# Parameters
data_name = "pErythroblast;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_192-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_192-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 19:24:14,702 [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	Erythroblast 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	69214	51798	10.2287	30401327	3956009	0.1302	3996138	0.1315	10401378	0.3423
rep2	69214	51798	10.7078	26706298	3463247	0.1298	3539442	0.1326	9248240	0.3465

Metric	Value
auPRC	0.558
Calibrated Recall at 50% FDR	0.192
Number of Positive Examples in Test Data	53311
Number of Negative Examples in Test Data	8017540
Imbalance Ratio in Test Data	0.0066
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 8144 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 4262 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp1, Sp3, Klf3, Sp4, Zfx, Klf6, Wt1, Klf1, Klf7, Klf4, Sp5, E2f4, Klf5, Klf8, Klf15, Klf12, Zbtb17, Egr1, Zfp281, Usf2, Maz, Tfap2c, Egr2, Mxi1, Sall4, Tfap2b
metacluster_1/pattern_2 # seqlets: 1867 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Fli1, Ets1, Elk4, Elk1, Erg, Elf1, Elk3, Fev, Etv1, Etv4, Etv5, Etv2, Ehf, Etv3, Etv6, XP_911724.4, Elf3, Elf5, Elf2, Spi1, Elf4, Mbd2, Spdef, Irf8, E2f3, Spib
metacluster_1/pattern_3 # seqlets: 1842 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_4 # seqlets: 1488 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Foxi1, Nfya, Pbx3
metacluster_1/pattern_5 # seqlets: 1007 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Zfp42
metacluster_1/pattern_6 # seqlets: 961 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_1/pattern_7 # seqlets: 829 SequenceContrib ScoresHyp_Contrib Scores	Nfe2, Nfe2l2, Bach2, Bach1, Mafa, Mafk, Jun, Mafb, Mafg, Maff, Maf, Atf3, Fosb, Fosl2, Junb, Fosl1, Batf, Jund, Fos, Jdp2
metacluster_1/pattern_8 # seqlets: 804 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Atf7, Atf1, Creb5, Crem, Hlf, Nfil3, Usf1, Srebf2, Tef
metacluster_1/pattern_9 # seqlets: 782 SequenceContrib ScoresHyp_Contrib Scores	Tal1, Gata1, Gata5, Gata6, Gata4, Gata2, Gata3
metacluster_1/pattern_10 # seqlets: 769 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_11 # seqlets: 320 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_12 # seqlets: 304 SequenceContrib ScoresHyp_Contrib Scores	Tfeb, Arntl, Tfe3, Tfec, Mitf, Bhlhe40, Srebf1, Arnt, Clock, Mlx, Npas2, Tcfl5, Bhlhe41, Myc, Creb3l2, Rxrg, Max, Nr1h4, Mycn
metacluster_1/pattern_13 # seqlets: 197 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Stat1, Stat2, Irf7, Prdm1, Irf4, Irf3, Irf9, Batf3
metacluster_1/pattern_14 # seqlets: 74 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfic, Zfp322a, Nfib
metacluster_1/pattern_15 # seqlets: 46 SequenceContrib ScoresHyp_Contrib Scores