# Parameters
data_name = "ePyramidal_NRN;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_174-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_174-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 19:19:51,256 [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	excitatory pyramidal neurons
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	271577	201826	9.2944	102616700	28656306	0.2793	9055260	0.0883	42353186	0.4128
rep2	271577	201826	9.3941	89229958	25317375	0.2838	7692821	0.0862	37331570	0.4185

Metric	Value
auPRC	0.5855
Calibrated Recall at 50% FDR	0.28
Number of Positive Examples in Test Data	247169
Number of Negative Examples in Test Data	7823682
Imbalance Ratio in Test Data	0.0306
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 6401 SequenceContrib ScoresHyp_Contrib Scores	Egr2, Egr3, Zbtb17, Egr1, Zfp281, Klf1, Sp4, Sp1, Sp5, Klf6, Zfp740
metacluster_1/pattern_1 # seqlets: 2866 SequenceContrib ScoresHyp_Contrib Scores	Mef2a, Mef2c, Mef2d
metacluster_1/pattern_2 # seqlets: 2580 SequenceContrib ScoresHyp_Contrib Scores	Neurod2, Neurod1, Olig2, Neurog2, Atoh1, Bhlhe22, Msc, Neurog1, Tcf21, Twist2, Msgn1, Bhlha15, Lyl1, Ascl2, Ascl1, Tal1, Myog, Tfap4
metacluster_1/pattern_3 # seqlets: 2292 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_4 # seqlets: 2049 SequenceContrib ScoresHyp_Contrib Scores	Batf, Fosl2, Jdp2, Jund, Fos, Fosb, Junb, Atf3, Fosl1, Jun, Bach2, Nfe2, Bach1, Nfe2l2, Mafk, Mafa
metacluster_1/pattern_5 # seqlets: 1800 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfic, Nfia
metacluster_1/pattern_6 # seqlets: 1631 SequenceContrib ScoresHyp_Contrib Scores	Nfil3, Dbp, Hlf
metacluster_1/pattern_7 # seqlets: 1509 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx1, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_8 # seqlets: 1297 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_9 # seqlets: 902 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf1, Atf7, Creb5, Atf2, Crem, Srebf1, Tfec, Tfe3, Mlx, Tfeb, Rxrb, Bhlhe40, Srebf2, Mitf, Usf1, Arntl, Xbp1, Clock, Tef, Usf2, Creb3l2, Mafb, Npas2, Arnt
metacluster_1/pattern_10 # seqlets: 755 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elf1, Elk1, Fli1, Elk4, Elk3, Erg, Elf5, Etv5, Ets1, Fev, Etv1, Etv4, Elf2, Elf4, Etv6, Ehf, XP_911724.4, Etv3, Etv2, Elf3, Spdef, Spi1
metacluster_1/pattern_11 # seqlets: 616 SequenceContrib ScoresHyp_Contrib Scores	Nfyc, Nfyb, Nfya, Pbx3, Foxi1
metacluster_1/pattern_12 # seqlets: 377 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Pou2f1, Pou5f1
metacluster_1/pattern_13 # seqlets: 246 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_14 # seqlets: 212 SequenceContrib ScoresHyp_Contrib Scores	Yy1, Taf1, Sp2, Zfp42, Sp3
metacluster_1/pattern_15 # seqlets: 189 SequenceContrib ScoresHyp_Contrib Scores	Tbx20, Eomes, Tbx21, Tbx1, Tbr1, Tbx3, Tbx4, Tbx5
metacluster_1/pattern_16 # seqlets: 82 SequenceContrib ScoresHyp_Contrib Scores	Rorc, Nr1d2, Pparg