# Parameters
data_name = "MegEP;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_191-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_191-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 19:24:01,763 [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	Megakaryocyte-erythroid progenitor cell
Cell Group	Other Immune Cells
Experiment Name	ATAC
Experiment Group	ENCODE

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	120903	79742	8.4493	36753781	4047557	0.1102	3728438	0.1015	13691684	0.3727
rep2	120903	79742	9.0502	35701056	4599648	0.1289	3854372	0.108	13383561	0.3751

Metric	Value
auPRC	0.5575
Calibrated Recall at 50% FDR	0.243
Number of Positive Examples in Test Data	91857
Number of Negative Examples in Test Data	7978994
Imbalance Ratio in Test Data	0.0114
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 8332 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 2672 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Klf3, Sp3, Sp1, E2f4, Klf6, Klf7, Klf4, Klf8, Klf1, Klf12, Egr1, Zbtb17, Egr2, E2f1, Klf5, Sp5, Zfp281, Zfp740, Zfx, Zbtb1, Egr3
metacluster_1/pattern_2 # seqlets: 1667 SequenceContrib ScoresHyp_Contrib Scores	Gata4, Gata1, Gata6, Gata2, Tal1, Gata5, Gata3
metacluster_1/pattern_3 # seqlets: 1659 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elk1, Elk3, Elk4, Fli1, Erg, Ets1, Etv6, Etv5, Etv3, Etv4, Etv1, XP_911724.4, Elf1, Etv2, Elf4, Elf2, Elf5, Ehf, Fev, Spi1, Spib, Spic, Spdef, Elf3, Irf4, Irf8
metacluster_1/pattern_4 # seqlets: 1163 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Pbx3, Foxi1
metacluster_1/pattern_5 # seqlets: 982 SequenceContrib ScoresHyp_Contrib Scores	Sall4
metacluster_1/pattern_6 # seqlets: 956 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_7 # seqlets: 779 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_8 # seqlets: 773 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_9 # seqlets: 690 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_1/pattern_10 # seqlets: 519 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Usf2, Atf2, Atf7, Jdp2, Atf1, Crem, Creb5, Atf3, Usf1, Fosl2, Hlf, Rfx1, Nfil3, Jun, Srebf2, Tef, Dbp, Tfe3, Rxrb
metacluster_1/pattern_11 # seqlets: 451 SequenceContrib ScoresHyp_Contrib Scores	Bach2, Nfe2, Nfe2l2, Bach1, Mafk, Mafa, Mafb, Mafg, Maff, Maf, Fosb, Junb, Fosl1, Jund, Batf, Fos
metacluster_1/pattern_12 # seqlets: 350 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Stat1, Prdm1, Irf7, Irf3, Stat2, Irf9, Batf3
metacluster_1/pattern_13 # seqlets: 321 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Wt1, Maz
metacluster_1/pattern_14 # seqlets: 286 SequenceContrib ScoresHyp_Contrib Scores	Tfeb, Arntl, Tfec, Mitf, Clock, Bhlhe40, Arnt, Srebf1, Mlx, Npas2, Mxi1, Tcfl5, Bhlhe41, Nr1h4, Creb3l2, Mycn, Rxrg, Max, Myc
metacluster_1/pattern_15 # seqlets: 174 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_16 # seqlets: 111 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_17 # seqlets: 81 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_18 # seqlets: 55 SequenceContrib ScoresHyp_Contrib Scores