# Parameters
data_name = "ILC1;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_107-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_107-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 19:04:25,529 [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(WT)
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	97039	73602	11.7339	32132472	4625368	0.144	3401626	0.1059	11320082	0.3525
rep2	97039	73602	15.5455	27711464	6072822	0.2193	3837395	0.1386	10384063	0.375

Metric	Value
auPRC	0.5906
Calibrated Recall at 50% FDR	0.209
Number of Positive Examples in Test Data	83947
Number of Negative Examples in Test Data	7986904
Imbalance Ratio in Test Data	0.0104
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 5811 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 4706 SequenceContrib ScoresHyp_Contrib Scores	Erg, Ets1, Etv4, Elk1, Etv2, Gabpa, Fli1, Elk4, Spi1, Etv6, Elf2, Etv5, Elk3, Spib, Ehf, Fev, Elf1, Etv3, XP_911724.4, Etv1, Elf3, Elf4, Stat4, Irf8, Irf4, Ets2, Elf5, Spdef, Stat3, Spic
metacluster_1/pattern_2 # seqlets: 3373 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf6, Klf7, Klf4, Egr1, Klf8, Klf1, Klf12, Zbtb17, Egr2, Sp5, E2f1, Zfp281, Klf5, Zfx
metacluster_1/pattern_3 # seqlets: 1373 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_4 # seqlets: 1217 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Stat1, Prdm1, Irf7, Irf3, Stat2, Batf3, Irf9
metacluster_1/pattern_5 # seqlets: 1198 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_6 # seqlets: 1016 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_7 # seqlets: 950 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf7, Creb5, Jdp2, Atf2, Atf1, Crem, Jun, Nfil3, Mafb, Tef, Rxrb, Atf3, Dbp, Fosl1, Hlf, Cebpb, Gmeb2
metacluster_1/pattern_8 # seqlets: 806 SequenceContrib ScoresHyp_Contrib Scores	Nfkb1, Rela, Nfkb2, Relb, Rel
metacluster_1/pattern_9 # seqlets: 772 SequenceContrib ScoresHyp_Contrib Scores	Fosl2, Batf, Fosb, Fos, Junb, Jund, Bach2, Nfe2, Nfe2l2, Bach1, Mafa, Mafk
metacluster_1/pattern_10 # seqlets: 617 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_11 # seqlets: 598 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_12 # seqlets: 562 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Zfp42, Wt1
metacluster_1/pattern_13 # seqlets: 453 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Usf2, Tfeb, Arntl, Tfe3, Tfec, Mitf, Clock, Srebf1, Bhlhe40, Arnt, Mlx, Npas2, Mycn, Creb3l2, Srebf2, Max, Myc, Tcfl5, Xbp1, Bhlhe41, Mlxip, Hes1
metacluster_1/pattern_14 # seqlets: 340 SequenceContrib ScoresHyp_Contrib Scores	Rorc, Pparg, Nr1d2, Rora, Ppara, Nr1d1
metacluster_1/pattern_15 # seqlets: 182 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_16 # seqlets: 146 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_17 # seqlets: 93 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_1/pattern_18 # seqlets: 84 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_19 # seqlets: 74 SequenceContrib ScoresHyp_Contrib Scores