# Parameters
data_name = "TExh_SPLND;CD8+;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_118-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_118-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 19:07:15,914 [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	Spleen CD8+ T cell (Exhausted)
Cell Group	T 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	119388	99265	15.3738	19562267	4010154	0.2052	3112268	0.1592	6453968	0.3302
rep2	119388	99265	14.5692	27079728	7097208	0.2623	4850061	0.1792	8887877	0.3284
rep3	119388	99265	18.087	23108080	7183353	0.3111	4727684	0.2048	8014532	0.3471

Metric	Value
auPRC	0.5872
Calibrated Recall at 50% FDR	0.217
Number of Positive Examples in Test Data	110296
Number of Negative Examples in Test Data	7960555
Imbalance Ratio in Test Data	0.0137
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 7072 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 5664 SequenceContrib ScoresHyp_Contrib Scores	Erg, Ets1, Elk1, Gabpa, Fli1, Elk4, Etv2, Etv4, Etv5, Elf2, Elk3, Etv6, Spi1, Elf1, Fev, Ehf, Etv1, Etv3, XP_911724.4, Spib, Elf3, Elf4, Elf5, Stat4, Irf8, Irf4, Ets2, Spdef, Spic
metacluster_1/pattern_2 # seqlets: 3943 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Klf3, Sp2, Sp3, Sp1, Klf6, Klf7, Klf4, E2f4, Klf8, Klf1, Klf12, Egr1, Egr2, Zbtb17, Klf5, E2f1, Sp5, Zfp281, Egr3, Zfp740, Zfx, Zbtb1
metacluster_1/pattern_3 # seqlets: 2136 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Stat1, Prdm1, Irf7, Irf3, Stat2, Irf9, Batf3
metacluster_1/pattern_4 # seqlets: 1464 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_5 # seqlets: 1207 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Foxi1, Nfya, Pbx3
metacluster_1/pattern_6 # seqlets: 837 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_7 # seqlets: 806 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_8 # seqlets: 788 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_9 # seqlets: 664 SequenceContrib ScoresHyp_Contrib Scores	Jdp2, Jund, Batf, Fos, Fosb, Fosl2, Junb, Fosl1, Atf3, Jun, Bach2, Nfe2, Nfe2l2, Bach1, Mafa
metacluster_1/pattern_10 # seqlets: 567 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Atf7, Atf1, Crem, Usf2, Creb5, Nfil3, Rxrb
metacluster_1/pattern_11 # seqlets: 536 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Rfx1, Mxi1, Wt1
metacluster_1/pattern_12 # seqlets: 394 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfe3, Tfeb, Arntl, Tfec, Mitf, Srebf1, Bhlhe40, Clock, Arnt, Mlx, Srebf2, Npas2, Tcfl5, Hlf, Mycn, Bhlhe41, Max, Creb3l2, Myc
metacluster_1/pattern_13 # seqlets: 299 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_14 # seqlets: 251 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_15 # seqlets: 133 SequenceContrib ScoresHyp_Contrib Scores	Nfkb1, Rela, Nfkb2, Relb, Rel
metacluster_1/pattern_16 # seqlets: 111 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_17 # seqlets: 107 SequenceContrib ScoresHyp_Contrib Scores	Nfatc1
metacluster_1/pattern_18 # seqlets: 43 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic