# Parameters
data_name = "npES;ZHBTC4;doxyc;treat;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_184-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_184-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 19:22:22,475 [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 doxycycline-treated
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	226302	155704	9.9248	65499092	7412668	0.1132	5656778	0.0864	23236777	0.3549
rep2	226302	155704	10.0232	58855310	7702851	0.1309	5854599	0.0995	21373990	0.3633
rep3	226302	155704	8.9891	76933207	10456505	0.1359	7093858	0.0922	27836620	0.3619

Metric	Value
auPRC	0.7087
Calibrated Recall at 50% FDR	0.173
Number of Positive Examples in Test Data	150877
Number of Negative Examples in Test Data	7919974
Imbalance Ratio in Test Data	0.0187
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 3030 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_1 # seqlets: 2765 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp3, Klf3, Sp1, Sp2, Klf7, Klf8, Klf12, Klf4, Egr1, Zbtb17, Klf6, Klf5, E2f4, Klf1, Egr2, E2f1, Zfp281, Sp5, Sall4, Maz, Klf15, Zfp740, Egr3, Wt1, Zbtb1
metacluster_0/pattern_2 # seqlets: 1303 SequenceContrib ScoresHyp_Contrib Scores	Zfx, Mxi1
metacluster_0/pattern_3 # seqlets: 1210 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead2, Tead1
metacluster_0/pattern_4 # seqlets: 1175 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_5 # seqlets: 1056 SequenceContrib ScoresHyp_Contrib Scores	Sox17, Sox3, Sox4, Sox2, Nanog, Sox6, Sox9, Lef1, Sry
metacluster_0/pattern_6 # seqlets: 915 SequenceContrib ScoresHyp_Contrib Scores	Tfap2a, Tfap2c, Tfap2e, Tfap2b
metacluster_0/pattern_7 # seqlets: 768 SequenceContrib ScoresHyp_Contrib Scores	Bach2, Nfe2l2, Jun, Nfe2, Bach1, Fosl2, Jund, Fos, Fosl1, Atf3, Fosb, Junb, Batf, Mafk, Jdp2, Mafa, Mafg, Mafb, Maff, Maf
metacluster_0/pattern_8 # seqlets: 756 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_9 # seqlets: 689 SequenceContrib ScoresHyp_Contrib Scores	Nfyc, Nfyb, Nfya, Foxi1, Pbx3
metacluster_0/pattern_10 # seqlets: 689 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_11 # seqlets: 687 SequenceContrib ScoresHyp_Contrib Scores	Elf1, Gabpa, Fli1, Elk1, Elk4, Erg, Elk3, Ets1, Elf5, Etv5, Fev, Etv4, Etv6, Elf2, Ehf, Etv1, Elf4, Etv3, XP_911724.4, Elf3, Spi1, Etv2, Spic, Spdef, Spib
metacluster_0/pattern_12 # seqlets: 607 SequenceContrib ScoresHyp_Contrib Scores	Mbd2, E2f3, Rfx1, Usf2
metacluster_0/pattern_13 # seqlets: 445 SequenceContrib ScoresHyp_Contrib Scores	Esrra, Esrrb, Rara, Esrrg, Nr5a2, Rxrg, Rxra, Rarg, Nr5a1, Nr4a2, Nr2f1
metacluster_0/pattern_14 # seqlets: 444 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_15 # seqlets: 274 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfec, Tfeb, Mitf, Arntl, Tfe3, Srebf1, Bhlhe40, Mlx, Clock, Arnt, Npas2, Srebf2, Tcfl5, Creb3l2, Atf1, Bhlhe41, Hlf, Dbp, Xbp1, Mlxip, Mycn
metacluster_0/pattern_16 # seqlets: 240 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx4, Rfx6, Rfx7
metacluster_0/pattern_17 # seqlets: 195 SequenceContrib ScoresHyp_Contrib Scores	Zic3, Zic2, Zic1
metacluster_0/pattern_18 # seqlets: 160 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_19 # seqlets: 139 SequenceContrib ScoresHyp_Contrib Scores	Atf2, Atf7, Creb1, Creb5, Crem, Nfil3
metacluster_0/pattern_20 # seqlets: 129 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_21 # seqlets: 128 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_22 # seqlets: 112 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six4, Six1
metacluster_0/pattern_23 # seqlets: 111 SequenceContrib ScoresHyp_Contrib Scores	Grhl2
metacluster_0/pattern_24 # seqlets: 94 SequenceContrib ScoresHyp_Contrib Scores	Trp53, Trp73, Trp63, Tcfcp2l1
metacluster_0/pattern_25 # seqlets: 94 SequenceContrib ScoresHyp_Contrib Scores	Yy1, Taf1, Zfp42
metacluster_0/pattern_26 # seqlets: 76 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_0/pattern_27 # seqlets: 53 SequenceContrib ScoresHyp_Contrib Scores