# Parameters
data_name = "DC_LPS;4h;A;En"
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_195-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_195-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 19:24:45,204 [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	dendritic cell(100 ng/mL Lipopolysaccharide, 4hours)
Cell Group	Other Immune Cells
Experiment Name	ATAC
Experiment Group	ENCODE

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	142641	96690	17.1295	29455074	11012580	0.3741	6221966	0.2114	12851062	0.4366
rep2	142641	96690	6.515	78975437	4579417	0.058	4334187	0.0549	26151567	0.3312

Metric	Value
auPRC	0.6434
Calibrated Recall at 50% FDR	0.182
Number of Positive Examples in Test Data	120926
Number of Negative Examples in Test Data	7949925
Imbalance Ratio in Test Data	0.015
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 4745 SequenceContrib ScoresHyp_Contrib Scores	Spi1, Spib, Irf8, Irf4, Spic, Irf3, Etv6, Elf3, Etv2, Etv4, Prdm1, Ehf, Elf4, Ets1, Elf2, Etv3, Fli1, Gabpa, Elk1, XP_911724.4, Irf2, Elf5, Erg, Irf1
metacluster_1/pattern_1 # seqlets: 3226 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_2 # seqlets: 2766 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, Klf4, Klf7, Klf6, E2f4, Klf8, Klf12, Klf1, Egr1, Egr2, Zbtb17, Klf5, E2f1, Sp5, Zfp281, Egr3, Zfx, Zfp740, Sall4
metacluster_1/pattern_3 # seqlets: 2175 SequenceContrib ScoresHyp_Contrib Scores	Stat2, Stat1, Irf7, Irf9, Irf5, Zscan10
metacluster_1/pattern_4 # seqlets: 1551 SequenceContrib ScoresHyp_Contrib Scores	Rela, Nfkb1, Nfkb2, Relb, Rel
metacluster_1/pattern_5 # seqlets: 1482 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpd, Cebpa, Cebpg, Dbp, Cebpe, Nfil3, Hlf, Ddit3, Atf4, Tef, Jun, Jdp2, Pou3f3, Creb1
metacluster_1/pattern_6 # seqlets: 1434 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_7 # seqlets: 1427 SequenceContrib ScoresHyp_Contrib Scores	Fosl2, Atf3, Fosl1, Fosb, Batf, Junb, Fos, Jund, Bach2, Nfe2, Nfe2l2, Bach1, Mafk, Mafb, Mafa, Mafg, Maff, Maf, Nfatc1
metacluster_1/pattern_8 # seqlets: 1104 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Creb5, Atf1, Crem, Srebf1, Tfec, Rxrb, Mlx
metacluster_1/pattern_9 # seqlets: 891 SequenceContrib ScoresHyp_Contrib Scores	Elk4, Elk3, Etv1, Elf1, Etv5, Fev, Spdef, Mbd2, E2f3
metacluster_1/pattern_10 # seqlets: 772 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Foxi1, Nfya, Nfyc, Pbx3
metacluster_1/pattern_11 # seqlets: 622 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_12 # seqlets: 469 SequenceContrib ScoresHyp_Contrib Scores	Rfx1, Taf1, Yy1, Wt1, Rfx2, Maz, Rfx3, Zfp42, Usf2, Klf15, Mxi1, Nr1h4
metacluster_1/pattern_13 # seqlets: 464 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfeb, Arntl, Mitf, Tfe3, Bhlhe40, Clock, Npas2, Arnt, Creb3l2, Tcfl5, Srebf2, Xbp1, Bhlhe41, Mycn, Hes1, Max, Myc, Mlxip
metacluster_1/pattern_14 # seqlets: 311 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_1/pattern_15 # seqlets: 100 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_16 # seqlets: 82 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_17 # seqlets: 79 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2
metacluster_1/pattern_18 # seqlets: 42 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic