# Parameters
data_name = "ISP;A;CL"
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_49-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_49-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 18:50:46,294 [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	ISP (Immature single positive)
Cell Group	T cells
Experiment Name	ATAC
Experiment Group	Casellas Lab

Metric	Value
auPRC	0.5958
Calibrated Recall at 50% FDR	0.234
Number of Positive Examples in Test Data	106087
Number of Negative Examples in Test Data	7964764
Imbalance Ratio in Test Data	0.0131
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 4684 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Fli1, Etv4, Elk1, Gabpa, Elk4, Etv2, Spi1, Etv5, Elk3, Etv6, Elf2, Fev, Etv1, Etv3, XP_911724.4, Spib, Elf1, Ehf, Elf4, Elf5, Irf8, Elf3, Irf4, Spic, Spdef, Zscan10
metacluster_1/pattern_1 # seqlets: 3283 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_2 # seqlets: 2363 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Klf3, Sp4, Sp1, Klf6, Klf4, E2f4, Klf7, Klf5, Egr1, Klf8, Klf12, Sp5, Zbtb17, Egr2, Klf1, Wt1, Zfp281, Maz, E2f1, Klf15, Srebf2, Sall4, Zfp740
metacluster_1/pattern_3 # seqlets: 1534 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfya, Nfyc, Pbx3, Foxi1
metacluster_1/pattern_4 # seqlets: 1113 SequenceContrib ScoresHyp_Contrib Scores	Tcf3, Ascl2, Myf6, Myog, Ascl1, Tcf7l1, Myod1, Ptf1a, Nhlh2, Bhlha15, Tcf12, Myf5, Tal1, Tcf4, Nhlh1, Snai2, Atoh1, Tgif1, Tcf21, Lyl1, Olig2, Meis2, Mnt, Meis3, Pknox2, Snai1, Neurod2, Figla
metacluster_1/pattern_5 # seqlets: 976 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_6 # seqlets: 950 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_7 # seqlets: 829 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf7, Prdm1, Stat1, Irf9, Stat2, Irf3, Batf3, Irf5
metacluster_1/pattern_8 # seqlets: 735 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Creb1, Atf2, Jdp2, Atf1, Crem, Creb5, Atf3, Usf2, Fosl2, Jun, Usf1, Nfil3, Tef, Hlf
metacluster_1/pattern_9 # seqlets: 692 SequenceContrib ScoresHyp_Contrib Scores	Zfx, Zfp335, Mxi1
metacluster_1/pattern_10 # seqlets: 687 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_11 # seqlets: 634 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx3, Runx2, Cbfb
metacluster_1/pattern_12 # seqlets: 500 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Zfp42
metacluster_1/pattern_13 # seqlets: 490 SequenceContrib ScoresHyp_Contrib Scores	Tfe3, Tfeb, Mitf, Arntl, Tfec, Clock, Srebf1, Bhlhe40, Arnt, Mlx, Npas2, Mycn, Tcfl5, Creb3l2, Max, Myc, Bhlhe41, Xbp1
metacluster_1/pattern_14 # seqlets: 470 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_15 # seqlets: 423 SequenceContrib ScoresHyp_Contrib Scores	Tcf7l2, Lef1, Tcf7
metacluster_1/pattern_16 # seqlets: 288 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx6, Rfx7
metacluster_1/pattern_17 # seqlets: 106 SequenceContrib ScoresHyp_Contrib Scores	Mef2c, Mef2a, Mef2d
metacluster_1/pattern_18 # seqlets: 45 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic