# Parameters
data_name = "pMeg;A;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_189-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_189-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 19:23:33,425 [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	Megakaryocyte primary cell
Cell Group	Other Immune Cells
Experiment Name	ATAC
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	134033	96187	17.9057	30178694	6595393	0.2187	4333984	0.1437	11749993	0.3896
rep2	134033	96187	17.7766	29885640	7123197	0.2385	4365552	0.1462	11905837	0.3986

Metric	Value
auPRC	0.6153
Calibrated Recall at 50% FDR	0.238
Number of Positive Examples in Test Data	109130
Number of Negative Examples in Test Data	7961721
Imbalance Ratio in Test Data	0.0135
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 8920 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 7530 SequenceContrib ScoresHyp_Contrib Scores	Spi1, Spib, Irf8, Irf4, Spic, Elf3, Etv2, Prdm1, Irf3, Ehf, Irf2, Ets1, Irf1, Elf5, Etv6, Etv4, Elf1, Gabpa, Erg, Elf4, Elf2, Etv3, Fli1, XP_911724.4, Elk1, Rela
metacluster_1/pattern_2 # seqlets: 2689 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Cebpd, Cebpg, Dbp, Nfil3, Hlf, Atf4, Ddit3, Cebpe, Tef
metacluster_1/pattern_3 # seqlets: 2039 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Klf3, Sp2, Sp3, Sp1, Klf7, Klf6, Klf4, Klf8, E2f4, Klf1, Klf12, Egr1, Egr2, Zbtb17, Klf5, E2f1, Sp5, Zfp281, Egr3, Zfp740, Zbtb1
metacluster_1/pattern_4 # seqlets: 1582 SequenceContrib ScoresHyp_Contrib Scores	Stat2, Zscan10, Irf7, Stat1, Irf9
metacluster_1/pattern_5 # seqlets: 964 SequenceContrib ScoresHyp_Contrib Scores	Elk4, Elk3, Etv1, Etv5, Fev, Spdef
metacluster_1/pattern_6 # seqlets: 770 SequenceContrib ScoresHyp_Contrib Scores	Twist1
metacluster_1/pattern_7 # seqlets: 581 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_8 # seqlets: 400 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Jdp2, Atf7, Usf2, Atf1, Crem, Creb5, Atf3, Usf1, Fosl2, Zfx, Jun, Rfx1
metacluster_1/pattern_9 # seqlets: 391 SequenceContrib ScoresHyp_Contrib Scores	Nfe2, Nfe2l2, Bach2, Bach1, Mafk, Mafa, Fosb, Mafb, Junb, Fosl1, Mafg, Jund, Maff, Batf, Fos, Maf
metacluster_1/pattern_10 # seqlets: 355 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_11 # seqlets: 251 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_12 # seqlets: 216 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_13 # seqlets: 199 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx3, Runx2, Cbfb, Gfi1b
metacluster_1/pattern_14 # seqlets: 170 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_1/pattern_15 # seqlets: 135 SequenceContrib ScoresHyp_Contrib Scores	Tfe3, Tfeb, Arntl, Mitf, Tfec, Srebf1, Bhlhe40, Clock, Arnt, Mlx, Npas2, Srebf2, Mycn, Creb3l2, Tcfl5, Myc, Max, Bhlhe41, Xbp1, Rarg
metacluster_1/pattern_16 # seqlets: 110 SequenceContrib ScoresHyp_Contrib Scores	Nr1d2, Rorc, Nfatc1
metacluster_1/pattern_17 # seqlets: 105 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_18 # seqlets: 107 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_19 # seqlets: 51 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_20 # seqlets: 45 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_21 # seqlets: 39 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_22 # seqlets: 32 SequenceContrib ScoresHyp_Contrib Scores