# Parameters
data_name = "ES;JM8.N4;Asynch;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_186-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_186-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 19:23:11,598 [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	JM8.N4 Asynchronous
Cell Group	ES cells and embryonic 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	137776	97818	4.6453	176383965	8614474	0.0488	9551189	0.0542	54514429	0.3091
rep2	137776	97818	3.533	197121315	8359286	0.0424	10010761	0.0508	63031595	0.3198

Metric	Value
auPRC	0.7026
Calibrated Recall at 50% FDR	0.199
Number of Positive Examples in Test Data	38727
Number of Negative Examples in Test Data	8032124
Imbalance Ratio in Test Data	0.0048
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 6213 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp4, Sp3, Klf3, Sp1, Klf6, E2f4, Klf4, Klf7, Klf8, Klf1, Klf12, Egr1, Zbtb17, Egr2, E2f1, Klf5, Zfp281, Sp5, Zfx, Sall4
metacluster_0/pattern_1 # seqlets: 2132 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_2 # seqlets: 1535 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_3 # seqlets: 1458 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_4 # seqlets: 1237 SequenceContrib ScoresHyp_Contrib Scores	Mxi1, Wt1, Usf2, Rfx1, Mbd2, Maz, Klf15
metacluster_0/pattern_5 # seqlets: 811 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Fli1, Ets1, Elk4, Elf1, Erg, Elk3, Elk1, Etv4, Etv1, Fev, Etv5, Etv2, Ehf, Etv3, Etv6, XP_911724.4, Elf5, Elf4, Elf2, Elf3, Spdef, Spi1, E2f3
metacluster_0/pattern_6 # seqlets: 675 SequenceContrib ScoresHyp_Contrib Scores	Pou5f1, Nanog, Pou2f2, Sox2
metacluster_0/pattern_7 # seqlets: 662 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Atf7, Jdp2, Crem, Atf1, Creb5, Atf3, Usf1, Fosl2, Jun, Hlf
metacluster_0/pattern_8 # seqlets: 652 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_0/pattern_9 # seqlets: 619 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_10 # seqlets: 547 SequenceContrib ScoresHyp_Contrib Scores	Sox3, Sox4, Sox6, Lef1, Sox17, Sry, Sox12, Sox14, Sox7, Sox8, Sox11, Sox9, Sox18, Sox5, Sox21, Sox10, Tcf7, Tcf7l1, Sox15, Tcf7l2
metacluster_0/pattern_11 # seqlets: 514 SequenceContrib ScoresHyp_Contrib Scores	Tfe3, Tfeb, Arntl, Tfec, Mitf, Clock, Srebf1, Bhlhe40, Arnt, Mlx, Npas2, Mycn, Srebf2, Myc, Max, Tcfl5, Creb3l2, Bhlhe41, Xbp1, Mlxip, Rarg
metacluster_0/pattern_12 # seqlets: 407 SequenceContrib ScoresHyp_Contrib Scores	Bach2, Nfe2l2, Mafk, Nfe2, Jund, Fosl1, Bach1, Fos, Mafb, Mafg, Maff, Batf, Mafa, Fosb, Maf, Junb
metacluster_0/pattern_13 # seqlets: 378 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead2, Tead1
metacluster_0/pattern_14 # seqlets: 366 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_0/pattern_15 # seqlets: 220 SequenceContrib ScoresHyp_Contrib Scores	Zic5, Stat3, Stat4
metacluster_0/pattern_16 # seqlets: 147 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_0/pattern_17 # seqlets: 129 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_18 # seqlets: 128 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_0/pattern_19 # seqlets: 91 SequenceContrib ScoresHyp_Contrib Scores	Grhl2
metacluster_0/pattern_20 # seqlets: 76 SequenceContrib ScoresHyp_Contrib Scores	Rest