# Parameters
data_name = "CD4+CD8-TCR+CD25-Foxp3+;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_41-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_41-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 18:49:02,845 [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	CD4+CD8-TCRhi CD25-Foxp3+
Cell Group	T 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	109043	83403	16.1576	9895974	1283074	0.1299	1222315	0.1237	3122130	0.3161
rep2	109043	83403	11.3524	40345667	7473028	0.1853	5328740	0.1321	14080833	0.3492

Metric	Value
auPRC	0.5724
Calibrated Recall at 50% FDR	0.234
Number of Positive Examples in Test Data	86569
Number of Negative Examples in Test Data	7984282
Imbalance Ratio in Test Data	0.0107
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 6814 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Etv4, Etv2, Fli1, Elk1, Elk4, Gabpa, Etv5, Spi1, Elk3, Etv6, Fev, Elf2, XP_911724.4, Etv3, Etv1, Spib, Elf1, Elf4, Ehf, Elf5, Elf3, Irf8, Spdef, Spic, Irf4, Stat3, Zscan10, Stat4
metacluster_1/pattern_1 # seqlets: 4111 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_2 # seqlets: 3463 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf6, Klf7, Klf4, Klf8, Klf12, Klf1, Egr1, Zbtb17, Egr2, E2f1, Klf5, Sp5, Zfp281, Zfx, Zfp740, Egr3, Zbtb1
metacluster_1/pattern_3 # seqlets: 1528 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_4 # seqlets: 1232 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf7, Prdm1, Stat1, Irf3, Stat2, Irf9, Batf3
metacluster_1/pattern_5 # seqlets: 1199 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_6 # seqlets: 794 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Jdp2, Atf2, Atf7, Crem, Usf2, Creb5, Atf3, Atf1, Fosl2, Jun, Nfil3, Tef, Fosl1
metacluster_1/pattern_7 # seqlets: 781 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_8 # seqlets: 661 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Wt1, Maz, Rfx1
metacluster_1/pattern_9 # seqlets: 652 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb
metacluster_1/pattern_10 # seqlets: 630 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfe3, Tfeb, Arntl, Tfec, Mitf, Srebf1, Clock, Bhlhe40, Arnt, Mlx, Npas2, Srebf2, Tcfl5, Mycn, Hlf, Max, Myc, Creb3l2, Bhlhe41, Xbp1, Mlxip
metacluster_1/pattern_11 # seqlets: 498 SequenceContrib ScoresHyp_Contrib Scores	Jund, Fos, Fosb, Junb, Batf, Bach2, Nfe2, Nfe2l2, Bach1, Mafa, Mafk, Mafb
metacluster_1/pattern_12 # seqlets: 390 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_13 # seqlets: 327 SequenceContrib ScoresHyp_Contrib Scores	Nfkb2, Nfkb1, Rela, Relb, Rel
metacluster_1/pattern_14 # seqlets: 282 SequenceContrib ScoresHyp_Contrib Scores	Sox2, Pou5f1
metacluster_1/pattern_15 # seqlets: 194 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_16 # seqlets: 161 SequenceContrib ScoresHyp_Contrib Scores	Tcf7l2, Lef1, Tcf7l1, Tcf3, Tcf7
metacluster_1/pattern_17 # seqlets: 132 SequenceContrib ScoresHyp_Contrib Scores	Gata3
metacluster_1/pattern_18 # seqlets: 121 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_19 # seqlets: 108 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_20 # seqlets: 88 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_21 # seqlets: 74 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2
metacluster_1/pattern_22 # seqlets: 73 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_23 # seqlets: 67 SequenceContrib ScoresHyp_Contrib Scores	Nr2f1, Nr2f6, Nr4a2, Nr2c2, Esrrb, Nr2e3, Rxra, Rxrb, Esrra, Nr5a2, Nr1h3, Rara, Rarg, Esrrg, Ppara, Rarb, Mybl1, Rxrg, Nr2c1, Pparg, Hnf4g, Nr2e1
metacluster_1/pattern_24 # seqlets: 64 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic