# Parameters
data_name = "CN_PHT_RCPTR;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_154-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_154-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 19:14:30,362 [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 cone photoreceptors
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	148954	114410	21.7676	30932642	9609091	0.3108	6967520	0.2254	11652073	0.3769
rep2	148954	114410	23.1075	27082405	8207576	0.3033	6123020	0.2262	10108202	0.3735

Metric	Value
auPRC	0.6428
Calibrated Recall at 50% FDR	0.235
Number of Positive Examples in Test Data	117598
Number of Negative Examples in Test Data	7953253
Imbalance Ratio in Test Data	0.0146
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 6425 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 5502 SequenceContrib ScoresHyp_Contrib Scores	Crx, Otx2, Dmbx1, Otx1, Obox3, Obox1, Pitx1, Pitx3, Obox6, Gsc, Pitx2
metacluster_1/pattern_2 # seqlets: 2035 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_3 # seqlets: 1331 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Sp4, Klf6, Klf3, Klf1, Sp1, Klf7, Egr1, E2f4, Klf12, Klf8, Klf4, Zfx, Zbtb17, Egr2, Klf15, Klf5, Zfp281, Wt1, E2f1, Maz, Sp5, Zbtb1, Zfp740, E2f7
metacluster_1/pattern_4 # seqlets: 1178 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Foxi1, Nfyc, Nfya, Pbx3
metacluster_1/pattern_5 # seqlets: 1059 SequenceContrib ScoresHyp_Contrib Scores	Fli1, Gabpa, Ets1, Elk4, Elk1, Erg, Elf1, Elk3, Etv4, Etv1, Fev, Etv2, Etv5, Etv3, XP_911724.4, Etv6, Ehf, Elf3, Elf5, Elf2, Elf4, Mbd2, Spi1, E2f3, Spdef
metacluster_1/pattern_6 # seqlets: 832 SequenceContrib ScoresHyp_Contrib Scores	Rfx1, Taf1, Yy1, Usf2, Zfp42, Rfx2
metacluster_1/pattern_7 # seqlets: 749 SequenceContrib ScoresHyp_Contrib Scores	Ptf1a, Rela
metacluster_1/pattern_8 # seqlets: 657 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_9 # seqlets: 594 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Jdp2, Atf7, Atf2, Crem, Creb5, Atf3, Atf1, Fosl2, Nfil3, Jun, Tef, Fosl1
metacluster_1/pattern_10 # seqlets: 540 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfe3, Arntl, Mitf, Tfeb, Tfec, Clock, Arnt, Mlx, Srebf1, Bhlhe40, Npas2, Mycn, Max, Srebf2, Myc, Creb3l2, Tcfl5, Hlf, Xbp1, Bhlhe41, Rarg, Nr2f6, Mlxip, Hes1
metacluster_1/pattern_11 # seqlets: 353 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_12 # seqlets: 321 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_13 # seqlets: 289 SequenceContrib ScoresHyp_Contrib Scores	Neurod1, Neurod2, Neurog2, Olig2, Atoh1, Msgn1, Msc, Bhlhe22, Neurog1, Tcf21, Ascl2, Ascl1, Twist2, Lyl1, Bhlha15, Tcf12, Snai1
metacluster_1/pattern_14 # seqlets: 190 SequenceContrib ScoresHyp_Contrib Scores	Rorc, Rora, Esr2
metacluster_1/pattern_15 # seqlets: 125 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx7, Rfx6
metacluster_1/pattern_16 # seqlets: 96 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2
metacluster_1/pattern_17 # seqlets: 66 SequenceContrib ScoresHyp_Contrib Scores	Irf2, Irf1, Prdm1, Irf8, Irf7, Stat2, Stat1, Irf3, Irf4, Spib, Irf9, Batf3
metacluster_1/pattern_18 # seqlets: 82 SequenceContrib ScoresHyp_Contrib Scores