# Parameters
data_name = "MEF.GATA-1-ER;D;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_272-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_272-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 19:42:29,311 [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	MEL-GATA-1-ER cell line
Cell Group	Cancer or Immortalized cells
Experiment Name	DHS
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	118042	85788	12.7996	13596350	3738330	0.2753	2259805	0.1664	5907310	0.4351
rep2	118042	85788	21.1754	2836542	778497	0.2763	629312	0.2234	1225797	0.4351
rep3	118042	85788	15.6108	14644325	4525109	0.3094	3001958	0.2053	6225773	0.4257
rep4	118042	85788	10.3328	12508650	2933346	0.2349	1936566	0.1551	5356420	0.4289
rep5	118042	85788	18.308	3795062	889776	0.2357	811630	0.215	1625900	0.4306

Metric	Value
auPRC	0.5226
Calibrated Recall at 50% FDR	0.224
Number of Positive Examples in Test Data	115113
Number of Negative Examples in Test Data	7955738
Imbalance Ratio in Test Data	0.0143
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 11007 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 3756 SequenceContrib ScoresHyp_Contrib Scores	Spi1, Spib, Irf8, Irf4, Spic, Elf3, Etv2, Irf3, Prdm1, Ehf, Etv6, Etv4, Irf2, Irf1, Elf4, Ets1, Elf2, Elf5, Etv3, Gabpa, Elk1, Fli1, XP_911724.4
metacluster_1/pattern_2 # seqlets: 3457 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf6, Klf7, Egr1, Klf4, Klf1, Klf8, Klf12, Zbtb17, Egr2, E2f1, Sp5, Zfp281, Zfx, Klf5
metacluster_1/pattern_3 # seqlets: 1385 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Foxi1, Nfya, Nfyc, Pbx3
metacluster_1/pattern_4 # seqlets: 1330 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_5 # seqlets: 745 SequenceContrib ScoresHyp_Contrib Scores	Erg, Elk4, Elf1, Elk3, Etv5, Etv1, Fev, Spdef
metacluster_1/pattern_6 # seqlets: 629 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_7 # seqlets: 526 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic, Zfp322a
metacluster_1/pattern_8 # seqlets: 518 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Usf2, Jdp2, Atf7, Crem, Atf1, Creb5, Atf3, Hlf, Fosl2, Nfil3, Usf1, Jun, Tef, Rfx1, Fosl1, Dbp, Cebpb
metacluster_1/pattern_9 # seqlets: 501 SequenceContrib ScoresHyp_Contrib Scores	Gata5, Gata6, Tal1, Gata1, Gata4, Gata2, Gata3
metacluster_1/pattern_10 # seqlets: 487 SequenceContrib ScoresHyp_Contrib Scores	Nfe2, Nfe2l2, Bach2, Bach1, Mafk, Mafa, Mafb, Mafg, Maff, Fosb, Maf, Junb, Jund, Fos, Batf
metacluster_1/pattern_11 # seqlets: 228 SequenceContrib ScoresHyp_Contrib Scores	Tfe3, Tfeb, Tfec, Arntl, Mitf, Bhlhe40, Srebf1, Clock, Arnt, Mlx, Srebf2, Npas2, Mxi1, Tcfl5, Rxrg, Bhlhe41, Nr1h4, Rxrb, Creb3l2, Mycn
metacluster_1/pattern_12 # seqlets: 204 SequenceContrib ScoresHyp_Contrib Scores	Stat1, Stat2, Irf7, Irf9, Batf3
metacluster_1/pattern_13 # seqlets: 155 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_14 # seqlets: 116 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_1/pattern_15 # seqlets: 101 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_16 # seqlets: 98 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_17 # seqlets: 98 SequenceContrib ScoresHyp_Contrib Scores	Rest