# Parameters
data_name = "pCMP;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_194-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_194-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 19:24:42,551 [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	Common myeloid progenitor primary 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	149530	99201	13.2877	25987572	5283275	0.2035	3488734	0.1343	10974790	0.4226
rep2	149530	99201	14.3173	21414655	4649433	0.2173	3122243	0.1459	9109933	0.4258

Metric	Value
auPRC	0.6136
Calibrated Recall at 50% FDR	0.231
Number of Positive Examples in Test Data	118406
Number of Negative Examples in Test Data	7952445
Imbalance Ratio in Test Data	0.0147
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 9087 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 5872 SequenceContrib ScoresHyp_Contrib Scores	Spi1, Spib, Irf8, Irf4, Etv2, Elf3, Ehf, Ets1, Spic, Erg, Prdm1, Etv6, Irf3, Gabpa, Elf1, Etv4, Elk1, Elf5, Etv3, Elf4, Irf2, Fli1, Irf1, XP_911724.4, Elk4, Elf2, Elk3, Etv1, Etv5, Ets2
metacluster_1/pattern_2 # seqlets: 3127 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Klf3, Sp3, Sp1, Klf6, E2f4, Klf7, Klf4, Klf8, Klf1, Klf12, Egr1, Egr2, Zbtb17, E2f1, Sp5, Klf5, Zfp281, Egr3, Zfx, Zfp740, Zbtb1
metacluster_1/pattern_3 # seqlets: 1309 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_4 # seqlets: 1130 SequenceContrib ScoresHyp_Contrib Scores	Irf7, Stat2, Stat1, Zscan10, Irf9
metacluster_1/pattern_5 # seqlets: 915 SequenceContrib ScoresHyp_Contrib Scores	Gata4, Gata1, Gata6, Gata2, Tal1, Gata5, Gata3
metacluster_1/pattern_6 # seqlets: 907 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Foxi1, Nfya, Pbx3
metacluster_1/pattern_7 # seqlets: 882 SequenceContrib ScoresHyp_Contrib Scores	Bach2, Nfe2, Nfe2l2, Bach1, Mafk, Mafa, Jun, Mafg, Mafb, Maff, Atf3, Maf, Fosb, Fosl2, Junb, Fosl1, Jund, Fos, Batf, Jdp2
metacluster_1/pattern_8 # seqlets: 830 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_9 # seqlets: 482 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Usf2, Atf7, Atf2, Crem, Atf1, Creb5, Nfil3
metacluster_1/pattern_10 # seqlets: 471 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_11 # seqlets: 466 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Cebpd, Cebpg, Dbp, Hlf, Cebpe, Atf4, Ddit3, Tef
metacluster_1/pattern_12 # seqlets: 415 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_13 # seqlets: 370 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_14 # seqlets: 325 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx1, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_15 # seqlets: 279 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic, Zfp322a
metacluster_1/pattern_16 # seqlets: 229 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfe3, Tfeb, Arntl, Tfec, Mitf, Bhlhe40, Srebf1, Clock, Arnt, Mlx, Srebf2, Npas2, Wt1, Rxrg, Mxi1, Tcfl5, Nr1h4, Bhlhe41, Rxrb, Max, Mycn, Creb3l2, Rxra, Myc, Maz, Nr2f1, Klf15, Mlxip
metacluster_1/pattern_17 # seqlets: 179 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_1/pattern_18 # seqlets: 156 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_19 # seqlets: 82 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_20 # seqlets: 72 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2c, Mef2a
metacluster_1/pattern_21 # seqlets: 49 SequenceContrib ScoresHyp_Contrib Scores