# Parameters
data_name = "AML;AE9a;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_145-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_145-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 19:11:55,560 [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	Ckit Mice cells AE9a (AML)
Cell Group	Cancer or Immortalized 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	191860	154261	8.7801	69330884	15587785	0.2249	8044624	0.1161	26874663	0.3877
rep2	191860	154261	10.3657	58011754	16424451	0.2832	7872148	0.1357	23817243	0.4107

Metric	Value
auPRC	0.5125
Calibrated Recall at 50% FDR	0.271
Number of Positive Examples in Test Data	161644
Number of Negative Examples in Test Data	7909207
Imbalance Ratio in Test Data	0.02
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 6574 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 4943 SequenceContrib ScoresHyp_Contrib Scores	Etv4, Spi1, Ets1, Spib, Etv2, Etv6, Erg, Gabpa, Fli1, Etv3, Elk1, XP_911724.4, Elk4, Irf8, Irf4, Elk3, Elf4, Elf2, Spic, Etv1, Etv5, Ehf, Elf5, Elf3, Elf1, Fev, Spdef, Prdm1, Irf3, Irf2, Zscan10
metacluster_1/pattern_2 # seqlets: 3293 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Klf3, Klf4, Sp2, Sp3, Klf7, Klf1, Klf8, Klf12, Klf6, Sp1, E2f4, Egr1, Klf5, Egr2, Zbtb17, E2f1, Zfp740, Sall4, Zfp281, Sp5, Egr3, Zbtb1
metacluster_1/pattern_3 # seqlets: 1042 SequenceContrib ScoresHyp_Contrib Scores	Gata4, Gata2, Tal1, Gata1, Gata6, Gata3, Gata5
metacluster_1/pattern_4 # seqlets: 968 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_5 # seqlets: 941 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic
metacluster_1/pattern_6 # seqlets: 881 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_7 # seqlets: 782 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_8 # seqlets: 728 SequenceContrib ScoresHyp_Contrib Scores	Bach2, Nfe2l2, Nfe2, Bach1, Mafk, Mafa, Jun, Mafb, Mafg, Atf3, Maff, Maf, Fosb, Fosl2, Junb, Fosl1, Jund, Batf, Fos, Jdp2
metacluster_1/pattern_9 # seqlets: 718 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfx, Zfp42, Maz, Wt1, Mxi1, Usf2
metacluster_1/pattern_10 # seqlets: 609 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Creb1, Creb5, Atf1, Crem, Nfil3, Hlf, Dbp, Tef, Creb3l2, Cebpb, Tfec, Usf1, Cebpa, Srebf1, Tfe3, Atf4, Rxrb, Cebpg, Mlx
metacluster_1/pattern_11 # seqlets: 576 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Stat1, Irf7, Stat2, Irf9, Batf3
metacluster_1/pattern_12 # seqlets: 446 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_13 # seqlets: 348 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_14 # seqlets: 284 SequenceContrib ScoresHyp_Contrib Scores	Tfeb, Arntl, Mitf, Bhlhe40, Clock, Arnt, Npas2, Srebf2, Tcfl5, Mycn, Max, Bhlhe41, Myc, Xbp1, Mlxip
metacluster_1/pattern_15 # seqlets: 159 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_16 # seqlets: 139 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_17 # seqlets: 98 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_18 # seqlets: 47 SequenceContrib ScoresHyp_Contrib Scores	Rest