# Parameters
data_name = "EPP;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_190-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_190-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 19:23:50,762 [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	Erythroid progenitor 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	64522	47276	12.4527	25644174	3366869	0.1314	3376099	0.1317	8600571	0.3356
rep2	64522	47276	11.3989	28925972	3346903	0.1158	3429597	0.1186	9691451	0.3353

Metric	Value
auPRC	0.5581
Calibrated Recall at 50% FDR	0.193
Number of Positive Examples in Test Data	48132
Number of Negative Examples in Test Data	8022719
Imbalance Ratio in Test Data	0.006
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 5454 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 2404 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Foxi1, Nfyc, Nfya, Pbx3
metacluster_1/pattern_2 # seqlets: 2190 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Klf3, Sp3, Sp1, Klf6, E2f4, Klf7, Klf4, Klf1, Klf8, Egr1, Klf12, Zbtb17, E2f1, Sp5, Egr2, Klf5, Zfp281, Zfx
metacluster_1/pattern_3 # seqlets: 1922 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Fli1, Elk4, Ets1, Elk1, Elf1, Erg, Elk3, Etv2, Etv4, Etv1, Fev, Etv5, Ehf, Etv3, Etv6, XP_911724.4, Elf3, Elf5, Elf4, Elf2, Spdef, Spi1, Irf8
metacluster_1/pattern_4 # seqlets: 1651 SequenceContrib ScoresHyp_Contrib Scores	Zfp740, Egr3, Sall4
metacluster_1/pattern_5 # seqlets: 1575 SequenceContrib ScoresHyp_Contrib Scores	Yy1, Taf1, Zfp42, Rfx1, Wt1, Maz, Mxi1, Usf2
metacluster_1/pattern_6 # seqlets: 1548 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_7 # seqlets: 935 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_8 # seqlets: 821 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Atf7, Jdp2, Atf1, Crem, Creb5, Atf3, Fosl2, Jun, Hlf, Fosl1, Usf1, Nfil3, Rxrb, Tef
metacluster_1/pattern_9 # seqlets: 667 SequenceContrib ScoresHyp_Contrib Scores	Gata1, Tal1, Gata5, Gata6, Gata4, Gata2, Gata3
metacluster_1/pattern_10 # seqlets: 545 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_11 # seqlets: 441 SequenceContrib ScoresHyp_Contrib Scores	Tfe3, Arntl, Tfeb, Tfec, Mitf, Bhlhe40, Clock, Srebf1, Arnt, Mlx, Srebf2, Npas2, Tcfl5, Bhlhe41, Myc, Creb3l2, Mycn, Max
metacluster_1/pattern_12 # seqlets: 424 SequenceContrib ScoresHyp_Contrib Scores	Bach2, Nfe2, Nfe2l2, Bach1, Mafk, Mafa, Mafg, Mafb, Maff, Maf, Fosb, Junb, Batf, Jund, Fos
metacluster_1/pattern_13 # seqlets: 396 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_14 # seqlets: 274 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_15 # seqlets: 255 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf7, Irf2, Stat1, Prdm1, Stat2, Irf9, Irf3, Irf4, Spib
metacluster_1/pattern_16 # seqlets: 153 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_17 # seqlets: 119 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_18 # seqlets: 80 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic