# Parameters
data_name = "wES;limb;E14.5;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_256-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_256-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 19:38:32,190 [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	mixed embryonic mouse limb(E14.5)
Cell Group	ES cells and embryonic tissues
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	239587	150985	8.7845	142677506	20445407	0.1433	12474716	0.0874	55712084	0.3905
rep2	239587	150985	10.3288	89941398	12652028	0.1407	7884974	0.0877	36579258	0.4068

Metric	Value
auPRC	0.6502
Calibrated Recall at 50% FDR	0.208
Number of Positive Examples in Test Data	130293
Number of Negative Examples in Test Data	7940558
Imbalance Ratio in Test Data	0.0161
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 5368 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 2953 SequenceContrib ScoresHyp_Contrib Scores	Twist1, Tcf21, Olig2, Bhlha15, Msc, Lhx3, Neurog1, Tal1, Atoh1, Lhx1, Lhx5, Bhlhe22, Neurod1, Tfap4, Lmx1b, Ptf1a, Tcf3, Myog, Twist2, Myf6, Prop1, Ascl2, Tcf12, Neurod2, Alx3, Lhx4, Myf5, Tcf4
metacluster_1/pattern_2 # seqlets: 2780 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Sp1, Klf3, Sp5, Sp4, Klf6, Klf15, Wt1, Zbtb17, Maz, Zfx, Klf1, Egr1, Zfp281, Klf5, Rela, Klf4, Egr2, Usf2, E2f4, Fli1, Klf7, E2f1, Mbd2, E2f6, Klf12, Klf8, Mxi1, E2f3, Nr1h4, E2f7
metacluster_1/pattern_3 # seqlets: 1539 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic
metacluster_1/pattern_4 # seqlets: 1266 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_5 # seqlets: 1127 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_6 # seqlets: 991 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elk4, Ets1, Erg, Elk3, Elk1, Etv4, Etv1, Etv3, Etv6, Etv5, XP_911724.4, Elf1, Etv2, Fev, Elf4, Ehf, Elf5, Elf2, Spdef, Elf3, Spi1, Spib, Spic, Irf4, Irf8
metacluster_1/pattern_7 # seqlets: 783 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_8 # seqlets: 763 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Jdp2, Creb5, Creb1, Atf1, Crem, Nfil3, Jun, Dbp, Cebpa, Atf3, Cebpb, Hlf, Srebf1, Mlx, Tfec, Tef, Fosl2, Mafb, Fosl1, Ddit3, Rxrb
metacluster_1/pattern_9 # seqlets: 709 SequenceContrib ScoresHyp_Contrib Scores	Tead2, Tead4, Tead1
metacluster_1/pattern_10 # seqlets: 666 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_1/pattern_11 # seqlets: 552 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx1, Rfx2, Rfx4, Rfx6, Rfx7
metacluster_1/pattern_12 # seqlets: 516 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_1/pattern_13 # seqlets: 478 SequenceContrib ScoresHyp_Contrib Scores	Hoxd13, Hoxa13, Hoxc13, Hoxb13, Hoxa9, Meis1, Cdx2, Hoxd9, Evx1, Hoxd11, Hoxc9, Cdx4, Hoxc11, Hoxc12, Hoxd10, Hoxa11, Hoxc10, Hoxb9, Pbx1, Hoxa10
metacluster_1/pattern_14 # seqlets: 452 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_1/pattern_15 # seqlets: 276 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfe3, Tfeb, Arntl, Mitf, Bhlhe40, Clock, Arnt, Npas2, Srebf2, Mycn, Tcfl5, Max, Myc, Creb3l2, Bhlhe41, Xbp1, Rarg
metacluster_1/pattern_16 # seqlets: 276 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_17 # seqlets: 233 SequenceContrib ScoresHyp_Contrib Scores	Grhl2, Tcfcp2l1
metacluster_1/pattern_18 # seqlets: 176 SequenceContrib ScoresHyp_Contrib Scores	Sox9, Sox4, Sox10, Sox3, Sox6, Sox2, Sox11, Sox12, Sox21, Sox17, Tcf7l2, Lef1, Sox5
metacluster_1/pattern_19 # seqlets: 169 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_20 # seqlets: 167 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_21 # seqlets: 163 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_22 # seqlets: 157 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_23 # seqlets: 128 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_24 # seqlets: 117 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_25 # seqlets: 58 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33