# Parameters
data_name = "TSLEC_SPLND;CD8+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_119-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_119-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 19:07:18,031 [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	Spleen CD8+ T cell(SLEC)
Cell Group	T cells
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	113741	88795	16.0087	22643370	6194866	0.2738	4644797	0.2053	7777734	0.3438
rep2	113741	88795	16.2777	23506852	6491758	0.2764	4880229	0.2078	8151996	0.3471
rep3	113741	88795	15.2524	23831594	5197585	0.2183	4220036	0.1772	8075239	0.3391

Metric	Value
auPRC	0.5924
Calibrated Recall at 50% FDR	0.207
Number of Positive Examples in Test Data	100198
Number of Negative Examples in Test Data	7970653
Imbalance Ratio in Test Data	0.0124
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 6822 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Elk1, Etv2, Gabpa, Etv4, Elk4, Fli1, Spi1, Etv6, Elk3, Etv5, Elf2, Ehf, Elf1, Spib, Fev, Etv3, Etv1, XP_911724.4, Elf3, Elf4, Stat4, Elf5, Irf8, Irf4, Ets2, Spdef
metacluster_1/pattern_1 # seqlets: 6330 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_2 # seqlets: 2473 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Klf3, Sp3, Sp1, Klf6, Klf7, Klf4, E2f4, Klf1, Klf8, Klf12, Egr1, Zbtb17, Egr2, Klf5, E2f1, Sp5, Zfp281, Egr3, Zfx
metacluster_1/pattern_3 # seqlets: 1989 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Stat1, Irf7, Prdm1, Stat2, Irf9, Irf3, Batf3, Irf5
metacluster_1/pattern_4 # seqlets: 1132 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_5 # seqlets: 1080 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_6 # seqlets: 900 SequenceContrib ScoresHyp_Contrib Scores	Fos, Fosl1, Fosl2, Jund, Batf, Fosb, Junb, Atf3, Jun, Jdp2, Bach2, Mafa, Nfe2l2, Nfe2, Bach1, Mafk, Mafb, Mafg
metacluster_1/pattern_7 # seqlets: 848 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_8 # seqlets: 755 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_9 # seqlets: 533 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Wt1
metacluster_1/pattern_10 # seqlets: 506 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Usf2, Atf2, Atf7, Atf1, Crem, Creb5, Rfx1, Usf1, Nfil3, Rxrb
metacluster_1/pattern_11 # seqlets: 455 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_12 # seqlets: 315 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_13 # seqlets: 229 SequenceContrib ScoresHyp_Contrib Scores	Tfe3, Tfeb, Arntl, Tfec, Mitf, Srebf1, Clock, Bhlhe40, Arnt, Mlx, Npas2, Srebf2, Tcfl5, Mycn, Creb3l2, Max, Myc, Hlf, Bhlhe41
metacluster_1/pattern_14 # seqlets: 214 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_15 # seqlets: 189 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_16 # seqlets: 161 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_17 # seqlets: 143 SequenceContrib ScoresHyp_Contrib Scores	Nfkb1, Rela, Nfkb2, Relb, Rel
metacluster_1/pattern_18 # seqlets: 135 SequenceContrib ScoresHyp_Contrib Scores	Maz, Klf15, Sall4, Mbd2
metacluster_1/pattern_19 # seqlets: 111 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_20 # seqlets: 69 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Pou2f1
metacluster_1/pattern_21 # seqlets: 42 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_22 # seqlets: 65 SequenceContrib ScoresHyp_Contrib Scores