# Parameters
data_name = "ESNPHL_SPLND_BlbCA;CL"
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_21-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_21-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 18:45:12,338 [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	eosinophils (isolated from spleens, BalbC)
Cell Group	Other Immune Cells
Experiment Name	ATAC
Experiment Group	Casellas Lab

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	59033	35812	11.6043	2890857	70741	0.0246	202703	0.0705	872867	0.3036
rep2	59033	35812	17.1991	18133477	1602501	0.0885	1763619	0.0974	5291480	0.2921
rep3	59033	35812	10.7493	22921120	1258052	0.0549	1825268	0.0797	7080664	0.3092

Metric	Value
auPRC	0.6563
Calibrated Recall at 50% FDR	0.208
Number of Positive Examples in Test Data	40644
Number of Negative Examples in Test Data	8030207
Imbalance Ratio in Test Data	0.005
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 6111 SequenceContrib ScoresHyp_Contrib Scores	Spic, Spi1, Spib, Etv6, Irf8, Irf4, Etv4, Ets1, Etv3, Elk1, Erg, Gabpa, Fli1, XP_911724.4, Etv2, Elk3, Elk4, Elf4, Elf2, Etv1, Etv5, Ehf, Elf1, Elf3, Elf5, Spdef, Prdm1, Irf3, Irf2, Irf1, Irf9
metacluster_0/pattern_1 # seqlets: 3732 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Klf3, Sp4, Sp1, Klf6, Klf4, E2f4, Klf5, Klf7, Egr1, Sp5, Klf8, Klf12, Zbtb17, Egr2, Wt1, Klf1, Zfp281, Maz, E2f1, Klf15, Egr3, Sall4, Srebf2, Zfp740
metacluster_0/pattern_2 # seqlets: 3620 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_3 # seqlets: 2219 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_4 # seqlets: 1561 SequenceContrib ScoresHyp_Contrib Scores	Nrf1, Zfx
metacluster_0/pattern_5 # seqlets: 1304 SequenceContrib ScoresHyp_Contrib Scores	Usf2, Creb1, Atf1, Atf2, Usf1, Atf7, Crem, Jdp2, Rfx1, Tfe3, Creb5, Atf3, Tfec, Mxi1, Bhlhe40, Srebf1, Mitf, Tfeb, Fosl2, Arntl, Rxrb, Clock, Mlx
metacluster_0/pattern_6 # seqlets: 1008 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_7 # seqlets: 996 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_0/pattern_8 # seqlets: 407 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Cebpd, Cebpg, Dbp, Hlf, Cebpe, Nfil3, Atf4, Ddit3, Tef, Pou3f3
metacluster_0/pattern_9 # seqlets: 387 SequenceContrib ScoresHyp_Contrib Scores	Jun, Jund, Fos, Bach2, Fosl1, Nfe2l2, Nfe2, Bach1, Fosb, Junb, Batf, Mafk, Mafa, Mafg, Mafb, Maff, Maf
metacluster_0/pattern_10 # seqlets: 328 SequenceContrib ScoresHyp_Contrib Scores	Irf7, Stat1, Stat2, Irf5, Batf3, Irf6
metacluster_0/pattern_11 # seqlets: 321 SequenceContrib ScoresHyp_Contrib Scores	Fev
metacluster_0/pattern_12 # seqlets: 319 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_13 # seqlets: 250 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_0/pattern_14 # seqlets: 215 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_0/pattern_15 # seqlets: 141 SequenceContrib ScoresHyp_Contrib Scores	Gata4, Gata2, Tal1, Gata1, Gata6, Gata3, Gata5
metacluster_0/pattern_16 # seqlets: 49 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Foxa2