# Parameters
data_name = "DP3b;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_48-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_48-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 18:50:41,867 [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	DN3b
Cell Group	T cells
Experiment Name	ATAC
Experiment Group	Casellas Lab

Metric	Value
auPRC	0.582
Calibrated Recall at 50% FDR	0.247
Number of Positive Examples in Test Data	105288
Number of Negative Examples in Test Data	7965563
Imbalance Ratio in Test Data	0.013
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 5084 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 4061 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Elk1, Etv2, Etv4, Gabpa, Elk4, Fli1, Elf2, Spi1, Etv6, Elk3, Ehf, Etv5, Spib, Fev, Elf1, Elf3, Etv1, Etv3, XP_911724.4, Elf4, Ets2, Irf8, Irf4, Stat4, Elf5, Spic
metacluster_1/pattern_2 # seqlets: 3263 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Klf3, Sp4, Sp1, Klf6, Zfx, Klf15, Wt1, Klf1, Egr1, Maz, Sp5, E2f4, Zfp281, Klf5, Zbtb17, Klf4, Klf7, Klf8, Klf12, Usf2, Egr2, Tfap2c, E2f1, Nr1h4, Ptf1a, Srebf2
metacluster_1/pattern_3 # seqlets: 1705 SequenceContrib ScoresHyp_Contrib Scores	Tcf3, Snai2, Myf6, Tcf4, Ascl2, Ascl1, Tcf12, Tcf7l1, Myog, Myod1, Mnt, Nhlh2, Snai1, Pknox2, Hes5, Myf5, Tal1, Meis2, Meis3, Bhlha15, Nhlh1, Hey2, Figla
metacluster_1/pattern_4 # seqlets: 1545 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_5 # seqlets: 1495 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_6 # seqlets: 1160 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Foxi1, Nfyc, Nfya, Pbx3
metacluster_1/pattern_7 # seqlets: 958 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Stat1, Irf7, Prdm1, Irf3, Stat2, Irf9, Batf3
metacluster_1/pattern_8 # seqlets: 728 SequenceContrib ScoresHyp_Contrib Scores	Tcf7l2, Lef1, Tcf7
metacluster_1/pattern_9 # seqlets: 609 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_10 # seqlets: 591 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_11 # seqlets: 567 SequenceContrib ScoresHyp_Contrib Scores	Hes7, Hes1
metacluster_1/pattern_12 # seqlets: 496 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfe3, Tfeb, Arntl, Tfec, Mitf, Srebf1, Bhlhe40, Clock, Arnt, Mlx, Npas2, Creb3l2, Tcfl5, Mycn, Max, Bhlhe41, Atf1, Myc, Creb1, Atf7, Hlf, Atf2, Jdp2, Xbp1, Dbp
metacluster_1/pattern_13 # seqlets: 481 SequenceContrib ScoresHyp_Contrib Scores	Creb5, Crem, Atf3, Mafb, Fosl2, Nfil3, Fosl1, Rxrb, Tef, Jun
metacluster_1/pattern_14 # seqlets: 322 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx1, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_15 # seqlets: 75 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic
metacluster_1/pattern_16 # seqlets: 64 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2
metacluster_1/pattern_17 # seqlets: 37 SequenceContrib ScoresHyp_Contrib Scores	Rest