# Parameters
data_name = "pGMP;A;En"
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_196-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_196-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 19:25:10,911 [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	Granulocyte monocyte 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	159589	110507	15.3855	27182580	8622840	0.3174	4625438	0.1703	12422144	0.4573
rep2	159589	110507	10.7975	43071479	8485775	0.1971	5076150	0.1179	17637162	0.4097

Metric	Value
auPRC	0.6378
Calibrated Recall at 50% FDR	0.222
Number of Positive Examples in Test Data	133027
Number of Negative Examples in Test Data	7937824
Imbalance Ratio in Test Data	0.0165
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 8153 SequenceContrib ScoresHyp_Contrib Scores	Spib, Spi1, Irf8, Irf4, Spic, Elf3, Irf3, Etv2, Prdm1, Ehf, Ets1, Irf2, Irf1, Etv6, Etv4, Elf5, Elf1, Gabpa, Elf4, Elf2, Erg, Etv3, Fli1, Elk1, XP_911724.4
metacluster_1/pattern_1 # seqlets: 8047 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_2 # seqlets: 4246 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Cebpd, Nfil3, Cebpg, Dbp, Hlf, Atf4, Ddit3, Cebpe, Tef
metacluster_1/pattern_3 # seqlets: 2169 SequenceContrib ScoresHyp_Contrib Scores	Stat2, Zscan10, Irf7, Stat1, Irf9
metacluster_1/pattern_4 # seqlets: 1731 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Sp1, Klf3, Klf4, E2f4, Klf7, Sp5, Zbtb17, Klf6, Egr1, Klf8, Klf12, Egr2, Klf5, Klf1, Wt1, Zfp281, Maz, E2f1, Egr3, Zfp740
metacluster_1/pattern_5 # seqlets: 748 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_6 # seqlets: 557 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_7 # seqlets: 542 SequenceContrib ScoresHyp_Contrib Scores	Elk4, Elk3, Etv1, Etv5, Fev, Spdef, Myc
metacluster_1/pattern_8 # seqlets: 461 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_9 # seqlets: 381 SequenceContrib ScoresHyp_Contrib Scores	Nrf1, Zfx
metacluster_1/pattern_10 # seqlets: 304 SequenceContrib ScoresHyp_Contrib Scores	Bcl6
metacluster_1/pattern_11 # seqlets: 286 SequenceContrib ScoresHyp_Contrib Scores	Bach2, Nfe2, Nfe2l2, Bach1, Mafa, Mafk, Jun, Atf3, Fosl2, Mafb, Mafg, Fosl1, Fosb, Junb, Maff, Jund, Fos, Batf, Maf, Jdp2
metacluster_1/pattern_12 # seqlets: 189 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Rfx1, Usf2
metacluster_1/pattern_13 # seqlets: 174 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Cbfb, Runx3
metacluster_1/pattern_14 # seqlets: 153 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_15 # seqlets: 140 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_16 # seqlets: 115 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_17 # seqlets: 112 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_18 # seqlets: 51 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_19 # seqlets: 49 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_20 # seqlets: 39 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_21 # seqlets: 39 SequenceContrib ScoresHyp_Contrib Scores