# Parameters
data_name = "MCRPHG_BMD.LPD_Stmltd;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_143-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_143-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 19:11:31,111 [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	bone marrow-derived macrophages(Lipid A stimulation 120min)
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	116765	75199	13.2127	14651988	2167237	0.1481	1479012	0.1011	5833419	0.3986
rep2	116765	75199	9.3591	8537967	641008	0.0752	649779	0.0763	3088077	0.3624
rep3	116765	75199	14.521	17628648	4318226	0.2452	2368863	0.1345	7713306	0.438
rep4	116765	75199	7.1732	14571958	465768	0.032	816061	0.0561	4844595	0.3329

Metric	Value
auPRC	0.5825
Calibrated Recall at 50% FDR	0.228
Number of Positive Examples in Test Data	89513
Number of Negative Examples in Test Data	7981338
Imbalance Ratio in Test Data	0.0111
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 5386 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 4753 SequenceContrib ScoresHyp_Contrib Scores	Spi1, Spib, Irf8, Irf4, Spic, Etv2, Elf3, Irf3, Prdm1, Ehf, Etv6, Irf2, Ets1, Etv4, Irf1, Elf5, Elf4, Etv3, Elf2, Gabpa, Elk1, Fli1, Erg, XP_911724.4, Elf1
metacluster_1/pattern_2 # seqlets: 2849 SequenceContrib ScoresHyp_Contrib Scores	Fosl1, Fosb, Junb, Atf3, Fos, Fosl2, Jund, Jun, Jdp2, Batf, Bach2, Nfe2l2, Nfe2, Bach1, Mafk, Mafa
metacluster_1/pattern_3 # seqlets: 2579 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf7, Klf6, Klf4, Klf8, Klf1, Klf12, Egr1, Egr2, Zbtb17, E2f1, Sp5, Klf5, Zfp281, Egr3, Zfx, Zfp740
metacluster_1/pattern_4 # seqlets: 1754 SequenceContrib ScoresHyp_Contrib Scores	Stat1, Stat2, Irf7, Irf9, Zscan10, Irf5
metacluster_1/pattern_5 # seqlets: 1420 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfya, Nfyc, Foxi1, Pbx3
metacluster_1/pattern_6 # seqlets: 1338 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Cebpd, Dbp, Nfil3, Cebpg, Hlf, Atf4, Ddit3, Cebpe, Tef
metacluster_1/pattern_7 # seqlets: 1279 SequenceContrib ScoresHyp_Contrib Scores	Atf2, Atf7, Creb5, Creb1, Atf1, Crem, Srebf1, Tfec, Mlx, Rxrb, Mafb
metacluster_1/pattern_8 # seqlets: 911 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_9 # seqlets: 723 SequenceContrib ScoresHyp_Contrib Scores	Rela, Nfkb1, Relb, Nfkb2, Rel
metacluster_1/pattern_10 # seqlets: 701 SequenceContrib ScoresHyp_Contrib Scores	Elk4, Elk3, Etv1, Etv5, Fev, Spdef, Mbd2
metacluster_1/pattern_11 # seqlets: 646 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_12 # seqlets: 576 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_13 # seqlets: 479 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Mitf, Tfeb, Usf2, Arntl, Tfe3, Bhlhe40, Clock, Arnt, Npas2, Srebf2, Tcfl5, Creb3l2, Bhlhe41, Xbp1, Max, Mycn, Mlxip, Arnt2
metacluster_1/pattern_14 # seqlets: 424 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Rfx1
metacluster_1/pattern_15 # seqlets: 255 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb
metacluster_1/pattern_16 # seqlets: 109 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_17 # seqlets: 105 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Pou2f1
metacluster_1/pattern_18 # seqlets: 103 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_19 # seqlets: 41 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_20 # seqlets: 37 SequenceContrib ScoresHyp_Contrib Scores