# Parameters
data_name = "ILC1_AbxGRMFree;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_110-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_110-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 19:04:39,891 [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	ILC1_AbxGermFree
Cell Group	Other Immune 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	83210	61208	16.4294	21962388	3640936	0.1659	2781801	0.1268	7630087	0.3477
rep2	83210	61208	10.3344	29522650	3549119	0.1203	2833919	0.096	9741478	0.3302

Metric	Value
auPRC	0.5801
Calibrated Recall at 50% FDR	0.211
Number of Positive Examples in Test Data	69188
Number of Negative Examples in Test Data	8001663
Imbalance Ratio in Test Data	0.0086
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 4268 SequenceContrib ScoresHyp_Contrib Scores	Erg, Ets1, Fli1, Etv2, Elk1, Etv4, Gabpa, Elk4, Etv5, Elk3, Etv6, Spi1, Etv3, XP_911724.4, Fev, Etv1, Elf2, Elf4, Elf1, Spib, Ehf, Elf5, Elf3, Spdef, Spic, Irf8, Irf4, Stat3, Stat4, Zscan10, Stat6
metacluster_1/pattern_1 # seqlets: 4063 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_2 # seqlets: 3299 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf6, Klf7, Klf4, Klf8, Egr1, Klf12, Klf1, Zbtb17, Egr2, Sp5, E2f1, Zfp281, Klf5, Zfx, Egr3, Wt1
metacluster_1/pattern_3 # seqlets: 1622 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Creb5, Atf7, Jdp2, Atf2, Atf1, Crem, Jun, Nfil3, Tef, Mafb, Fosl1, Dbp, Rxrb, Gmeb2, Atf3, Hlf, Cebpb, Junb, Jund, Fosl2, Cebpa, Gmeb1
metacluster_1/pattern_4 # seqlets: 1410 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_5 # seqlets: 1295 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_6 # seqlets: 1155 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Pbx3, Foxi1
metacluster_1/pattern_7 # seqlets: 974 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf7, Prdm1, Stat1, Stat2, Irf9, Irf3, Batf3
metacluster_1/pattern_8 # seqlets: 902 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Zfp42, Maz
metacluster_1/pattern_9 # seqlets: 849 SequenceContrib ScoresHyp_Contrib Scores	Fosb, Fos, Bach2, Batf, Bach1, Nfe2, Nfe2l2, Mafa, Mafk, Mafg
metacluster_1/pattern_10 # seqlets: 703 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_11 # seqlets: 647 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_12 # seqlets: 603 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_13 # seqlets: 503 SequenceContrib ScoresHyp_Contrib Scores	Nfkb1, Rela, Nfkb2, Relb, Rel
metacluster_1/pattern_14 # seqlets: 407 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Usf2, Tfe3, Tfeb, Tfec, Arntl, Mitf, Srebf1, Bhlhe40, Clock, Arnt, Mlx, Npas2, Srebf2, Creb3l2, Tcfl5, Mycn, Max, Myc, Bhlhe41, Xbp1
metacluster_1/pattern_15 # seqlets: 313 SequenceContrib ScoresHyp_Contrib Scores	Rorc, Pparg, Nr1d2, Rora
metacluster_1/pattern_16 # seqlets: 83 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_17 # seqlets: 55 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Pou2f1
metacluster_1/pattern_18 # seqlets: 54 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic