# Parameters
data_name = "DC_pBMD;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_148-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_148-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 19:12:53,537 [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	Primary bone marrow derived dendritic cells (DCs, control vector)
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	154469	103456	14.5328	24931180	7736262	0.3105	3445600	0.1383	11539703	0.4632
rep2	154469	103456	16.7485	21897388	8341615	0.3813	3964571	0.1812	10667067	0.4876

Metric	Value
auPRC	0.6119
Calibrated Recall at 50% FDR	0.238
Number of Positive Examples in Test Data	134344
Number of Negative Examples in Test Data	7936507
Imbalance Ratio in Test Data	0.0166
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 7019 SequenceContrib ScoresHyp_Contrib Scores	Spib, Spi1, Irf8, Irf4, Spic, Elf3, Etv2, Irf3, Ehf, Prdm1, Ets1, Etv6, Etv4, Irf2, Irf1, Erg, Elf5, Elf4, Etv3, Elf1, Elf2, Fli1, Gabpa, Elk1, XP_911724.4, Elk4, Elk3
metacluster_1/pattern_1 # seqlets: 4550 SequenceContrib ScoresHyp_Contrib Scores	Cebpa, Cebpb, Cebpd, Nfil3, Dbp, Ddit3, Atf4, Cebpg, Hlf, Cebpe, Tef
metacluster_1/pattern_2 # seqlets: 3326 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_3 # seqlets: 2383 SequenceContrib ScoresHyp_Contrib Scores	Fosl1, Atf3, Junb, Fosb, Jun, Fos, Fosl2, Jund, Jdp2, Batf, Bach2, Nfe2, Nfe2l2, Bach1, Mafk, Mafa, Mafb
metacluster_1/pattern_4 # seqlets: 1872 SequenceContrib ScoresHyp_Contrib Scores	Stat2, Stat1, Irf7, Zscan10, Irf9
metacluster_1/pattern_5 # seqlets: 1763 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Klf3, Sp2, Sp3, Sp1, Klf6, Klf7, Klf4, E2f4, Klf1, Klf8, Klf12, Egr1, Egr2, Zbtb17, Klf5, Sp5, E2f1, Zfp281, Egr3
metacluster_1/pattern_6 # seqlets: 1184 SequenceContrib ScoresHyp_Contrib Scores	Atf2, Atf7, Creb5, Creb1, Atf1, Crem, Srebf1, Tfec, Mlx, Rxrb
metacluster_1/pattern_7 # seqlets: 774 SequenceContrib ScoresHyp_Contrib Scores	Mitf, Usf1, Tfeb, Tfe3, Bhlhe40, Usf2, Arntl, Clock, Arnt, Srebf2, Npas2, Tcfl5, Bhlhe41, Creb3l2, Arnt2
metacluster_1/pattern_8 # seqlets: 767 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_9 # seqlets: 532 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Foxi1, Nfya, Nfyc, Pbx3
metacluster_1/pattern_10 # seqlets: 460 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_11 # seqlets: 422 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_12 # seqlets: 376 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_13 # seqlets: 218 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Cbfb, Runx3
metacluster_1/pattern_14 # seqlets: 133 SequenceContrib ScoresHyp_Contrib Scores	Yy1, Taf1, Zfx, Rfx1, Zfp42, Wt1, Maz
metacluster_1/pattern_15 # seqlets: 86 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_16 # seqlets: 38 SequenceContrib ScoresHyp_Contrib Scores