# Parameters
data_name = "BRN;CRBLM;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_72-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_72-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 18:56:31,126 [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	Brain- Cerebellum
Cell Group	Neural Cells and Tissues
Experiment Name	ATAC
Experiment Group	Casellas Lab

Metric	Value
auPRC	0.6228
Calibrated Recall at 50% FDR	0.242
Number of Positive Examples in Test Data	57412
Number of Negative Examples in Test Data	8013439
Imbalance Ratio in Test Data	0.0071
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 2862 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Sp1, Klf3, Sp4, Sp5, Wt1, Klf6, Maz, Zbtb17, Klf15, Zfx, Klf1, Egr1, Zfp281, Klf5, Rela, Usf2, Klf4, Mxi1, Egr2, Klf7, Ctcfl, E2f1, E2f4, Klf12, Fli1, Klf8, Ptf1a, Mbd2, Nr1h4, E2f6, Tfap2c, Sall4
metacluster_0/pattern_1 # seqlets: 2623 SequenceContrib ScoresHyp_Contrib Scores	Ctcf
metacluster_0/pattern_2 # seqlets: 2031 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_3 # seqlets: 1647 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_4 # seqlets: 1611 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elk4, Ets1, Elf1, Elk1, Erg, Elk3, Etv2, Etv4, Etv1, Fev, Etv5, Etv6, Etv3, Ehf, XP_911724.4, Elf3, Elf5, Elf4, Spi1, Elf2, Spdef, Irf8, E2f3, Spib
metacluster_0/pattern_5 # seqlets: 1525 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_0/pattern_6 # seqlets: 1414 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Jdp2, Creb5, Atf2, Atf7, Crem, Atf1, Nfil3, Tef, Jun, Dbp, Hlf, Gmeb2, Mafb, Cebpb, Fosl1, Cebpa, Atf3, Gmeb1, Cebpg, Cebpd, Jund, Esr2, Junb, Rxrb, Fosl2, Atf4, Xbp1, Rora
metacluster_0/pattern_7 # seqlets: 1064 SequenceContrib ScoresHyp_Contrib Scores	Neurod1, Neurod2, Olig2, Neurog2, Atoh1, Msgn1, Msc, Bhlhe22, Neurog1, Tcf21, Bhlha15, Twist2, Ascl2, Lyl1, Ascl1, Clock
metacluster_0/pattern_8 # seqlets: 851 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_9 # seqlets: 687 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Zfp42
metacluster_0/pattern_10 # seqlets: 617 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_11 # seqlets: 546 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Arntl, Tfe3, Tfeb, Tfec, Mitf, Srebf1, Bhlhe40, Arnt, Mlx, Npas2, Srebf2, Myc, Tcfl5, Mycn, Max, Creb3l2, Bhlhe41, Rarg, Mlxip
metacluster_0/pattern_12 # seqlets: 532 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6, Sox2, Pou5f1
metacluster_0/pattern_13 # seqlets: 338 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf7, Stat2, Prdm1, Irf9, Stat1, Irf4, Irf5, Irf3, Batf3, Irf6
metacluster_0/pattern_14 # seqlets: 244 SequenceContrib ScoresHyp_Contrib Scores	Fos, Batf, Fosb, Mafk, Bach2, Nfe2l2, Nfe2, Mafg, Maff, Mafa, Maf, Bach1
metacluster_0/pattern_15 # seqlets: 232 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_0/pattern_16 # seqlets: 114 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2c, Mef2a