# Parameters
data_name = "Heart;D;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_56-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_56-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 18:52:03,101 [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	Heart
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	130707	82136	21.4535	5954075	683659	0.1152	857769	0.1445	2123860	0.3578
rep2	130707	82136	13.2306	38502670	4998168	0.1299	4105237	0.1067	13824122	0.3592
rep3	130707	82136	15.6391	23641085	2972321	0.1258	2844689	0.1204	8491684	0.3595

Metric	Value
auPRC	0.6195
Calibrated Recall at 50% FDR	0.21
Number of Positive Examples in Test Data	93709
Number of Negative Examples in Test Data	7977142
Imbalance Ratio in Test Data	0.0116
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 2263 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Fli1, Gabpa, Elk1, Elk4, Etv5, Etv4, Elk3, Etv2, Fev, Etv6, Etv1, Etv3, Spi1, XP_911724.4, Elf2, Elf1, Elf4, Ehf, Elf5, Spib, Spdef, Elf3, Spic, Irf8, Irf4, Zscan10
metacluster_0/pattern_1 # seqlets: 1936 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_0/pattern_2 # seqlets: 1918 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_3 # seqlets: 1670 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, Klf6, E2f4, Klf4, Klf7, Egr1, Klf1, Klf8, Klf12, Zbtb17, Sp5, Egr2, E2f1, Klf5, Zfp281, Wt1, Zfx
metacluster_0/pattern_4 # seqlets: 1616 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_0/pattern_5 # seqlets: 1175 SequenceContrib ScoresHyp_Contrib Scores	Zfp740, Zbtb1, Sall4
metacluster_0/pattern_6 # seqlets: 1127 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Creb1, Atf2, Creb5, Jdp2, Atf1, Crem, Rxrb, Nfil3, Mafb, Jun, Tef, Atf3, Dbp
metacluster_0/pattern_7 # seqlets: 1026 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_8 # seqlets: 847 SequenceContrib ScoresHyp_Contrib Scores	Lyl1, Olig2, Myog, Atoh1, Tfap4, Twist1, Tcf21, Tal1, Ptf1a, Ascl2, Myf5, Tcf3, Tgif1, Figla, Neurod1, Msc, Myb, Myf6, Ascl1, Myod1, Neurod2, Snai1, Bhlha15, Tcf12, Neurog2, Meis2, Tcf4, Neurog1, Meis3
metacluster_0/pattern_9 # seqlets: 843 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_10 # seqlets: 648 SequenceContrib ScoresHyp_Contrib Scores	Fosl1, Jund, Fosb, Junb, Fos, Fosl2, Batf, Bach2, Nfe2l2, Nfe2, Bach1, Mafa, Mafk
metacluster_0/pattern_11 # seqlets: 595 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfec, Usf2, Tfeb, Mitf, Arntl, Tfe3, Srebf1, Bhlhe40, Clock, Mlx, Npas2, Arnt, Srebf2, Creb3l2, Tcfl5, Bhlhe41, Xbp1, Hlf, Mycn, Mlxip
metacluster_0/pattern_12 # seqlets: 570 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpd, Cebpa, Cebpg, Cebpe, Atf4, Ddit3, Gmeb2
metacluster_0/pattern_13 # seqlets: 459 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Maz, Zfp42, Mxi1, Klf15
metacluster_0/pattern_14 # seqlets: 289 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_0/pattern_15 # seqlets: 259 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf7, Stat2, Irf9, Prdm1, Stat1, Irf5, Irf6, Irf3
metacluster_0/pattern_16 # seqlets: 227 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx4, Rfx7, Rfx6, Stat4
metacluster_0/pattern_17 # seqlets: 192 SequenceContrib ScoresHyp_Contrib Scores	Gata6, Gata4, Gata1, Gata2, Gata5, Gata3
metacluster_0/pattern_18 # seqlets: 194 SequenceContrib ScoresHyp_Contrib Scores	Mbd2
metacluster_0/pattern_19 # seqlets: 187 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_20 # seqlets: 110 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_21 # seqlets: 95 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_22 # seqlets: 92 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33