# Parameters
data_name = "Melanotrope;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_182-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_182-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 19:21:41,724 [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	FACS-purified melanotrope cells
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	258113	203957	7.7178	80478162	16118072	0.2003	8471919	0.1053	30573594	0.38
rep2	258113	203957	6.4851	100166213	12333774	0.1232	7545732	0.0753	34241602	0.3419

Metric	Value
auPRC	0.5756
Calibrated Recall at 50% FDR	0.231
Number of Positive Examples in Test Data	167096
Number of Negative Examples in Test Data	7903755
Imbalance Ratio in Test Data	0.0207
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 2410 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_1 # seqlets: 2238 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp1, Sp3, Sp2, Klf3, E2f4, Zbtb17, Egr1, Klf7, Klf6, E2f1, Klf8, Klf12, Sp5, Egr2, Klf15, Wt1, Zfp281, Klf1, Klf4, Klf5, Maz, Egr3, E2f7, Zfp740
metacluster_0/pattern_2 # seqlets: 1671 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_3 # seqlets: 1542 SequenceContrib ScoresHyp_Contrib Scores	Fli1, Elk4, Gabpa, Elf1, Elk1, Erg, Elk3, Ets1, Elf5, Etv5, Fev, Etv1, Etv4, Elf4, Elf2, Etv6, Etv3, Ehf, XP_911724.4, Etv2, Elf3, Spdef, Spi1
metacluster_0/pattern_4 # seqlets: 1502 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_0/pattern_5 # seqlets: 1199 SequenceContrib ScoresHyp_Contrib Scores	Gbx1, Phox2b, Vsx2, Phox2a, Crx, Prrx1, Barhl1, Otp, Lhx2, Isx, Gsc, Lhx8, Pou2f1, Rax, Gbx2, Esx1
metacluster_0/pattern_6 # seqlets: 1086 SequenceContrib ScoresHyp_Contrib Scores	Fosl1, Junb, Fosb, Atf3, Fosl2, Jund, Fos, Jun, Jdp2, Batf, Bach2, Nfe2l2, Bach1, Nfe2
metacluster_0/pattern_7 # seqlets: 965 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Atf7, Creb5, Crem, Atf1, Nfil3, Tef, Cebpb, Dbp, Mafb, Gmeb2, Cebpa, Hlf, Gmeb1, Cebpg, Cebpd, Ddit3, Atf4, Esr2, Rora, Xbp1, Rxrb
metacluster_0/pattern_8 # seqlets: 965 SequenceContrib ScoresHyp_Contrib Scores	Ascl1, Myf6, Ascl2, Myod1, Myog, Snai2, Tcf12, Tcf3, Ptf1a, Tal1, Bhlha15, Myf5, Tcf4, Atoh1, Nhlh1, Tcf7l1, Nhlh2, Neurod2, Tgif1
metacluster_0/pattern_9 # seqlets: 942 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx1, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_0/pattern_10 # seqlets: 595 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Stat2, Stat1, Prdm1, Irf8, Irf7, Irf4, Irf9, Irf5, Batf3
metacluster_0/pattern_11 # seqlets: 562 SequenceContrib ScoresHyp_Contrib Scores	Arntl, Tfeb, Tfe3, Bhlhe40, Clock, Usf1, Pax2, Npas2, Usf2, Srebf1, Tfec, Mitf, Bhlhe41, Mlx, Arnt
metacluster_0/pattern_12 # seqlets: 440 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfya, Nfyc, Pbx3, Foxi1
metacluster_0/pattern_13 # seqlets: 408 SequenceContrib ScoresHyp_Contrib Scores	Nr4a2, Rorc, Nr4a1, Esrrg, Nr5a2, Rara, Rarg, Nr2f6, Rarb
metacluster_0/pattern_14 # seqlets: 405 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfx, Zfp42, Mxi1
metacluster_0/pattern_15 # seqlets: 399 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_16 # seqlets: 301 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_0/pattern_17 # seqlets: 282 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_18 # seqlets: 202 SequenceContrib ScoresHyp_Contrib Scores	Stat4
metacluster_0/pattern_19 # seqlets: 157 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_0/pattern_20 # seqlets: 158 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_0/pattern_21 # seqlets: 102 SequenceContrib ScoresHyp_Contrib Scores	Nfatc2, Nfatc3
metacluster_0/pattern_22 # seqlets: 44 SequenceContrib ScoresHyp_Contrib Scores