# Parameters
data_name = "naiveT;trnsgncTCR_SV40-I_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_120-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_120-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 19:07:19,289 [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 transgenic TCR SV40-I CD8 T cells
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	136492	116981	13.4942	48266522	8494866	0.1761	5577320	0.1156	15803954	0.3276
rep2	136492	116981	14.0674	49016170	9430677	0.1925	6048192	0.1234	16329274	0.3333
rep3	136492	116981	14.7601	42694779	9533885	0.2234	6255088	0.1466	14130164	0.3311

Metric	Value
auPRC	0.5992
Calibrated Recall at 50% FDR	0.217
Number of Positive Examples in Test Data	128820
Number of Negative Examples in Test Data	7942031
Imbalance Ratio in Test Data	0.016
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 9527 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_1 # seqlets: 5005 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Elk1, Etv2, Gabpa, Fli1, Elk4, Etv4, Etv5, Spi1, Elf2, Etv6, Elk3, Elf1, Fev, Ehf, Etv1, XP_911724.4, Etv3, Spib, Elf3, Elf4, Stat4, Elf5, Ets2, Irf8, Spdef, Irf4, Spic
metacluster_0/pattern_2 # seqlets: 3598 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Klf3, Sp4, Sp1, Klf6, Klf4, E2f4, Klf5, Egr1, Klf7, Sp5, Klf8, Zbtb17, Klf12, Egr2, Wt1, Zfp281, Klf1, Maz, E2f1, Klf15, Sall4, Egr3, Srebf2, Zfp740
metacluster_0/pattern_3 # seqlets: 1256 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_4 # seqlets: 978 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Stat1, Prdm1, Stat2, Irf7, Irf3, Irf9, Batf3
metacluster_0/pattern_5 # seqlets: 979 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Foxi1, Nfya, Pbx3
metacluster_0/pattern_6 # seqlets: 723 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_0/pattern_7 # seqlets: 656 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_0/pattern_8 # seqlets: 609 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_9 # seqlets: 526 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfx, Zfp42, Rfx1
metacluster_0/pattern_10 # seqlets: 482 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Usf2, Tfe3, Tfeb, Arntl, Tfec, Mitf, Clock, Arnt, Srebf1, Bhlhe40, Mlx, Npas2, Rxrg, Atf7, Tcfl5, Rxrb, Mycn, Atf2, Jdp2, Hlf, Creb3l2, Creb1, Bhlhe41, Rxra, Max, Myc, Atf1, Nr2f1
metacluster_0/pattern_11 # seqlets: 413 SequenceContrib ScoresHyp_Contrib Scores	Crem, Creb5, Atf3, Fosl2, Jun
metacluster_0/pattern_12 # seqlets: 156 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_13 # seqlets: 112 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_0/pattern_14 # seqlets: 108 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_15 # seqlets: 70 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_16 # seqlets: 66 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_0/pattern_17 # seqlets: 51 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_18 # seqlets: 45 SequenceContrib ScoresHyp_Contrib Scores	Nfkb2, Nfkb1, Rela, Relb