# Parameters
data_name = "Th17;CD4+;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_3-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_3-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 18:41:46,054 [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	Th17 CD4
Cell Group	T cells
Experiment Name	ATAC
Experiment Group	Casellas Lab

Metric	Value
auPRC	0.6069
Calibrated Recall at 50% FDR	0.22
Number of Positive Examples in Test Data	97092
Number of Negative Examples in Test Data	7973759
Imbalance Ratio in Test Data	0.012
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 5033 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 4851 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Elk1, Etv4, Gabpa, Fli1, Elk4, Spi1, Etv2, Elk3, Etv5, Etv6, Fev, Elf2, Etv1, Spib, XP_911724.4, Etv3, Elf1, Elf4, Ehf, Elf5, Irf8, Irf4, Spic, Elf3, Spdef, Zscan10, Stat3
metacluster_1/pattern_2 # seqlets: 3826 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf6, Klf7, Klf4, Klf8, Klf1, Klf12, Egr1, Zbtb17, Egr2, E2f1, Klf5, Sp5, Zfp281, Zfx, Zfp740, Egr3, Zbtb1
metacluster_1/pattern_3 # seqlets: 1636 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_4 # seqlets: 1416 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_5 # seqlets: 1352 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf7, Stat1, Prdm1, Irf9, Batf3, Stat2, Irf3
metacluster_1/pattern_6 # seqlets: 954 SequenceContrib ScoresHyp_Contrib Scores	Fosl2, Batf, Jdp2, Bach2, Fos, Bach1, Jund, Nfe2l2, Nfe2, Jun, Fosl1, Fosb, Atf3, Junb, Mafa, Mafk, Mafb, Mafg, Nfatc1, Maff, Maf
metacluster_1/pattern_7 # seqlets: 920 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf7, Creb5, Atf2, Atf1, Crem, Nfil3, Tef, Dbp, Rxrb, Hlf, Gmeb2, Cebpb, Cebpa
metacluster_1/pattern_8 # seqlets: 817 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_9 # seqlets: 724 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Zfp42, Wt1, Mxi1
metacluster_1/pattern_10 # seqlets: 688 SequenceContrib ScoresHyp_Contrib Scores	Nfkb1, Nfkb2, Rela, Relb, Rel
metacluster_1/pattern_11 # seqlets: 659 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_12 # seqlets: 616 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Usf2, Tfe3, Tfeb, Arntl, Tfec, Mitf, Srebf1, Bhlhe40, Clock, Arnt, Mlx, Npas2, Srebf2, Creb3l2, Tcfl5, Mycn, Max, Myc, Bhlhe41, Xbp1, Mlxip
metacluster_1/pattern_13 # seqlets: 455 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx6, Rfx7
metacluster_1/pattern_14 # seqlets: 444 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_15 # seqlets: 145 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_16 # seqlets: 144 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic
metacluster_1/pattern_17 # seqlets: 129 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Pou2f1
metacluster_1/pattern_18 # seqlets: 124 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_19 # seqlets: 91 SequenceContrib ScoresHyp_Contrib Scores