# Parameters
data_name = "restingB;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_73-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_73-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 18:56:50,799 [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	restingB
Cell Group	B cells
Experiment Name	ATAC
Experiment Group	Casellas Lab

Metric	Value
auPRC	0.7228
Calibrated Recall at 50% FDR	0.16
Number of Positive Examples in Test Data	39260
Number of Negative Examples in Test Data	8031591
Imbalance Ratio in Test Data	0.0049
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 4737 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 3920 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Etv6, Spi1, Etv2, Erg, Spib, Gabpa, Elk1, Fli1, Etv4, Etv3, XP_911724.4, Elk4, Spic, Elk3, Etv5, Elf1, Etv1, Elf4, Irf4, Irf8, Elf2, Ehf, Elf3, Elf5, Spdef, Fev, Prdm1, Irf2, Irf1, Irf3
metacluster_1/pattern_2 # seqlets: 3775 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf6, Klf7, Klf4, Klf1, Klf8, Klf12, Egr1, Zbtb17, Egr2, E2f1, Sp5, Klf5, Zfp281, Zfx, Zfp740
metacluster_1/pattern_3 # seqlets: 2048 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_4 # seqlets: 1699 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_5 # seqlets: 1530 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Jdp2, Atf2, Atf7, Creb5, Atf1, Crem, Jun, Atf3, Gmeb2, Fosl2, Junb
metacluster_1/pattern_6 # seqlets: 1217 SequenceContrib ScoresHyp_Contrib Scores	Yy1, Taf1, Rfx1, Zfp42
metacluster_1/pattern_7 # seqlets: 1076 SequenceContrib ScoresHyp_Contrib Scores	Stat2, Irf7, Stat1, Zscan10, Irf9
metacluster_1/pattern_8 # seqlets: 998 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_9 # seqlets: 782 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Usf2, Tfec, Arntl, Tfeb, Mitf, Bhlhe40, Srebf1, Tfe3, Clock, Mlx, Arnt, Npas2, Srebf2, Tcfl5, Creb3l2, Bhlhe41, Xbp1, Hlf, Mlxip, Dbp, Max, Arnt2
metacluster_1/pattern_10 # seqlets: 458 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2
metacluster_1/pattern_11 # seqlets: 334 SequenceContrib ScoresHyp_Contrib Scores	Wt1, Maz, Klf15, Sall4, Mxi1, Tfap2c
metacluster_1/pattern_12 # seqlets: 241 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_13 # seqlets: 140 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_14 # seqlets: 125 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_15 # seqlets: 109 SequenceContrib ScoresHyp_Contrib Scores	Nfkb2, Nfkb1, Rela, Relb, Rel
metacluster_1/pattern_16 # seqlets: 107 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2c, Mef2a
metacluster_1/pattern_17 # seqlets: 41 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Zfp322a, Nfic