# Parameters
data_name = "aB_LPS+IL21;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_15-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_15-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 18:44:08,351 [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	aB LPS+IL21
Cell Group	B cells
Experiment Name	ATAC
Experiment Group	Casellas Lab

Metric	Value
auPRC	0.7158
Calibrated Recall at 50% FDR	0.175
Number of Positive Examples in Test Data	37148
Number of Negative Examples in Test Data	8033703
Imbalance Ratio in Test Data	0.0046
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 6794 SequenceContrib ScoresHyp_Contrib Scores	Sp1, Sp2, Spib, Spi1, Sp3, Irf8, Irf4, Erg, Maz, Wt1, Klf3, Sp4, Sp5, Etv4, Ets1, Etv2, Klf15, Etv6, Zfx, Rela, Elk1, Irf2, Zbtb17, Ehf, Elf3, Etv3, Fli1, Spic, Gabpa, Klf6, XP_911724.4, Elf4, Elk4, Prdm1, Irf1, Elk3, Elf2, Elf1, Etv1, Elf5, Etv5, Irf3, Zfp281, Fev, Zscan10, Tcf7, Usf2, Ets2, Ctcfl, Bcl6, Nr1d2, Mxi1, E2f3, Ptf1a, Spdef, Mecp2, Klf4, Nr1h4
metacluster_1/pattern_1 # seqlets: 4226 SequenceContrib ScoresHyp_Contrib Scores	Ctcf
metacluster_1/pattern_2 # seqlets: 3770 SequenceContrib ScoresHyp_Contrib Scores	E2f4, Klf7, Egr1, Klf8, Klf12, Klf5, Egr2, Klf1, E2f1, Egr3, Srebf2, Zbtb1, Zfp740
metacluster_1/pattern_3 # seqlets: 1766 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_4 # seqlets: 1724 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_5 # seqlets: 1349 SequenceContrib ScoresHyp_Contrib Scores	Yy1, Taf1, Rfx1, Zfp42
metacluster_1/pattern_6 # seqlets: 1194 SequenceContrib ScoresHyp_Contrib Scores	Stat1, Stat2, Irf7, Irf9, Irf5
metacluster_1/pattern_7 # seqlets: 1039 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_8 # seqlets: 796 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Atf7, Atf1, Jdp2, Crem, Creb5, Atf3, Fosl2, Fosl1, Jun, Nfil3, Rxrb, Tef, Hlf
metacluster_1/pattern_9 # seqlets: 619 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Pou2f1
metacluster_1/pattern_10 # seqlets: 567 SequenceContrib ScoresHyp_Contrib Scores	Tfec, Tfeb, Usf1, Mitf, Arntl, Bhlhe40, Srebf1, Tfe3, Mlx, Arnt, Clock, Npas2, Tcfl5, Bhlhe41, Creb3l2, Dbp, Mlxip, Arnt2
metacluster_1/pattern_11 # seqlets: 303 SequenceContrib ScoresHyp_Contrib Scores	Nfkb1, Nfkb2, Relb, Rel
metacluster_1/pattern_12 # seqlets: 231 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_13 # seqlets: 228 SequenceContrib ScoresHyp_Contrib Scores	Fos, Jund, Fosb, Batf, Junb, Bach2, Nfe2, Nfe2l2, Bach1, Mafa, Mafk
metacluster_1/pattern_14 # seqlets: 181 SequenceContrib ScoresHyp_Contrib Scores	Ebf1, Prdm16
metacluster_1/pattern_15 # seqlets: 119 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_16 # seqlets: 115 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_17 # seqlets: 40 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib