 669 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_10 # seqlets: 650 SequenceContrib ScoresHyp_Contrib Scores	Bach2, Nfe2l2, Nfe2, Bach1, Mafk, Mafa, Mafg, Maff, Maf, Fosb, Fos, Batf
metacluster_0/pattern_11 # seqlets: 529 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfeb, Arntl, Tfe3, Tfec, Mitf, Clock, Arnt, Srebf1, Bhlhe40, Mlx, Srebf2, Npas2, Tcfl5, Myc, Bhlhe41, Mycn, Creb3l2, Nr1h4, Max
metacluster_0/pattern_12 # seqlets: 418 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_13 # seqlets: 382 SequenceContrib ScoresHyp_Contrib Scores	Irf7, Stat1, Stat2, Irf3, Irf9, Batf3
metacluster_0/pattern_14 # seqlets: 337 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_0/pattern_15 # seqlets: 117 SequenceContrib ScoresHyp_Contrib Scores	Rela, A1JVI6_MOUSE
metacluster_0/pattern_16 # seqlets: 51 SequenceContrib ScoresHyp_Contrib Scores