# Parameters
data_name = "Fr_BRN;P0;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_246-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_246-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 19:35:19,948 [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	forebrain(P0)
Cell Group	Neural Cells and Tissues
Experiment Name	DHS
Experiment Group	ENCODE

Metric	Value
auPRC	0.6542
Calibrated Recall at 50% FDR	0.185
Number of Positive Examples in Test Data	142042
Number of Negative Examples in Test Data	7928809
Imbalance Ratio in Test Data	0.0176
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 3142 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 2446 SequenceContrib ScoresHyp_Contrib Scores	Sp3, Sp1, Sp2, Sp4, Klf3, Zbtb17, Sp5, Klf4, Klf5, E2f4, Klf6, Zfp281, Wt1, Klf7, Egr1, Maz, Klf8, Klf12, Egr2, E2f1, Klf15, Srebf2, Sall4, Klf1, Bcl6
metacluster_1/pattern_2 # seqlets: 2447 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib
metacluster_1/pattern_3 # seqlets: 1494 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_4 # seqlets: 1458 SequenceContrib ScoresHyp_Contrib Scores	Neurod1, Neurog2, Neurod2, Olig2, Atoh1, Tcf21, Bhlhe22, Lyl1, Neurog1, Bhlha15, Msc, Twist2, Msgn1, Myog, Tal1, Tfap4, Twist1, Tcf12
metacluster_1/pattern_5 # seqlets: 1290 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx1, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_6 # seqlets: 1032 SequenceContrib ScoresHyp_Contrib Scores	Sox4, Sox3, Sox9, Sox2, Sox17, Sox6, Tcf7, Nanog, Lef1
metacluster_1/pattern_7 # seqlets: 889 SequenceContrib ScoresHyp_Contrib Scores	Nrf1, Zfx
metacluster_1/pattern_8 # seqlets: 886 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_9 # seqlets: 806 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elf1, Fli1, Elk1, Elk4, Elk3, Erg, Ets1, Fev, Etv5, Elf5, Etv1, Etv4, Elf2, Etv6, Elf4, Ehf, Etv3, XP_911724.4, Spi1, Etv2, Elf3, Spdef
metacluster_1/pattern_10 # seqlets: 789 SequenceContrib ScoresHyp_Contrib Scores	Pou2f1, Prrx1, Otp, Lhx2, Phox2b, Gbx1, Phox2a, Esx1, Alx3, Isx, En2, Evx2, Prrx2, Hoxa2, Prop1, Lhx3, Noto, Uncx, Rax, Hoxd3, Lhx8, Lhx4, Pax6, Nkx1-2, Msx1, Hoxd1, Vsx1, Vsx2, Pou1f1, Pax7, Lmx1b, Gbx2, Alx1, Rhox6, Lhx9, En1, Hnf1a, Msx3, Nobox, Arx, Shox2, Emx2, Hoxc5, Msx2, Pou2f2, Lhx5, Pou2f3, Nkx1-1, Hoxa1, Gsx2, Alx4, Dlx3, Lhx1, Sebox, Lbx2, Hoxc6, Barhl1, Vax2, Evx1, Pdx1, Hlx, Pou3f1, Barx1, Vax1, Lhx6, Pou6f1, Nkx6-1, Arid3b, Pou3f2, Hoxa4, Hoxa3, Pou4f3, Dlx1, Hoxb3, Dbx1, Isl2, Dlx2, Mnx1, Hoxa5, Hoxb4, Lmx1a, Tlx2, Pax4, Pou3f4, Meox1
metacluster_1/pattern_11 # seqlets: 681 SequenceContrib ScoresHyp_Contrib Scores	Pou5f1
metacluster_1/pattern_12 # seqlets: 673 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Atf1, Creb1, Creb5, Jdp2, Crem, Tfec, Srebf1, Mlx, Bhlhe40, Usf1, Mitf, Rxrb, Tfe3, Nfil3, Dbp, Usf2, Atf3, Hlf, Jun, Tef, Creb3l2, Tfeb, Mafb, Cebpb, Xbp1, Cebpa, Arntl, Fosl2
metacluster_1/pattern_13 # seqlets: 521 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_14 # seqlets: 515 SequenceContrib ScoresHyp_Contrib Scores	Mef2a, Mef2d, Mef2c
metacluster_1/pattern_15 # seqlets: 466 SequenceContrib ScoresHyp_Contrib Scores	Ascl2, Ascl1, Myod1, Ptf1a, Myf5, Tcf3, Myf6, Tgif1, Meis2, Tcf4, Figla, Tcf7l1, Snai1
metacluster_1/pattern_16 # seqlets: 353 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Mxi1
metacluster_1/pattern_17 # seqlets: 309 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_18 # seqlets: 95 SequenceContrib ScoresHyp_Contrib Scores	Fos, Jund, Fosl1, Fosb, Batf, Junb, Mafa, Mafk, Bach2, Nfe2, Nfe2l2, Mafg, Maf, Bach1, Maff