# Parameters
data_name = "RTN;D1;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_234-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_234-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 19:33:20,671 [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	Retina(newborn 1 day)
Cell Group	Neural Cells and Tissues
Experiment Name	DHS
Experiment Group	ENCODE

Metric	Value
auPRC	0.653
Calibrated Recall at 50% FDR	0.192
Number of Positive Examples in Test Data	127996
Number of Negative Examples in Test Data	7942855
Imbalance Ratio in Test Data	0.0159
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 2586 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_1 # seqlets: 2405 SequenceContrib ScoresHyp_Contrib Scores	Sp1, Sp3, Sp4, Sp2, Zbtb17, Klf3, E2f4, Egr1, Klf6, Klf7, E2f1, Klf8, Klf12, Egr2, Zfp281, Sp5, Maz, Klf15, Wt1, Klf1, Klf5, Klf4, E2f7, Zfp740, Sall4, Egr3
metacluster_0/pattern_2 # seqlets: 2022 SequenceContrib ScoresHyp_Contrib Scores	Mxi1, Zfx, Myc, Usf2
metacluster_0/pattern_3 # seqlets: 1653 SequenceContrib ScoresHyp_Contrib Scores	Lhx9, Emx2, Lhx2, Prrx2, Shox2, En2, Rax, Vsx2, Lbx2, Arx, Lhx8, Alx1, Nkx1-2, Gbx1, Uncx, Gbx2, Rhox6, Vsx1, Pax6, Evx1, Gsx2, Vax2, Alx4, Msx3, Nkx1-1, Hoxa2, Pou1f1, Vax1, Lhx6, Lhx3, Pdx1, Alx3, Hoxa1, Hoxd3, Lhx4, Nobox, En1, Noto, Prop1, Hoxb3, Hoxa3, Mnx1, Sebox, Pax7, Prrx1, Msx1, Hoxa5, Otp, Hoxc5, Phox2b, Phox2a, Hoxb5, Esx1, Hoxd1, Pax4, Msx2, Isx, Pou2f2, Bsx, Lmx1b, Dlx5, Evx2, Barhl1, Barhl2, Pou2f3, Hoxb4, Barx1, Meox1, Nkx6-3, Isl1, Lmx1a, Pou3f1, Pou3f2, Hlx, Isl2, Pou2f1, Nkx6-1, Hoxc6, Lhx1, Pou6f1, Barx2, Dbx2, Dlx2, Lhx5, Hoxa4, Dlx4, Hoxb6, Duxbl1, Meox2, Hoxa7, Hoxa6, Dlx3, Hoxc10, Hoxb7, Pou4f3, Dlx1, Dbx1, Tlx2, Nanog, Pou3f4, Hoxc4, Hoxc8, Nkx3-2, Hnf1b, Hoxd13, Hoxa13, Hnf1a, Hoxc13, Nkx3-1, A1JVI6_MOUSE, Hmx2, Hoxc9, Hoxb13, Twist1, Arid3b, Hmbox1
metacluster_0/pattern_4 # seqlets: 1419 SequenceContrib ScoresHyp_Contrib Scores	Atoh1, Neurod2, Ascl1, Neurog2, Neurod1, Ascl2, Olig2, Tal1, Ptf1a, Bhlha15, Msc, Lyl1, Myog, Tcf3, Bhlhe22, Myf6, Myod1, Msgn1, Tcf12, Neurog1, Tcf21, Tfap4, Myf5, Snai1, Tcf4, Tcf7l1, Tgif1, Clock, Meis2, Figla
metacluster_0/pattern_5 # seqlets: 1192 SequenceContrib ScoresHyp_Contrib Scores	Sox3, Sox6, Sox2, Sox17, Sox9, Sox4, Sox12, Foxd1, Pou5f1, Sox10, Sry
metacluster_0/pattern_6 # seqlets: 1104 SequenceContrib ScoresHyp_Contrib Scores	Crx, Obox1, Otx2, Dmbx1, Pitx1, Obox6, Otx1, Pitx2, Pitx3, Mzf1, Obox5, Q8VHG7_MOUSE
metacluster_0/pattern_7 # seqlets: 922 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_8 # seqlets: 855 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx1, Rfx4, Rfx6, Rfx7
metacluster_0/pattern_9 # seqlets: 691 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elf1, Elk1, Elk3, Fli1, Elk4, Erg, Elf5, Ets1, Etv5, Etv1, Elf2, Etv4, Fev, Etv6, Elf4, Ehf, XP_911724.4, Etv3, Elf3, Spi1, Etv2, Spdef, Spic
metacluster_0/pattern_10 # seqlets: 683 SequenceContrib ScoresHyp_Contrib Scores	Rorc, Rora, Pparg, Ppara, Nr1d2, Nr1d1, Esr2
metacluster_0/pattern_11 # seqlets: 555 SequenceContrib ScoresHyp_Contrib Scores	Atf2, Atf7, Creb1, Crem, Jdp2, Atf1, Creb5, Atf3, Fosl2, Nfil3, Jun, Rxrb, Srebf1, Tfec, Tef
metacluster_0/pattern_12 # seqlets: 545 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic
metacluster_0/pattern_13 # seqlets: 542 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_14 # seqlets: 452 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Mitf, Tfeb, Tfe3, Arntl, Npas2, Arnt, Mlx, Bhlhe40, Creb3l2, Srebf2, Mycn, Tcfl5, Xbp1, Bhlhe41, Max, Mlxip
metacluster_0/pattern_15 # seqlets: 397 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_16 # seqlets: 342 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_0/pattern_17 # seqlets: 249 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_18 # seqlets: 138 SequenceContrib ScoresHyp_Contrib Scores	Pax5
metacluster_0/pattern_19 # seqlets: 124 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_20 # seqlets: 95 SequenceContrib ScoresHyp_Contrib Scores	Tfap2a, Tfap2c, Tfap2b, Tfap2e
metacluster_0/pattern_21 # seqlets: 91 SequenceContrib ScoresHyp_Contrib Scores	Jund, Fosl1, Junb, Fosb, Fos, Batf, Nfe2, Nfe2l2, Mafa, Bach2, Mafk
metacluster_0/pattern_22 # seqlets: 97 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_23 # seqlets: 48 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2c, Mef2a
metacluster_0/pattern_24 # seqlets: 52 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_25 # seqlets: 37 SequenceContrib ScoresHyp_Contrib Scores