# Parameters
data_name = "ES;JM8.N4;Mitosis;A;GEO"
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_187-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_187-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 19:23:17,413 [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	JM8.N4 Mitosis
Cell Group	ES cells and embryonic tissues
Experiment Name	ATAC
Experiment Group	GEO

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	121173	75150	3.9409	145556657	5190019	0.0357	7256741	0.0499	46929464	0.3225
rep2	121173	75150	3.54	186466550	5825601	0.0312	8392411	0.045	58666393	0.3147

Metric	Value
auPRC	0.6752
Calibrated Recall at 50% FDR	0.219
Number of Positive Examples in Test Data	29932
Number of Negative Examples in Test Data	8040919
Imbalance Ratio in Test Data	0.0037
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 3829 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Klf3, Sp4, Sp1, Klf6, Zfx, Klf15, Klf1, Wt1, Maz, Egr1, Sp5, Zfp281, Zbtb17, E2f4, Klf4, Klf5, Klf7, Klf8, Klf12, Usf2, Egr2, Tfap2c, Rela, E2f1, Nr1h4, Ctcfl
metacluster_0/pattern_1 # seqlets: 2337 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Pbx3, Foxi1
metacluster_0/pattern_2 # seqlets: 1822 SequenceContrib ScoresHyp_Contrib Scores	Ctcf
metacluster_0/pattern_3 # seqlets: 1654 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_4 # seqlets: 1469 SequenceContrib ScoresHyp_Contrib Scores	Sall4, Srebf2, Bcl6, Zscan10, Ptf1a
metacluster_0/pattern_5 # seqlets: 1406 SequenceContrib ScoresHyp_Contrib Scores	Fli1, Gabpa, Ets1, Elk4, Erg, Elk1, Elf1, Etv4, Etv1, Elk3, Fev, Etv2, Etv5, Mbd2, Etv3, XP_911724.4, Etv6, Ehf, Elf2, E2f3, Elf5, Elf3, E2f7, Elf4, Spi1
metacluster_0/pattern_6 # seqlets: 1096 SequenceContrib ScoresHyp_Contrib Scores	Pou5f1, Nanog, Pou2f2, Sox2, Pou2f1
metacluster_0/pattern_7 # seqlets: 870 SequenceContrib ScoresHyp_Contrib Scores	Lef1, Sox30, Sox6, Sry, Sox3, Sox4, Sox12, Sox5, Sox14, Sox7, Sox21, Sox18, Sox8, Sox11
metacluster_0/pattern_8 # seqlets: 799 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Rfx1
metacluster_0/pattern_9 # seqlets: 763 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_0/pattern_10 # seqlets: 744 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Atf7, Jdp2, Crem, Atf1, Creb5, Atf3, Usf1, Fosl2, Jun, Hlf
metacluster_0/pattern_11 # seqlets: 505 SequenceContrib ScoresHyp_Contrib Scores	Tfeb, Arntl, Tfe3, Tfec, Clock, Mitf, Arnt, Srebf1, Bhlhe40, Mlx, Npas2, Mxi1, Tcfl5, Mycn, Rxrg, Bhlhe41, Creb3l2, Max, Rxrb, Myc
metacluster_0/pattern_12 # seqlets: 452 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_13 # seqlets: 407 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_0/pattern_14 # seqlets: 397 SequenceContrib ScoresHyp_Contrib Scores	Fosl1, Fos, Mafk, Jund, Mafg, Mafb, Bach2, Maff, Fosb, Maf, Junb, Batf, Mafa, Nfe2l2, Nfe2, Bach1
metacluster_0/pattern_15 # seqlets: 298 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_16 # seqlets: 254 SequenceContrib ScoresHyp_Contrib Scores	Tead2, Tead4, Tead1
metacluster_0/pattern_17 # seqlets: 248 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_0/pattern_18 # seqlets: 192 SequenceContrib ScoresHyp_Contrib Scores	E2f6
metacluster_0/pattern_19 # seqlets: 172 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_0/pattern_20 # seqlets: 154 SequenceContrib ScoresHyp_Contrib Scores	Tfap2b
metacluster_0/pattern_21 # seqlets: 154 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_22 # seqlets: 84 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_0/pattern_23 # seqlets: 83 SequenceContrib ScoresHyp_Contrib Scores	Zic2, Zic3
metacluster_0/pattern_24 # seqlets: 80 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_25 # seqlets: 67 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_26 # seqlets: 64 SequenceContrib ScoresHyp_Contrib Scores	Grhl2
metacluster_0/pattern_27 # seqlets: 40 SequenceContrib ScoresHyp_Contrib Scores