# Parameters
data_name = "iPV_NRN;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_175-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_175-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 19:19:58,942 [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	parvalbumin-positive (PV) inhibitory neurons
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	244415	175463	8.2016	107232529	18294259	0.1706	10075227	0.094	40350339	0.3764
rep2	244415	175463	9.4307	89739894	16489626	0.1838	8937326	0.0996	33835729	0.3771

Metric	Value
auPRC	0.5743
Calibrated Recall at 50% FDR	0.255
Number of Positive Examples in Test Data	177059
Number of Negative Examples in Test Data	7893792
Imbalance Ratio in Test Data	0.0219
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 3216 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_1 # seqlets: 2746 SequenceContrib ScoresHyp_Contrib Scores	Mef2a, Mef2c, Mef2d
metacluster_1/pattern_2 # seqlets: 2159 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_3 # seqlets: 1790 SequenceContrib ScoresHyp_Contrib Scores	Tcf12, Tcf7l1, Myog, Ascl1, Myf6, Myod1, Bhlha15, Snai2, Nhlh2, Tcf3, Tal1, Ascl2, Tcf4, Tcf21, Ptf1a
metacluster_1/pattern_4 # seqlets: 1359 SequenceContrib ScoresHyp_Contrib Scores	Sp3, Sp2, Sp1, Klf3, Sp4, Klf5, Klf4, Zbtb17, Klf6, Egr1, E2f4, Wt1, Sp5, Klf7, Maz, E2f1, Klf8, Egr2, Klf12, Zfp281, Klf15, Srebf2, Egr3, Sall4, Klf1
metacluster_1/pattern_5 # seqlets: 961 SequenceContrib ScoresHyp_Contrib Scores	Atf3, Fosb, Junb, Fosl2, Fosl1, Jun, Fos, Jund, Batf, Jdp2, Bach2, Nfe2l2, Nfe2, Mafa, Mafk, Bach1, Mafb, Mafg, Maf, Maff, Nfatc1
metacluster_1/pattern_6 # seqlets: 891 SequenceContrib ScoresHyp_Contrib Scores	Dbp, Tef, Nfil3
metacluster_1/pattern_7 # seqlets: 786 SequenceContrib ScoresHyp_Contrib Scores	Dlx3, Phox2a, Phox2b, Nkx1-2, Gbx1, Lhx2, Hoxd3, En2, Barhl1, Lhx3, Nkx1-1, Isx, Lhx8, Barx1, Lhx6, Pdx1, Evx2, Gbx2, Dlx5, Otp, Evx1, Prrx1, Hoxa2, Mnx1, Rax, Vax1, Gsx2, Emx2, Hoxc6, Dlx4, Vax2, Esx1, Msx1, Uncx, Vsx1, Hoxa3, Vsx2, En1, Pou2f1, Meox1, Dbx2, Alx3, Prrx2, Hoxa1, Hoxa5, Hoxb3, Lhx9, Msx3, Dlx2, Dlx1, Hoxb4, Barx2, Nobox, Arx, Isl1, Pax6, Hoxa4, Hoxb5, Hoxc4, Lhx4, Prop1, Pou1f1, Shox2, Alx1, Meox2, Rhox6, Barhl2, Nanog, Alx4, Hoxa7, Hoxa6, Pou6f1, Msx2, Hoxd1, Lbx2, Hoxb6, Noto
metacluster_1/pattern_8 # seqlets: 757 SequenceContrib ScoresHyp_Contrib Scores	Rorc, Rora, Pparg, Ppara, Nr1d2, Esrrg, Nr5a2, Nr1d1, Esr2
metacluster_1/pattern_9 # seqlets: 755 SequenceContrib ScoresHyp_Contrib Scores	Rela, Zfp740, Bcl6, Zscan10
metacluster_1/pattern_10 # seqlets: 718 SequenceContrib ScoresHyp_Contrib Scores	Cic
metacluster_1/pattern_11 # seqlets: 714 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elf1, Elk1, Fli1, Elk4, Elk3, Erg, Ets1, Elf5, Etv5, Fev, Etv1, Etv4, Elf2, Elf4, Etv6, Ehf, XP_911724.4, Etv3, Spi1, Elf3, Etv2, Spdef
metacluster_1/pattern_12 # seqlets: 664 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_1/pattern_13 # seqlets: 518 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Creb5, Creb1, Atf1, Crem, Cebpb, Cebpa, Hlf, Srebf1, Gmeb2, Ddit3, Atf4, Tfec, Rxrb, Cebpd, Mlx, Cebpg
metacluster_1/pattern_14 # seqlets: 472 SequenceContrib ScoresHyp_Contrib Scores	Nrf1, Zfx
metacluster_1/pattern_15 # seqlets: 437 SequenceContrib ScoresHyp_Contrib Scores	Nfyc, Nfyb, Nfya, Foxi1, Pbx3
metacluster_1/pattern_16 # seqlets: 385 SequenceContrib ScoresHyp_Contrib Scores	Usf2, Usf1, Tfeb, Tfe3, Mitf, Arntl, Clock, Npas2, Arnt, Bhlhe40, Creb3l2, Mycn, Tcfl5, Max, Bhlhe41, Xbp1, Myc, Mlxip, Arnt2
metacluster_1/pattern_17 # seqlets: 363 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx1, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_18 # seqlets: 162 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_1/pattern_19 # seqlets: 162 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2