# Parameters
data_name = "naiveT_SPLND;CD4+;D;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_206-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_206-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 19:28:03,381 [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	Naive splenic CD4+ T-cells
Cell Group	T cells
Experiment Name	DHS
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	43667	28604	10.4676	8387784	834174	0.0996	737849	0.0881	3002624	0.3587
rep2	43667	28604	8.3375	40446645	1862741	0.0461	2353723	0.0582	12981221	0.3211

Metric	Value
auPRC	0.6113
Calibrated Recall at 50% FDR	0.212
Number of Positive Examples in Test Data	34535
Number of Negative Examples in Test Data	8036316
Imbalance Ratio in Test Data	0.0043
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 5720 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Elk1, Gabpa, Fli1, Elk4, Etv2, Etv5, Elk3, Elf1, Etv4, Elf2, Spi1, Fev, Etv6, Ehf, Etv1, XP_911724.4, Etv3, Elf3, Spib, Elf4, Elf5, Spdef, Stat4, Irf8, Spic, Ets2, Irf4
metacluster_1/pattern_1 # seqlets: 3641 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf6, Klf7, Klf4, Klf8, Klf1, Klf12, Egr1, Zbtb17, Egr2, E2f1, Klf5, Sp5, Zfp281, Zfx, Zfp740, Egr3
metacluster_1/pattern_2 # seqlets: 2155 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_3 # seqlets: 2082 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_4 # seqlets: 1849 SequenceContrib ScoresHyp_Contrib Scores	Ctcfl, Ctcf
metacluster_1/pattern_5 # seqlets: 1580 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Creb5, Jdp2, Atf7, Atf2, Atf1, Crem, Jun, Nfil3, Tef, Mafb, Fosl1, Dbp, Gmeb2, Cebpb, Hlf, Atf3, Jund, Junb, Cebpa, Gmeb1, Rxrb, Fosl2, Cebpd, Cebpg, Esr2
metacluster_1/pattern_6 # seqlets: 920 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Usf2, Tfeb, Tfec, Arntl, Mitf, Tfe3, Srebf1, Bhlhe40, Clock, Mlx, Arnt, Npas2, Creb3l2, Srebf2, Tcfl5, Bhlhe41, Xbp1, Max, Mycn, Myc, Mlxip, Hes1
metacluster_1/pattern_7 # seqlets: 865 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_8 # seqlets: 859 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Zfp42
metacluster_1/pattern_9 # seqlets: 634 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_10 # seqlets: 503 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_11 # seqlets: 491 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf7, Stat1, Stat2, Prdm1, Irf3, Irf9, Batf3
metacluster_1/pattern_12 # seqlets: 260 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_13 # seqlets: 175 SequenceContrib ScoresHyp_Contrib Scores	Nfkb2, Nfkb1, Rela, Relb, Rel
metacluster_1/pattern_14 # seqlets: 175 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_15 # seqlets: 142 SequenceContrib ScoresHyp_Contrib Scores	Fos, Fosb, Batf, Bach2, Nfe2, Nfe2l2, Bach1
metacluster_1/pattern_16 # seqlets: 93 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Zfp322a, Nfic
metacluster_1/pattern_17 # seqlets: 85 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Pou2f1
metacluster_1/pattern_18 # seqlets: 88 SequenceContrib ScoresHyp_Contrib Scores