# Parameters
data_name = "LVR;8wks;D;GEO"
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_202-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_202-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 19:27:24,425 [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	Liver (Adult 8 weeks)
Cell Group	Other Tissues
Experiment Name	DHS
Experiment Group	GEO

Metric	Value
auPRC	0.5037
Calibrated Recall at 50% FDR	0.279
Number of Positive Examples in Test Data	151013
Number of Negative Examples in Test Data	7919838
Imbalance Ratio in Test Data	0.0187
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 3934 SequenceContrib ScoresHyp_Contrib Scores	Nr1h3, Nr2c2, Nr2f6, Rxra, Hnf4g, Rxrb, Ppara, Hnf4a, Nr2f1, Pparg, Nr2c1, Nr4a2, Nr2e3, Nr5a2, Nr5a1, Rarg, Rara, Rarb, Nr2f2, Esrrb, Esrra
metacluster_1/pattern_1 # seqlets: 3213 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Cebpd, Nfil3, Dbp, Cebpg, Hlf, Atf4, Ddit3, Cebpe, Tef, Pou3f3
metacluster_1/pattern_2 # seqlets: 2677 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_3 # seqlets: 1931 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf6, Klf7, Egr1, Klf4, Klf8, Klf12, Klf1, Zbtb17, Sp5, Egr2, Zfp281, E2f1, Klf5, Egr3, Wt1, Zfx
metacluster_1/pattern_4 # seqlets: 1464 SequenceContrib ScoresHyp_Contrib Scores	Foxa2, Foxa3, Foxa1, Foxd3, Foxc1, Foxd1, Foxm1, Foxc2, Foxb1, Foxj2, Foxg1, Foxk1, Foxl1, Foxl2, Foxp2, Gm5294, Foxj3, Foxo3, Foxq1, Foxo1, Foxp1, Foxj1, Foxo4
metacluster_1/pattern_5 # seqlets: 1345 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elk1, Fli1, Elk4, Ets1, Erg, Elk3, Etv5, Elf1, Etv4, Fev, Etv1, Etv6, Etv3, XP_911724.4, Etv2, Spi1, Elf4, Elf5, Ehf, Elf2, Spdef, Elf3, Spib, Spic
metacluster_1/pattern_6 # seqlets: 1109 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_7 # seqlets: 1050 SequenceContrib ScoresHyp_Contrib Scores	Hnf1b, Hnf1a
metacluster_1/pattern_8 # seqlets: 1024 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_9 # seqlets: 981 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic
metacluster_1/pattern_10 # seqlets: 874 SequenceContrib ScoresHyp_Contrib Scores	Onecut1, Cux2
metacluster_1/pattern_11 # seqlets: 718 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Foxi1, Nfya, Pbx3
metacluster_1/pattern_12 # seqlets: 523 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfec, Usf2, Tfeb, Arntl, Mitf, Srebf1, Bhlhe40, Tfe3, Mlx, Clock, Arnt, Npas2, Srebf2, Tcfl5, Creb3l2, Bhlhe41, Atf1, Xbp1, Mlxip, Arnt2
metacluster_1/pattern_13 # seqlets: 459 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Creb5, Atf7, Atf2, Jdp2, Crem, Mafb, Jun, Gmeb2, Fosl1, Atf3, Junb
metacluster_1/pattern_14 # seqlets: 443 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf7, Irf8, Prdm1, Irf9, Stat1, Stat2, Irf4, Irf3, Irf5
metacluster_1/pattern_15 # seqlets: 283 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_16 # seqlets: 268 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Maz, Rfx1
metacluster_1/pattern_17 # seqlets: 249 SequenceContrib ScoresHyp_Contrib Scores	Rxrg, Esrrg
metacluster_1/pattern_18 # seqlets: 104 SequenceContrib ScoresHyp_Contrib Scores	Bach2, Nfe2l2, Nfe2, Mafk, Bach1, Mafa, Mafg, Maff, Maf, Fosl2, Batf, Fosb, Jund, Fos, Cic
metacluster_1/pattern_19 # seqlets: 97 SequenceContrib ScoresHyp_Contrib Scores	Gata4, Gata2, Gata1, Tal1, Gata6, Gata3, Gata5
metacluster_1/pattern_20 # seqlets: 90 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33