# Parameters
data_name = "RTN;A;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_104-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_104-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 19:03:40,216 [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	WT retina
Cell Group	Neural Cells and Tissues
Experiment Name	ATAC
Experiment Group	GEO

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	149877	108264	16.881	39257849	9388108	0.2392	7772426	0.1981	14482689	0.3691
rep2	149877	108264	14.309	47859418	12036971	0.2516	9712932	0.203	17959926	0.3754

Metric	Value
auPRC	0.6368
Calibrated Recall at 50% FDR	0.185
Number of Positive Examples in Test Data	113072
Number of Negative Examples in Test Data	7957779
Imbalance Ratio in Test Data	0.014
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 7997 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_1 # seqlets: 3877 SequenceContrib ScoresHyp_Contrib Scores	Crx, Otx2, Otx1, Pax7, Obox6, Dmbx1
metacluster_0/pattern_2 # seqlets: 1669 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Klf3, Sp4, Sp1, Klf6, Klf1, E2f4, Wt1, Klf4, Egr1, Klf5, Sp5, Klf7, Klf8, Klf12, Maz, Zfp281, Zbtb17, Egr2, Zfx, Klf15, E2f1, E2f7, Sall4, Zfp740
metacluster_0/pattern_3 # seqlets: 1501 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_4 # seqlets: 1196 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Fli1, Ets1, Erg, Elk4, Elk1, Elf1, Elk3, Etv4, Etv1, Etv2, Etv5, Fev, Ehf, Etv3, Etv6, XP_911724.4, Elf4, Elf5, Elf2, Spi1, Elf3, Spdef
metacluster_0/pattern_5 # seqlets: 1195 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Foxi1, Nfyc, Nfya, Pbx3
metacluster_0/pattern_6 # seqlets: 1073 SequenceContrib ScoresHyp_Contrib Scores	Neurod1, Neurod2, Neurog2, Olig2, Atoh1, Msgn1, Bhlhe22, Msc, Neurog1, Tcf21, Ascl2, Bhlha15, Lyl1, Ascl1, Twist2, Ptf1a
metacluster_0/pattern_7 # seqlets: 776 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_8 # seqlets: 763 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Zfp42, Mxi1, Usf2
metacluster_0/pattern_9 # seqlets: 667 SequenceContrib ScoresHyp_Contrib Scores	Rorc, Rora, Pparg, Ppara, Esr2, Nr1d2, Nr1d1
metacluster_0/pattern_10 # seqlets: 647 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfe3, Tfeb, Arntl, Mitf, Tfec, Clock, Srebf1, Bhlhe40, Arnt, Mlx, Npas2, Creb3l2, Srebf2, Mycn, Tcfl5, Max, Myc, Creb1, Atf1, Bhlhe41, Rarg, Hlf, Atf7, Xbp1, Dbp
metacluster_0/pattern_11 # seqlets: 621 SequenceContrib ScoresHyp_Contrib Scores	Jdp2, Atf2, Crem, Creb5, Atf3, Fosl2, Nfil3, Tef, Jun, Fosl1
metacluster_0/pattern_12 # seqlets: 593 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_13 # seqlets: 484 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_0/pattern_14 # seqlets: 431 SequenceContrib ScoresHyp_Contrib Scores	Tfap2b
metacluster_0/pattern_15 # seqlets: 262 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx6, Rfx7
metacluster_0/pattern_16 # seqlets: 240 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_0/pattern_17 # seqlets: 140 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_18 # seqlets: 73 SequenceContrib ScoresHyp_Contrib Scores