# Parameters
data_name = "ROD_PHT_RCPTR;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_150-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_150-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 19:13:28,691 [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	rod photoreceptors
Cell Group	Neural Cells and Tissues
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	101710	80801	18.3134	27113832	7229300	0.2668	5845481	0.2157	9622188	0.3551
rep2	101710	80801	15.8442	33786975	8107787	0.2401	6421735	0.1902	12226199	0.362

Metric	Value
auPRC	0.6354
Calibrated Recall at 50% FDR	0.163
Number of Positive Examples in Test Data	86434
Number of Negative Examples in Test Data	7984417
Imbalance Ratio in Test Data	0.0107
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 6606 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 3493 SequenceContrib ScoresHyp_Contrib Scores	Crx, Otx2, Otx1, Pax7, Dmbx1, Obox6
metacluster_1/pattern_2 # seqlets: 1909 SequenceContrib ScoresHyp_Contrib Scores	Nrf1, Zfx, Sp2
metacluster_1/pattern_3 # seqlets: 1518 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Fli1, Ets1, Elk4, Elk1, Elf1, Erg, Elk3, Etv4, Etv1, Etv2, Fev, Etv5, Ehf, Etv3, XP_911724.4, Etv6, Elf5, Elf3, Elf4, Elf2, Spdef, Spi1, E2f3, Mbd2
metacluster_1/pattern_4 # seqlets: 1461 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp3, Sp1, Klf3, E2f4, Klf6, Egr1, Klf7, Klf4, Klf8, Klf1, Klf12, Sp5, Zbtb17
metacluster_1/pattern_5 # seqlets: 1458 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Foxi1, Nfyc, Nfya, Pbx3
metacluster_1/pattern_6 # seqlets: 1446 SequenceContrib ScoresHyp_Contrib Scores	Klf5, Wt1, Egr2, Klf15, Zfp281, Maz, E2f1, Zfp740, Sall4, Nr1h4, Usf2, Zbtb1, Mxi1, E2f7, Srebf2
metacluster_1/pattern_7 # seqlets: 999 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_8 # seqlets: 741 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Rfx1
metacluster_1/pattern_9 # seqlets: 666 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_10 # seqlets: 627 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Atf7, Jdp2, Crem, Atf1, Creb5, Atf3, Usf1, Fosl2, Jun, Nfil3, Hlf, Fosl1, Tef
metacluster_1/pattern_11 # seqlets: 607 SequenceContrib ScoresHyp_Contrib Scores	Tfe3, Tfeb, Arntl, Tfec, Mitf, Clock, Arnt, Bhlhe40, Srebf1, Mlx, Npas2, Tcfl5, Mycn, Bhlhe41, Rxrg, Creb3l2, Max, Myc, Rxrb
metacluster_1/pattern_12 # seqlets: 385 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_13 # seqlets: 307 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_14 # seqlets: 184 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_15 # seqlets: 140 SequenceContrib ScoresHyp_Contrib Scores	Stat4
metacluster_1/pattern_16 # seqlets: 97 SequenceContrib ScoresHyp_Contrib Scores	Rorc, Pparg, Nr1d2, Rorb, Rora, Esr2