# Parameters
data_name = "LNG;8wks;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_227-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_227-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 19:31:23,750 [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	Lung(adult-8wks)
Cell Group	Other 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	260857	184646	6.1606	230472976	NA	NA	NA	NA	NA	NA
rep2	260857	184646	12.1179	22295185	3892858	0.1747	2513194	0.1128	9786489	0.4392
rep3	260857	184646	12.532	22241916	3299640	0.1484	2213542	0.0996	9566384	0.4303

Metric	Value
auPRC	0.5492
Calibrated Recall at 50% FDR	0.253
Number of Positive Examples in Test Data	146818
Number of Negative Examples in Test Data	7924033
Imbalance Ratio in Test Data	0.0182
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 3193 SequenceContrib ScoresHyp_Contrib Scores	Etv4, Etv2, Etv6, Ets1, Fli1, Erg, Etv3, Gabpa, XP_911724.4, Elk1, Elk4, Spic, Elk3, Spi1, Spib, Etv1, Elf4, Elf2, Etv5, Ehf, Elf3, Elf5, Irf8, Irf4, Spdef, Elf1, Fev, Pgr
metacluster_0/pattern_1 # seqlets: 2598 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_2 # seqlets: 2493 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Cebpd, Dbp, Nfil3, Hlf, Cebpg, Atf4, Ddit3, Cebpe, Tef, Pou3f3
metacluster_0/pattern_3 # seqlets: 2364 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp1, Sp3, Sp2, Klf3, Zbtb17, E2f4, Klf6, Egr1, Klf7, Klf8, Klf12, E2f1, Sp5, Egr2, Klf15, Wt1, Klf1, Klf4, Klf5, Zfp281, Maz, Egr3, E2f7, Nhlh1
metacluster_0/pattern_4 # seqlets: 1679 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_0/pattern_5 # seqlets: 1563 SequenceContrib ScoresHyp_Contrib Scores	Foxa1, Foxc1, Foxc2, Foxb1, Foxd1, Foxa2, Foxm1, Foxj2, Foxl1, Foxk1, Foxg1, Foxd3, Foxl2, Foxj3, Gm5294, Foxa3, Foxp2, Foxo3, Foxp1, Foxq1, Foxj1
metacluster_0/pattern_6 # seqlets: 1043 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Jdp2, Atf7, Atf2, Creb5, Atf1, Crem, Jun, Mafb, Fosl1, Atf3, Jund, Gmeb2, Junb, Fosl2, Gmeb1, Rxrb, Rora, Esr2
metacluster_0/pattern_7 # seqlets: 1002 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_8 # seqlets: 820 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_9 # seqlets: 809 SequenceContrib ScoresHyp_Contrib Scores	Nkx2-6, Nkx2-4, Nkx2-1, Nkx2-5, Nkx2-9, Nkx2-3, Nkx2-2, Nkx3-1, Nkx3-2, Hmx1, Hmx2
metacluster_0/pattern_10 # seqlets: 761 SequenceContrib ScoresHyp_Contrib Scores	Fosb, Fos, Bach2, Batf, Nfe2l2, Nfe2, Bach1, Mafa, Mafk
metacluster_0/pattern_11 # seqlets: 674 SequenceContrib ScoresHyp_Contrib Scores	Tfe3, Usf1, Usf2, Tfeb, Arntl, Npas2, Clock, Bhlhe40, Mitf, Arnt, Tfec, Srebf1, Mlx, Bhlhe41, Creb3l2, Hey2, Xbp1, Max, Myc, Srebf2, Tcfl5, Mycn, Mlxip, Arnt2, Hes2, Hes5, Hes1, Epas1
metacluster_0/pattern_12 # seqlets: 642 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf7, Stat2, Prdm1, Stat1, Irf9, Irf5, Irf3, Irf6
metacluster_0/pattern_13 # seqlets: 597 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead2, Tead1
metacluster_0/pattern_14 # seqlets: 433 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_15 # seqlets: 297 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Zfx, Zfp42, Mxi1
metacluster_0/pattern_16 # seqlets: 265 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_0/pattern_17 # seqlets: 262 SequenceContrib ScoresHyp_Contrib Scores	Lyl1, Olig2, Twist1, Myog, Tal1, Ptf1a, Bhlha15, Figla, Tfap4, Tcf3, Tcf21, Ascl2, Atoh1, Neurod1, Tcf12, Ascl1, Msc, Neurod2, Snai1, Myf6, Myod1, Myf5, Tcf7l1, Tcf4
metacluster_0/pattern_18 # seqlets: 257 SequenceContrib ScoresHyp_Contrib Scores	Grhl2
metacluster_0/pattern_19 # seqlets: 169 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_0/pattern_20 # seqlets: 151 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx6, Rfx7
metacluster_0/pattern_21 # seqlets: 139 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_22 # seqlets: 126 SequenceContrib ScoresHyp_Contrib Scores	Gata1, Gata2, Gata6, Gata4, Gata3, Gata5
metacluster_0/pattern_23 # seqlets: 72 SequenceContrib ScoresHyp_Contrib Scores	Hnf1b, Hnf1a
metacluster_0/pattern_24 # seqlets: 50 SequenceContrib ScoresHyp_Contrib Scores