# Parameters
data_name = "B_SPLND;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_139-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_139-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 19:11:19,790 [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	Splenic B cell
Cell Group	B 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	52733	32568	8.1848	24806682	1388018	0.056	1917392	0.0774	8012042	0.3232
rep2	52733	32568	7.168	29118676	1454931	0.05	2115843	0.0727	9302465	0.3197

Metric	Value
auPRC	0.6035
Calibrated Recall at 50% FDR	0.222
Number of Positive Examples in Test Data	40505
Number of Negative Examples in Test Data	8030346
Imbalance Ratio in Test Data	0.005
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 5855 SequenceContrib ScoresHyp_Contrib Scores	Spi1, Spib, Ets1, Etv6, Etv2, Spic, Erg, Irf8, Irf4, Etv4, Gabpa, Elk1, Etv3, Fli1, XP_911724.4, Elk4, Elf1, Elk3, Etv5, Etv1, Elf4, Ehf, Elf2, Elf3, Elf5, Prdm1, Fev, Irf2, Spdef, Irf3, Irf1
metacluster_1/pattern_1 # seqlets: 3810 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf7, Klf6, Klf4, Klf8, Klf12, Klf1, Egr1, Zbtb17, Egr2, E2f1, Sp5, Klf5, Zfp281, Zfx, Zfp740, Zbtb1, Egr3
metacluster_1/pattern_2 # seqlets: 3515 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_3 # seqlets: 1966 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_4 # seqlets: 1940 SequenceContrib ScoresHyp_Contrib Scores	Stat2, Stat1, Irf7, Zscan10
metacluster_1/pattern_5 # seqlets: 1800 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_6 # seqlets: 1055 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_1/pattern_7 # seqlets: 946 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Usf2, Atf7, Jdp2, Atf1, Crem, Creb5, Atf3, Fosl2, Jun, Fosl1, Nfil3, Tef, Hlf
metacluster_1/pattern_8 # seqlets: 844 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfec, Tfeb, Arntl, Mitf, Tfe3, Srebf1, Bhlhe40, Clock, Mlx, Arnt, Npas2, Creb3l2, Srebf2, Tcfl5, Bhlhe41, Xbp1, Max, Mycn, Hes1, Mlxip
metacluster_1/pattern_9 # seqlets: 835 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Zfp42
metacluster_1/pattern_10 # seqlets: 346 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_11 # seqlets: 317 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2
metacluster_1/pattern_12 # seqlets: 274 SequenceContrib ScoresHyp_Contrib Scores	Gmeb2, Gmeb1
metacluster_1/pattern_13 # seqlets: 236 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_14 # seqlets: 229 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_15 # seqlets: 211 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_16 # seqlets: 152 SequenceContrib ScoresHyp_Contrib Scores	Nfkb2, Nfkb1, Rela, Relb
metacluster_1/pattern_17 # seqlets: 118 SequenceContrib ScoresHyp_Contrib Scores	Stat3
metacluster_1/pattern_18 # seqlets: 110 SequenceContrib ScoresHyp_Contrib Scores	Maz, Wt1, Klf15, Ptf1a, Bcl6
metacluster_1/pattern_19 # seqlets: 65 SequenceContrib ScoresHyp_Contrib Scores	Ebf1, Prdm16