# Parameters
data_name = "MPP;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_0-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_0-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 18:41:46,025 [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	MPP
Cell Group	Other Immune Cells
Experiment Name	ATAC
Experiment Group	Casellas Lab

replicate	Naïve overlap peaks	IDR peaks	TSS enrichment (< 8 is very poor <10 is low)	Final number of unique mapping, dup-filtered, chrM filtered reads	Number of reads in called peak regions	Fraction of reads in called peak regions	Number of reads in promoter regions	Fraction of reads in promoter regions	Number of reads in enhancer regions	Fraction of reads in enhancer regions
rep1	127767	93706	13.4528	36486766	8702737	0.2386	5845964	0.1603	12580455	0.345
rep2	127767	93706	10.7789	37447135	3235885	0.0865	2754868	0.0736	12890593	0.3444

Metric	Value
auPRC	0.6045
Calibrated Recall at 50% FDR	0.215
Number of Positive Examples in Test Data	111476
Number of Negative Examples in Test Data	7959375
Imbalance Ratio in Test Data	0.0138
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 7218 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 5293 SequenceContrib ScoresHyp_Contrib Scores	Spib, Spi1, Spic, Irf8, Irf4, Etv2, Etv6, Elf3, Etv4, Ehf, Ets1, Elf4, Etv3, Irf3, Fli1, Prdm1, Gabpa, Elk1, XP_911724.4, Erg, Elf2, Elk4, Elk3, Elf5, Irf2, Irf1, Etv1, Elf1, Etv5
metacluster_1/pattern_2 # seqlets: 2858 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf6, Klf7, Klf4, Klf1, Egr1, Klf8, Klf12, Zbtb17, Egr2, E2f1, Sp5, Zfp281, Klf5, Zfx
metacluster_1/pattern_3 # seqlets: 1227 SequenceContrib ScoresHyp_Contrib Scores	Atf1, Usf1, Tfec, Usf2, Bhlhe40, Creb1, Mitf, Srebf1, Atf7, Tfe3, Tfeb, Arntl, Atf2, Crem, Mlx, Clock, Srebf2, Creb5, Jdp2, Creb3l2, Rxrb, Xbp1, Npas2, Tcfl5, Atf3, Bhlhe41, Dbp, Hlf, Tef
metacluster_1/pattern_4 # seqlets: 1001 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_5 # seqlets: 980 SequenceContrib ScoresHyp_Contrib Scores	Stat1, Irf7, Stat2, Irf9, Batf3
metacluster_1/pattern_6 # seqlets: 935 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Foxi1, Nfyc, Nfya, Pbx3
metacluster_1/pattern_7 # seqlets: 891 SequenceContrib ScoresHyp_Contrib Scores	Fev, Spdef, Mbd2, E2f3
metacluster_1/pattern_8 # seqlets: 865 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_9 # seqlets: 610 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Cbfb, Runx3
metacluster_1/pattern_10 # seqlets: 605 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_11 # seqlets: 592 SequenceContrib ScoresHyp_Contrib Scores	Nfe2, Nfe2l2, Bach2, Bach1, Mafa, Mafk, Jun, Mafb, Mafg, Maff, Maf, Fosb, Fosl2, Junb, Fosl1, Jund, Batf, Fos
metacluster_1/pattern_12 # seqlets: 488 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_13 # seqlets: 481 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_14 # seqlets: 454 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_15 # seqlets: 431 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx1, Rfx2, Rfx4, Rfx6, Rfx7
metacluster_1/pattern_16 # seqlets: 318 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpd, Cebpa, Nfil3, Cebpg, Cebpe, Atf4, Ddit3, Pou3f3
metacluster_1/pattern_17 # seqlets: 270 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Wt1, Maz
metacluster_1/pattern_18 # seqlets: 207 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic
metacluster_1/pattern_19 # seqlets: 168 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_20 # seqlets: 88 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_21 # seqlets: 71 SequenceContrib ScoresHyp_Contrib Scores	Hoxc9, Meis1, Hoxa9, Cdx4, Evx1, Hoxa2, Hoxb4, Pdx1, Hoxa10, Hoxd10, Cdx2, Hoxb7, Cdx1, Hoxd8
metacluster_1/pattern_22 # seqlets: 62 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_23 # seqlets: 59 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_24 # seqlets: 48 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_25 # seqlets: 46 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_26 # seqlets: 42 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2c, Mef2a