# Parameters
data_name = "DP3a;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_47-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_47-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 18:50:30,981 [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	DN3a
Cell Group	T cells
Experiment Name	ATAC
Experiment Group	Casellas Lab

Metric	Value
auPRC	0.5771
Calibrated Recall at 50% FDR	0.238
Number of Positive Examples in Test Data	126544
Number of Negative Examples in Test Data	7944307
Imbalance Ratio in Test Data	0.0157
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 5526 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Etv4, Etv2, Elk1, Elk4, Fli1, Gabpa, Spi1, Etv6, Elf2, Ehf, Etv5, Elk3, Spib, Elf1, Elf3, Fev, Etv3, XP_911724.4, Etv1, Ets2, Elf4, Irf8, Irf4, Stat4, Elf5, Spic
metacluster_1/pattern_1 # seqlets: 5362 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_2 # seqlets: 3096 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Sp4, Klf3, Sp1, Klf6, E2f4, Klf4, Sp5, Klf7, Egr1, Zbtb17, Klf5, Klf8, Klf12, Wt1, Egr2, Zfp281, Klf1, Maz, E2f1, Klf15, Srebf2
metacluster_1/pattern_3 # seqlets: 2145 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_4 # seqlets: 1429 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_5 # seqlets: 1015 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Prdm1, Stat1, Irf3, Irf7, Stat2, Irf9, Batf3
metacluster_1/pattern_6 # seqlets: 1011 SequenceContrib ScoresHyp_Contrib Scores	Nrf1, Zfx
metacluster_1/pattern_7 # seqlets: 779 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_8 # seqlets: 779 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_9 # seqlets: 549 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Zfp42, Mxi1
metacluster_1/pattern_10 # seqlets: 534 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Usf2, Atf2, Atf7, Jdp2, Crem, Atf1, Creb5, Atf3, Usf1, Fosl2, Hlf, Nfil3
metacluster_1/pattern_11 # seqlets: 457 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_12 # seqlets: 404 SequenceContrib ScoresHyp_Contrib Scores	Tfe3, Tfec, Tfeb, Arntl, Mitf, Srebf1, Bhlhe40, Clock, Mlx, Arnt, Npas2, Tcfl5, Creb3l2, Mycn, Max, Bhlhe41, Myc, Dbp, Mlxip, Xbp1
metacluster_1/pattern_13 # seqlets: 288 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx4, Rfx7, Rfx6, Sox2, Pou5f1
metacluster_1/pattern_14 # seqlets: 196 SequenceContrib ScoresHyp_Contrib Scores	Bach2, Nfe2l2, Nfe2, Bach1, Mafk, Mafa, Mafb, Mafg, Maff, Jun, Maf, Fosb, Fosl1, Junb, Jund, Batf, Fos
metacluster_1/pattern_15 # seqlets: 151 SequenceContrib ScoresHyp_Contrib Scores	Gata3, Gata4, Mecom
metacluster_1/pattern_16 # seqlets: 92 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_17 # seqlets: 69 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib
metacluster_1/pattern_18 # seqlets: 54 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_19 # seqlets: 42 SequenceContrib ScoresHyp_Contrib Scores