# Parameters
data_name = "Md_BRN;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_252-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_252-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 19:36:44,754 [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	midbrain(P0)
Cell Group	Neural Cells and Tissues
Experiment Name	DHS
Experiment Group	ENCODE

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	230478	141069	10.1658	128539086	22178983	0.1726	NA	NA	53936397	0.4197
rep2	230478	141069	9.0222	79199726	7197922	0.0909	5609940	0.0708	26042712	0.3289

Metric	Value
auPRC	0.6323
Calibrated Recall at 50% FDR	0.208
Number of Positive Examples in Test Data	125309
Number of Negative Examples in Test Data	7945542
Imbalance Ratio in Test Data	0.0155
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 3137 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 2289 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib
metacluster_1/pattern_2 # seqlets: 1845 SequenceContrib ScoresHyp_Contrib Scores	Sp3, Sp2, Sp1, Sp4, Klf3, Klf6, Wt1, Zbtb17, Klf1, Sp5, E2f4, Klf4, Egr1, Klf5, Maz, Klf7, Zfp281, Klf8, Klf15, Egr2, Klf12, Zfx, E2f1, E2f7, Ptf1a, Fli1, Srebf2
metacluster_1/pattern_3 # seqlets: 1759 SequenceContrib ScoresHyp_Contrib Scores	Pax6, Sebox, Hoxc6, Lhx4, Lhx2, Hoxa1, Lhx9, Lhx3, Dbx1, Uncx, Otp, Prrx2, Pou1f1, Alx1, Esx1, Noto, Arid3b, Alx3, Hoxc9, Vsx2, Tlx2, Arx, Hoxc5, Lmx1b, Prop1, Lhx5, Gsx2, Hoxd3, Lbx2, Hoxa2, Hoxa4, Pou2f1, Alx4, Meox1, Shox2, Vsx1, Pou4f3, Vax1, Lmx1a, Msx1, Lhx1, Vax2, Nkx6-1, Hoxa5, Hoxa3, Prrx1, Rhox6, Hoxc10, Nobox, Hoxb4, Hoxa6, Nkx6-3, Lhx6, Meox2, Phox2b, Hoxa7, Hoxc4, Hoxb5, Pou2f2, Evx1, Hoxb3, Phox2a, Emx2, Pou3f1, Hlx, Hoxb7, Lhx8, Pdx1, Pou3f2, Isx, Msx3, Gbx1, En2, Hoxc8, Dlx2, Rax, Pou3f4, Hnf1a, Mnx1, Gbx2, Dlx4, Barx2, Nkx1-2, Bsx, Pax4, Twist1, Pou2f3, Cdx1, Hoxd9, En1, Pax7, Hoxa10, Hoxd8, Nkx1-1, Pou6f1, Hoxb8, Hnf1b, Hoxa9, Dlx5, Dlx1, Isl2, Hoxd10, Arid3a, Dlx3, Cdx2, Evx2, Nanog, Hoxd1, Hoxb9, Dbx2, Sp7, Hoxa11, Barx1, Hmx1, Barhl1, Hoxd11, Msx2, Isl1, Hoxc11
metacluster_1/pattern_4 # seqlets: 1430 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx1, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_5 # seqlets: 1416 SequenceContrib ScoresHyp_Contrib Scores	Neurod2, Neurod1, Neurog2, Atoh1, Olig2, Ascl1, Ascl2, Msgn1, Msc, Bhlhe22, Lyl1, Bhlha15, Tal1, Tcf21, Neurog1, Myog, Tcf12, Twist2
metacluster_1/pattern_6 # seqlets: 1204 SequenceContrib ScoresHyp_Contrib Scores	Usf2, Mxi1, Nrf1
metacluster_1/pattern_7 # seqlets: 1057 SequenceContrib ScoresHyp_Contrib Scores	Sox4, Sox3, Sox9, Sox2, Sox17, Sox6, Lef1, Tcf7, Foxd1
metacluster_1/pattern_8 # seqlets: 986 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Pbx3, Foxi1
metacluster_1/pattern_9 # seqlets: 858 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_10 # seqlets: 645 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elk1, Elk4, Ets1, Erg, Elk3, Etv5, Elf1, Fev, Etv4, Etv1, Etv6, Etv3, XP_911724.4, Ehf, Elf5, Etv2, Elf2, Elf4, Spi1, Spdef, Elf3
metacluster_1/pattern_11 # seqlets: 496 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_12 # seqlets: 446 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Jdp2, Creb5, Creb1, Atf1, Atf3, Crem, Fosl2, Nfil3, Hlf, Fosl1, Dbp, Jun, Mafb, Tef, Cebpb, Cebpa, Creb3l2, Tfe3, Tfec, Srebf1, Cebpg, Atf4, Usf1, Mlx, Rxrb
metacluster_1/pattern_13 # seqlets: 336 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_1/pattern_14 # seqlets: 320 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_15 # seqlets: 294 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_1/pattern_16 # seqlets: 236 SequenceContrib ScoresHyp_Contrib Scores	Tfeb, Mitf, Bhlhe40, Arntl, Arnt, Clock, Npas2, Tcfl5, Bhlhe41, Mlxip, Xbp1
metacluster_1/pattern_17 # seqlets: 150 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_18 # seqlets: 128 SequenceContrib ScoresHyp_Contrib Scores	Ebf1, Prdm16, Sp110
metacluster_1/pattern_19 # seqlets: 57 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_20 # seqlets: 52 SequenceContrib ScoresHyp_Contrib Scores