# Parameters
data_name = "Adrenal;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_59-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_59-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 18:53:21,552 [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	Adrenal
Cell Group	Other Tissues
Experiment Name	ATAC
Experiment Group	Casellas Lab

Metric	Value
auPRC	0.6136
Calibrated Recall at 50% FDR	0.208
Number of Positive Examples in Test Data	140042
Number of Negative Examples in Test Data	7930809
Imbalance Ratio in Test Data	0.0174
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 3017 SequenceContrib ScoresHyp_Contrib Scores	Nr5a2, Nr5a1, Esrra, Esrrb, Rxrg, Rxra, Esrrg, Rara, Rarg, Nr2f1, Nr4a2
metacluster_1/pattern_1 # seqlets: 2871 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_2 # seqlets: 2341 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf7, Klf6, Klf4, Klf8, Egr1, Klf12, Klf1, Zbtb17, Egr2, E2f1, Sp5, Klf5, Zfp281, Zfx, Egr3, Zfp740, Wt1
metacluster_1/pattern_3 # seqlets: 2244 SequenceContrib ScoresHyp_Contrib Scores	Fosl2, Batf, Jdp2, Fos, Jund, Fosb, Junb, Fosl1, Atf3, Jun, Bach2, Nfe2, Nfe2l2, Bach1, Mafa, Mafk
metacluster_1/pattern_4 # seqlets: 1446 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Cebpd, Nfil3, Dbp, Hlf, Cebpg, Ddit3, Atf4, Cebpe, Tef, Pou3f3
metacluster_1/pattern_5 # seqlets: 1382 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_6 # seqlets: 1196 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Creb5, Atf7, Atf1, Atf2, Crem, Rxrb, Mafb, Tfec, Srebf1, Tfe3, Mlx
metacluster_1/pattern_7 # seqlets: 1066 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic
metacluster_1/pattern_8 # seqlets: 637 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Fli1, Ets1, Elk4, Elf1, Erg, Elk3, Elk1, Etv4, Etv1, Etv2, Etv5, Etv3, Fev, Etv6, XP_911724.4, Elf4, Ehf, Elf5, Elf2, Spi1, Spdef, Elf3, Spib, Spic, Irf8
metacluster_1/pattern_9 # seqlets: 548 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_10 # seqlets: 438 SequenceContrib ScoresHyp_Contrib Scores	Evx1, Hoxa9, Cdx4, Hoxc9, Meis1, Hoxb7, Hoxa10, Hoxb8, Pdx1, Pbx2, Hoxb4
metacluster_1/pattern_11 # seqlets: 416 SequenceContrib ScoresHyp_Contrib Scores	Rfx1, Rfx2, Rfx4, Rfx3, Rfx7, Rfx6
metacluster_1/pattern_12 # seqlets: 367 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Maz, Zfp42, Mxi1, Klf15
metacluster_1/pattern_13 # seqlets: 275 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Prdm1, Stat1, Irf7, Stat2, Irf9, Irf3, Irf4, Irf5
metacluster_1/pattern_14 # seqlets: 254 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_1/pattern_15 # seqlets: 254 SequenceContrib ScoresHyp_Contrib Scores	Nr2f6, Pparg
metacluster_1/pattern_16 # seqlets: 240 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_17 # seqlets: 84 SequenceContrib ScoresHyp_Contrib Scores	Nfatc2