# Parameters
data_name = "SHRT_TRM_HSC;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_76-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_76-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 18:57:54,134 [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	Short Term HSC
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	133030	96939	10.2235	20036786	3717914	0.1857	3539382	0.1768	7352365	0.3673
rep2	133030	96939	17.6945	25151359	6351800	0.2527	4752093	0.1891	8887409	0.3536

Metric	Value
auPRC	0.6075
Calibrated Recall at 50% FDR	0.195
Number of Positive Examples in Test Data	112530
Number of Negative Examples in Test Data	7958321
Imbalance Ratio in Test Data	0.0139
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 3960 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 3418 SequenceContrib ScoresHyp_Contrib Scores	Spib, Spi1, Spic, Irf8, Irf4, Etv2, Etv6, Etv4, Elf3, Ets1, Etv3, Ehf, Gabpa, Elk1, Erg, XP_911724.4, Fli1, Elf4, Irf3, Prdm1, Elf2, Elk4, Elk3, Elf5, Etv1, Irf2, Elf1, Etv5, Irf1
metacluster_1/pattern_2 # seqlets: 3079 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp4, Sp3, Klf3, Sp1, E2f4, Klf6, Klf7, Klf4, Klf8, Klf1, Klf12, Egr1, Zbtb17, Egr2, E2f1, Sp5, Klf5, Zfp281, Zfx, Zfp740, Zbtb1, Egr3
metacluster_1/pattern_3 # seqlets: 1798 SequenceContrib ScoresHyp_Contrib Scores	Fev, Spdef, Mbd2, E2f3
metacluster_1/pattern_4 # seqlets: 1511 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf1, Tfe3, Jdp2, Tfec, Srebf1, Creb5, Usf1, Tfeb, Atf7, Mitf, Arntl, Crem, Atf2, Mlx, Bhlhe40, Xbp1, Usf2, Clock, Srebf2, Rxrb, Atf3, Creb3l2, Tef, Npas2, Nfil3, Jun, Dbp, Arnt, Hlf
metacluster_1/pattern_5 # seqlets: 1360 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_6 # seqlets: 1134 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_7 # seqlets: 1091 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_8 # seqlets: 805 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_9 # seqlets: 782 SequenceContrib ScoresHyp_Contrib Scores	Stat1, Irf7, Stat2, Irf9
metacluster_1/pattern_10 # seqlets: 745 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Zfp42, Mxi1
metacluster_1/pattern_11 # seqlets: 720 SequenceContrib ScoresHyp_Contrib Scores	Nfe2, Bach2, Nfe2l2, Bach1, Mafk, Mafa, Mafb, Mafg, Maff, Maf, Fosb, Fosl2, Junb, Batf, Fosl1, Jund, Fos
metacluster_1/pattern_12 # seqlets: 701 SequenceContrib ScoresHyp_Contrib Scores	Stat4
metacluster_1/pattern_13 # seqlets: 482 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_1/pattern_14 # seqlets: 450 SequenceContrib ScoresHyp_Contrib Scores	Gata1, Gata4, Tal1, Gata6, Gata2, Gata5, Gata3
metacluster_1/pattern_15 # seqlets: 378 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_16 # seqlets: 360 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_17 # seqlets: 347 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic