# Parameters
data_name = "apTreg;8wk;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_239-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_239-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 19:34:20,300 [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	Activated primary T regulatory cells(adult-8wks)
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	143218	118386	5.9786	143352065	33136453	0.2312	18530469	0.1293	53161456	0.3709
rep2	143218	118386	13.1811	25567255	5311831	0.2079	4615865	0.1806	8824946	0.3453

Metric	Value
auPRC	0.6326
Calibrated Recall at 50% FDR	0.191
Number of Positive Examples in Test Data	120395
Number of Negative Examples in Test Data	7950456
Imbalance Ratio in Test Data	0.0149
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 17072 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 1721 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_2 # seqlets: 1539 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Elk1, Gabpa, Etv4, Etv2, Elk4, Fli1, Elf2, Spi1, Etv6, Elk3, Spib, Etv5, Ehf, Elf1, Fev, Etv1, Elf3, Etv3, XP_911724.4, Irf8, Elf4, Irf4, Stat4, Elf5, Spic, Ets2
metacluster_1/pattern_3 # seqlets: 1093 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Stat1, Irf7, Stat2, Prdm1, Irf9, Irf3, Irf5, Batf3
metacluster_1/pattern_4 # seqlets: 558 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_5 # seqlets: 302 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_6 # seqlets: 187 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_7 # seqlets: 115 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_8 # seqlets: 114 SequenceContrib ScoresHyp_Contrib Scores	Rfx1, Rfx3, Rfx2, Rfx4, Rfx7, Rfx6, Hic1
metacluster_1/pattern_9 # seqlets: 110 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3