# Parameters
data_name = "apThEff;CD4+;8wks;D;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_237-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_237-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 19:33:49,544 [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	CD4-positive helper(adult-8wks, Activated primary CD4 effector cells)
Cell Group	T cells
Experiment Name	DHS
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	104595	82411	10.5663	89786849	19240560	0.2143	12925499	0.144	32428526	0.3613
rep2	104595	82411	12.4838	19636196	3346504	0.1705	2965295	0.1511	6792227	0.3462

Metric	Value
auPRC	0.6235
Calibrated Recall at 50% FDR	0.184
Number of Positive Examples in Test Data	104435
Number of Negative Examples in Test Data	7966416
Imbalance Ratio in Test Data	0.0129
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 13074 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 1480 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_2 # seqlets: 767 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf8, Stat1, Irf7, Prdm1, Irf4, Stat2, Spib, Irf3, Irf9, Batf3
metacluster_1/pattern_3 # seqlets: 560 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Etv2, Spi1, Elk1, Erg, Etv4, Gabpa, Ehf, Elk4, Elf1, Etv6, Elf3, Fli1, Elk3, Etv3, Etv1, XP_911724.4, Etv5, Elf4, Spic, Elf2, Fev, Elf5, Spdef
metacluster_1/pattern_4 # seqlets: 436 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2, Stat3
metacluster_1/pattern_5 # seqlets: 314 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp1, Sp3, Sp4, Klf3, Klf6, E2f4, Wt1, Klf1, Klf7, Zbtb17, Egr1, Klf4, Klf8, Klf12, Sp5, Zfp281, Klf5, Klf15, Zfx, Maz, Egr2
metacluster_1/pattern_6 # seqlets: 41 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_7 # seqlets: 39 SequenceContrib ScoresHyp_Contrib Scores	Nrf1