# Parameters
data_name = "SML_INTSTN;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_52-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_52-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 18:51:17,445 [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	Small Intestine
Cell Group	Other Tissues
Experiment Name	ATAC
Experiment Group	Casellas Lab

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	121670	77242	13.4635	10542151	1255555	0.1193	1292416	0.1228	3804706	0.3615
rep2	121670	77242	9.4448	44548119	5202199	0.1168	4276954	0.096	15948587	0.3582

Metric	Value
auPRC	0.5977
Calibrated Recall at 50% FDR	0.214
Number of Positive Examples in Test Data	86186
Number of Negative Examples in Test Data	7984665
Imbalance Ratio in Test Data	0.0107
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 4792 SequenceContrib ScoresHyp_Contrib Scores	Klf3, Sp4, Klf6, Sp3, Klf7, Sp1, Klf1, Klf8, Sp2, Klf12, Klf4, Klf5, E2f4, Egr1, Zbtb17, Klf15, E2f1, Egr2, Sp5, E2f7, Zfp281, Maz, Wt1
metacluster_0/pattern_1 # seqlets: 3224 SequenceContrib ScoresHyp_Contrib Scores	Etv4, Ehf, Elf2, Elf3, Ets1, Elk1, Etv6, Gabpa, Elk4, Elf1, Elf5, Elk3, Fli1, Erg, Etv3, XP_911724.4, Elf4, Etv2, Etv1, Spdef, Etv5, Spic, Fev, Spi1, Spib, Zic2, Irf4, Irf8, Zic3
metacluster_0/pattern_2 # seqlets: 2344 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_3 # seqlets: 1427 SequenceContrib ScoresHyp_Contrib Scores	Hnf4g, Hnf4a, Nr1h3, Rxra, Nr2f6, Nr2c2, Rxrb, Ppara, Pparg, Nr2f1, Nr5a2, Rarg, Nr5a1, Nr2c1, Nr2e3, Nr4a2, Rara, Rarb, Esrra
metacluster_0/pattern_4 # seqlets: 1415 SequenceContrib ScoresHyp_Contrib Scores	Evx2, Cdx2, Hoxb13, Hoxa13, Hoxc13, Hoxd9, Hoxb9, Hoxd13, Hoxa11, Hoxc11, Hoxc12, Hoxc10, Hoxa9, Hoxd10, Hoxd11, Cdx1, Hoxa10, Hoxd8, Hoxb7, Hoxc8, Cdx4, Hoxa7, Evx1, Meis1, Hoxc9, Hoxb8, Hoxa6
metacluster_0/pattern_5 # seqlets: 1102 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_6 # seqlets: 1076 SequenceContrib ScoresHyp_Contrib Scores	Nfyc, Nfyb, Nfya, Foxi1, Pbx3
metacluster_0/pattern_7 # seqlets: 983 SequenceContrib ScoresHyp_Contrib Scores	Atf1, Atf7, Creb1, Atf2, Tfec, Creb5, Bhlhe40, Jdp2, Usf1, Srebf1, Crem, Tfe3, Mitf, Usf2, Mlx, Tfeb, Srebf2, Arntl, Clock, Dbp, Xbp1, Hlf, Tef, Nfil3, Creb3l2, Atf3, Jun, Mafb, Cebpb, Npas2, Bhlhe41, Tcfl5, Cebpa
metacluster_0/pattern_8 # seqlets: 779 SequenceContrib ScoresHyp_Contrib Scores	Fosl2, Batf, Fos, Jund, Fosb, Junb, Fosl1, Bach2, Bach1, Nfe2, Nfe2l2, Mafa, Mafk
metacluster_0/pattern_9 # seqlets: 728 SequenceContrib ScoresHyp_Contrib Scores	Foxa2, Foxm1, Foxd3, Foxa3, Foxa1, Foxb1, Foxc1, Foxc2, Foxd1, Foxj2, Foxg1, Foxl1, Foxk1, Foxp2, Foxj3, Foxp1, Foxo3, Foxo1, Foxl2, Gm5294
metacluster_0/pattern_10 # seqlets: 610 SequenceContrib ScoresHyp_Contrib Scores	Hnf1b, Hnf1a
metacluster_0/pattern_11 # seqlets: 585 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Zfx, Zfp42, Mxi1
metacluster_0/pattern_12 # seqlets: 506 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_0/pattern_13 # seqlets: 451 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_14 # seqlets: 423 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf3, Irf7, Stat2, Stat1, Prdm1, Irf9, Batf3
metacluster_0/pattern_15 # seqlets: 185 SequenceContrib ScoresHyp_Contrib Scores	Grhl2
metacluster_0/pattern_16 # seqlets: 101 SequenceContrib ScoresHyp_Contrib Scores	Gata4, Tal1, Gata1, Gata2, Gata6, Gata3, Mecom, Gata5
metacluster_0/pattern_17 # seqlets: 97 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33