# Parameters
data_name = "Adipocyte_3T3-L1D;C57BL6;D8;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_232-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_232-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 19:32:52,487 [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	Mus musculus C57BL/6 adipocyte was differentiated from 3T3-L1 (Day 8)
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	185616	138619	8.4736	60982669	9879435	0.1621	5831935	0.0957	23647842	0.3879
rep2	185616	138619	4.4494	253967456	NA	NA	NA	NA	NA	NA

Metric	Value
auPRC	0.5294
Calibrated Recall at 50% FDR	0.244
Number of Positive Examples in Test Data	133720
Number of Negative Examples in Test Data	7937131
Imbalance Ratio in Test Data	0.0166
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 4358 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 2720 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Cebpd, Nfil3, Dbp, Cebpg, Hlf, Atf4, Ddit3, Cebpe, Tef, Pou3f3
metacluster_1/pattern_2 # seqlets: 2675 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf6, Klf7, Klf4, Egr1, Klf8, Klf12, Klf1, Zbtb17, Egr2, Sp5, E2f1, Zfp281, Klf5, Zfx, Egr3, Zfp740, Wt1
metacluster_1/pattern_3 # seqlets: 1472 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic
metacluster_1/pattern_4 # seqlets: 1395 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Fli1, Elk1, Elk4, Ets1, Erg, Elk3, Elf1, Fev, Etv5, Etv4, Etv1, Etv6, Ehf, XP_911724.4, Elf5, Etv3, Elf2, Etv2, Elf4, Spi1, Spdef, Elf3
metacluster_1/pattern_5 # seqlets: 1117 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfya, Nfyc, Foxi1, Pbx3
metacluster_1/pattern_6 # seqlets: 1068 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Usf2, Atf7, Atf2, Jdp2, Atf1, Crem, Creb5, Usf1, Atf3, Tfe3, Tfec, Fosl2, Srebf1, Srebf2, Bhlhe40, Mitf, Tfeb, Mlx
metacluster_1/pattern_7 # seqlets: 1008 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_8 # seqlets: 878 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_9 # seqlets: 843 SequenceContrib ScoresHyp_Contrib Scores	Ppara, Pparg, Nr2c2, Nr2f1, Rxrb, Rxra, Nr2f6, Rora, Nr4a2, Nr1h3, Rorc, Hnf4g, Nr2c1, Nr1d2, Nr1d1, Nr5a2, Nr2e3, Rarg, Esrrg, Hnf4a, Rara, Esrra, Zfp57, Nr5a1
metacluster_1/pattern_10 # seqlets: 786 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Zfp42
metacluster_1/pattern_11 # seqlets: 774 SequenceContrib ScoresHyp_Contrib Scores	Bach2, Jun, Nfe2l2, Nfe2, Fos, Fosl1, Jund, Batf, Fosb, Bach1, Junb, Mafk, Mafg, Mafb, Maf, Mafa, Maff
metacluster_1/pattern_12 # seqlets: 587 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf7, Irf2, Irf8, Irf4, Irf9, Spib, Stat2, Irf3, Stat1, Prdm1, Irf5
metacluster_1/pattern_13 # seqlets: 510 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_1/pattern_14 # seqlets: 224 SequenceContrib ScoresHyp_Contrib Scores	Foxd3, Foxa3, Foxc1, Foxa2, Foxp2, Foxd1, Foxo3, Foxj3, Foxa1, Foxk1, Foxj2, Foxc2, Foxb1, Foxg1, Foxo4, Foxl1, Foxl2, Foxp1, Foxq1, Gm5294, Foxm1, Foxj1, Foxo1
metacluster_1/pattern_15 # seqlets: 145 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_16 # seqlets: 127 SequenceContrib ScoresHyp_Contrib Scores	Twist1
metacluster_1/pattern_17 # seqlets: 117 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_18 # seqlets: 74 SequenceContrib ScoresHyp_Contrib Scores	Ebf1, Prdm16
metacluster_1/pattern_19 # seqlets: 56 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_20 # seqlets: 53 SequenceContrib ScoresHyp_Contrib Scores	Rest