# Parameters
data_name = "BSPHL;A;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_19-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_19-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 18:44:28,086 [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	basophils
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	174457	144811	26.825	12962452	7488055	0.5785	4642303	0.3586	5768483	0.4456
rep2	174457	144811	28.2415	10487771	6040733	0.5769	3826702	0.3655	4635920	0.4428
rep3	174457	144811	16.6966	33036477	16660505	0.5046	7634688	0.2312	14951421	0.4528
rep4	174457	144811	23.1443	17160668	9900039	0.5775	5843636	0.3409	7655375	0.4466

Metric	Value
auPRC	0.6121
Calibrated Recall at 50% FDR	0.212
Number of Positive Examples in Test Data	169357
Number of Negative Examples in Test Data	7901494
Imbalance Ratio in Test Data	0.021
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 5561 SequenceContrib ScoresHyp_Contrib Scores	Spib, Spi1, Irf8, Irf4, Etv2, Ets1, Spic, Etv4, Etv6, Erg, Ehf, Elf3, Etv3, Fli1, Gabpa, Elk1, XP_911724.4, Elf1, Elk4, Elf4, Elk3, Elf2, Etv1, Etv5, Prdm1, Irf3, Elf5, Irf2, Irf1, Fev, Spdef
metacluster_1/pattern_1 # seqlets: 4727 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_2 # seqlets: 2665 SequenceContrib ScoresHyp_Contrib Scores	Atf3, Fosl1, Fosb, Junb, Jun, Fos, Jund, Fosl2, Bach2, Nfe2, Nfe2l2, Jdp2, Bach1, Batf, Mafk, Mafa
metacluster_1/pattern_3 # seqlets: 2283 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Cebpd, Cebpg, Nfil3, Dbp, Atf4, Ddit3, Hlf, Cebpe, Tef
metacluster_1/pattern_4 # seqlets: 1898 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf6, Klf7, Klf4, Klf1, Egr1, Klf8, Klf12, Zbtb17, Egr2, E2f1, Sp5, Zfx, Klf5, Zfp281
metacluster_1/pattern_5 # seqlets: 1115 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Pbx3, Foxi1
metacluster_1/pattern_6 # seqlets: 1050 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_7 # seqlets: 869 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Creb5, Atf7, Atf2, Atf1, Crem, Mafb, Gmeb2, Rxrb
metacluster_1/pattern_8 # seqlets: 856 SequenceContrib ScoresHyp_Contrib Scores	Gata4, Gata2, Tal1, Gata1, Gata3, Gata6, Mecom, Gata5
metacluster_1/pattern_9 # seqlets: 697 SequenceContrib ScoresHyp_Contrib Scores	Irf7, Stat1, Stat2, Irf9, Irf5, Batf3
metacluster_1/pattern_10 # seqlets: 680 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_11 # seqlets: 589 SequenceContrib ScoresHyp_Contrib Scores	Hes7, Hes1
metacluster_1/pattern_12 # seqlets: 560 SequenceContrib ScoresHyp_Contrib Scores	Yy1, Taf1, Zfp42, Rfx1, Wt1, Maz, Usf2, Mxi1
metacluster_1/pattern_13 # seqlets: 397 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_1/pattern_14 # seqlets: 370 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_15 # seqlets: 331 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfe3, Tfeb, Arntl, Tfec, Mitf, Bhlhe40, Arnt, Srebf1, Clock, Mlx, Srebf2, Npas2, Tcfl5, Bhlhe41, Creb3l2, Max, Mycn, Myc, Rarg
metacluster_1/pattern_16 # seqlets: 206 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_17 # seqlets: 183 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_18 # seqlets: 106 SequenceContrib ScoresHyp_Contrib Scores	Mbd2
metacluster_1/pattern_19 # seqlets: 79 SequenceContrib ScoresHyp_Contrib Scores	Stat5b, Stat5a, Stat4, Stat6
metacluster_1/pattern_20 # seqlets: 69 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_21 # seqlets: 60 SequenceContrib ScoresHyp_Contrib Scores	Tfap2b
metacluster_1/pattern_22 # seqlets: 37 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Zfp322a