# Parameters
data_name = "iNKT;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_136-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_136-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 19:10:47,075 [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	Invariant NKT (iNKT) cells
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	127059	96922	15.6394	19703415	4451133	0.2261	3192489	0.1622	6946479	0.3529
rep2	127059	96922	18.6884	16390733	5107456	0.312	3617859	0.221	6048824	0.3695
rep3	127059	96922	11.6282	31918058	6007125	0.1883	4718452	0.1479	11282392	0.3537

Metric	Value
auPRC	0.5869
Calibrated Recall at 50% FDR	0.228
Number of Positive Examples in Test Data	108873
Number of Negative Examples in Test Data	7961978
Imbalance Ratio in Test Data	0.0135
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 6000 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Etv4, Etv2, Elk1, Gabpa, Fli1, Elk4, Elf2, Spi1, Etv6, Etv5, Elk3, Ehf, Fev, Spib, Elf1, Elf3, Etv3, XP_911724.4, Etv1, Stat4, Elf4, Irf8, Ets2, Irf4, Elf5, Stat3, Spdef
metacluster_1/pattern_1 # seqlets: 5899 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_2 # seqlets: 2487 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf6, Klf7, Egr1, Klf4, Klf8, Klf12, Klf1, Zbtb17, Egr2, Sp5, E2f1, Zfp281, Klf5, Egr3, Zfx
metacluster_1/pattern_3 # seqlets: 1233 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Stat1, Prdm1, Irf7, Stat2, Irf3, Irf9, Batf3
metacluster_1/pattern_4 # seqlets: 1209 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_5 # seqlets: 1125 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_6 # seqlets: 1121 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_7 # seqlets: 901 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_8 # seqlets: 741 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf1, Atf2, Creb1, Creb5, Jdp2, Crem, Rxrb, Dbp, Jun, Nfil3, Hlf, Mafb, Tfec, Tef, Atf3, Srebf1, Cebpb, Bhlhe40, Cebpa
metacluster_1/pattern_9 # seqlets: 660 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Usf2, Tfeb, Arntl, Mitf, Tfe3, Clock, Mlx, Arnt, Npas2, Srebf2, Tcfl5, Creb3l2, Bhlhe41, Xbp1, Mlxip
metacluster_1/pattern_10 # seqlets: 655 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_1/pattern_11 # seqlets: 641 SequenceContrib ScoresHyp_Contrib Scores	Hes7, Hes1
metacluster_1/pattern_12 # seqlets: 465 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx1, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_13 # seqlets: 250 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_1/pattern_14 # seqlets: 247 SequenceContrib ScoresHyp_Contrib Scores	Fos, Fosl2, Fosl1, Jund, Batf, Fosb, Junb, Mafa, Bach2, Mafk, Nfe2l2, Nfe2, Bach1, Mafg, Maff, Maf
metacluster_1/pattern_15 # seqlets: 224 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_16 # seqlets: 187 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_17 # seqlets: 154 SequenceContrib ScoresHyp_Contrib Scores	Tcf7l1, Tcf7l2, Lef1
metacluster_1/pattern_18 # seqlets: 136 SequenceContrib ScoresHyp_Contrib Scores	Nfkb2, Nfkb1, Rela, Relb, Rel
metacluster_1/pattern_19 # seqlets: 107 SequenceContrib ScoresHyp_Contrib Scores	Gata3, Gata1, Gata2, Gata4, Gata6, Tal1
metacluster_1/pattern_20 # seqlets: 94 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_21 # seqlets: 57 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33, Wt1
metacluster_1/pattern_22 # seqlets: 42 SequenceContrib ScoresHyp_Contrib Scores