# Parameters
data_name = "wES;Md_BRN;E11.5;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_251-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_251-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 19:36:14,713 [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	midbrain embryo(E11.5)
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	160380	115252	13.0985	76978972	13877552	0.1803	9356918	0.1216	29823067	0.3875
rep2	160380	115252	8.2951	64561157	10010016	0.1551	8448062	0.1309	23640519	0.3662

Metric	Value
auPRC	0.728
Calibrated Recall at 50% FDR	0.158
Number of Positive Examples in Test Data	141008
Number of Negative Examples in Test Data	7929843
Imbalance Ratio in Test Data	0.0175
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 3262 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_1 # seqlets: 2987 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_2 # seqlets: 1864 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Sp4, Sp1, Klf3, Klf6, Klf1, E2f4, Klf7, Klf4, Zfx, Klf8, Klf12, Egr1, Zbtb17, Klf5, E2f1, E2f7, Wt1, Egr2, Klf15, Zfp281, Maz, Zfp740, Fli1
metacluster_0/pattern_3 # seqlets: 1635 SequenceContrib ScoresHyp_Contrib Scores	Sox3, Sox4, Sox9, Sox2, Sox17, Sox6, Nanog, Lef1, Tcf7, Sox12
metacluster_0/pattern_4 # seqlets: 1518 SequenceContrib ScoresHyp_Contrib Scores	Atoh1, Neurod2, Neurog2, Ascl1, Neurod1, Ascl2, Bhlha15, Olig2, Myog, Tcf3, Ptf1a, Myod1, Tal1, Lyl1, Myf6, Tcf12, Tcf7l1, Tgif1, Myf5, Tcf4, Msc, Meis2, Snai1, Bhlhe22, Meis3, Tfap4, Snai2, Pknox2, Tcf21, Figla
metacluster_0/pattern_5 # seqlets: 1124 SequenceContrib ScoresHyp_Contrib Scores	Sp5, Rela, Bcl6, Sall4, E2f6, Srebf2
metacluster_0/pattern_6 # seqlets: 853 SequenceContrib ScoresHyp_Contrib Scores	Pou2f1, Lmx1b, Pou2f3, Pou3f1, Vsx1
metacluster_0/pattern_7 # seqlets: 655 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx1, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_0/pattern_8 # seqlets: 523 SequenceContrib ScoresHyp_Contrib Scores	Pou5f1, Pou2f2
metacluster_0/pattern_9 # seqlets: 465 SequenceContrib ScoresHyp_Contrib Scores	Ebf1, Prdm16
metacluster_0/pattern_10 # seqlets: 451 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_11 # seqlets: 437 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elk1, Elf1, Elk3, Elk4, Erg, Ets1, Elf5, Etv5, Etv1, Etv4, Elf2, Fev, Elf4, Ehf, Etv6, Etv3, XP_911724.4, Elf3, Spi1, Etv2, Spdef, Spic
metacluster_0/pattern_12 # seqlets: 282 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_13 # seqlets: 235 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_14 # seqlets: 222 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Atf1, Creb5, Jdp2, Creb1, Crem, Nfil3, Jun, Mafb, Rxrb, Dbp, Tfec, Hlf, Atf3, Srebf1, Tef, Cebpb, Cebpa, Mlx
metacluster_0/pattern_15 # seqlets: 221 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Usf2, Mxi1
metacluster_0/pattern_16 # seqlets: 203 SequenceContrib ScoresHyp_Contrib Scores	Tfe3, Usf1, Tfeb, Arntl, Mitf, Bhlhe40, Arnt, Clock, Npas2, Creb3l2, Tcfl5, Bhlhe41, Max, Mycn, Myc, Xbp1
metacluster_0/pattern_17 # seqlets: 189 SequenceContrib ScoresHyp_Contrib Scores	Hoxb8, Hoxb7, Hoxb4, Pdx1
metacluster_0/pattern_18 # seqlets: 191 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_19 # seqlets: 141 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_20 # seqlets: 132 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_0/pattern_21 # seqlets: 85 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_22 # seqlets: 66 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_23 # seqlets: 62 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_24 # seqlets: 52 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_25 # seqlets: 46 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_26 # seqlets: 44 SequenceContrib ScoresHyp_Contrib Scores	Sox1, Phf21a, Pou3f2
metacluster_0/pattern_27 # seqlets: 42 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_28 # seqlets: 38 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_29 # seqlets: 40 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_30 # seqlets: 56 SequenceContrib ScoresHyp_Contrib Scores	Rest