# Parameters
data_name = "ES;ZhBTc4;untreated;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_183-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_183-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 19:21:43,318 [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	ZHBTC4 ES untreated
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	241074	173485	9.431	75607493	10687074	0.1414	6741883	0.0892	27644752	0.3657
rep2	241074	173485	9.7991	53588215	8521771	0.1591	5753548	0.1074	20338178	0.3796
rep3	241074	173485	9.4419	59698817	9514043	0.1594	6245479	0.1046	22322997	0.374

Metric	Value
auPRC	0.6982
Calibrated Recall at 50% FDR	0.165
Number of Positive Examples in Test Data	177744
Number of Negative Examples in Test Data	7893107
Imbalance Ratio in Test Data	0.022
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 3624 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 2457 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Sp1, Klf15, Maz, Klf1, Zfx, Wt1, Klf6, Klf3, Zbtb17, Egr1, Sp5, Sp4, Zfp281, Egr2, Klf7, Klf4, Klf8, Klf12, Klf5, E2f4, Usf2, Rela, E2f1, Fli1, E2f7, Mxi1
metacluster_1/pattern_2 # seqlets: 2306 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_3 # seqlets: 1399 SequenceContrib ScoresHyp_Contrib Scores	Sall4, Zfp740
metacluster_1/pattern_4 # seqlets: 1208 SequenceContrib ScoresHyp_Contrib Scores	Sox2, Nanog, Sox6, Sox4, Sox3, Pou5f1, Sox17, Sox12, Sox30, Lef1, Sry, Sox14, Sox21, Sox7, Sox8, Sox18, Sox11, Sox5, Cux2
metacluster_1/pattern_5 # seqlets: 1182 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2
metacluster_1/pattern_6 # seqlets: 1014 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead2, Tead1
metacluster_1/pattern_7 # seqlets: 814 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Pbx3, Foxi1
metacluster_1/pattern_8 # seqlets: 731 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_9 # seqlets: 728 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_10 # seqlets: 592 SequenceContrib ScoresHyp_Contrib Scores	Nr5a2, Esrrg, Rarg, Esrrb, Esrra, Nr5a1
metacluster_1/pattern_11 # seqlets: 554 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elf1, Elk1, Elk4, Elk3, Erg, Elf5, Ets1, Etv5, Etv1, Fev, Etv4, Elf2, Etv6, Elf4, Ehf, Etv3, XP_911724.4, Etv2, Elf3, Spi1, Spdef, Spic
metacluster_1/pattern_12 # seqlets: 516 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_13 # seqlets: 462 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfeb, Tfec, Tfe3, Mitf, Srebf1, Arntl, Bhlhe40, Mlx, Clock, Arnt, Npas2, Srebf2, Creb3l2, Tcfl5, Atf1, Bhlhe41, Xbp1, Mycn, Dbp, Hlf, Max, Atf7, Mlxip, Creb1, Myc
metacluster_1/pattern_14 # seqlets: 444 SequenceContrib ScoresHyp_Contrib Scores	Zic2, Zic3
metacluster_1/pattern_15 # seqlets: 346 SequenceContrib ScoresHyp_Contrib Scores	Bach2, Nfe2, Nfe2l2, Bach1, Mafa, Mafk, Jun, Mafg, Atf3, Mafb, Fosl2, Maff, Fosb, Junb, Fosl1, Jund, Maf, Batf, Fos, Jdp2
metacluster_1/pattern_16 # seqlets: 243 SequenceContrib ScoresHyp_Contrib Scores	E2f3, Rfx1, Mbd2, Egr3, Tfap2b
metacluster_1/pattern_17 # seqlets: 203 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_18 # seqlets: 184 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_19 # seqlets: 150 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_20 # seqlets: 79 SequenceContrib ScoresHyp_Contrib Scores	Trp53, Trp73, Trp63
metacluster_1/pattern_21 # seqlets: 60 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six4, Six1
metacluster_1/pattern_22 # seqlets: 53 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_23 # seqlets: 32 SequenceContrib ScoresHyp_Contrib Scores