# Parameters
data_name = "CRBL_GRNL_Precrsr;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_105-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_105-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 19:04:22,869 [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	cerebellar granule cell precursors(wt)
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	234629	167668	11.3312	80617334	15959618	0.198	8640983	0.1072	31619312	0.3923
rep2	234629	167668	14.731	37313774	8010474	0.2148	5266538	0.1412	14971021	0.4014
rep3	234629	167668	14.7562	44515539	10235050	0.23	6036591	0.1357	18132759	0.4075

Metric	Value
auPRC	0.6606
Calibrated Recall at 50% FDR	0.206
Number of Positive Examples in Test Data	191604
Number of Negative Examples in Test Data	7879247
Imbalance Ratio in Test Data	0.0237
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 3898 SequenceContrib ScoresHyp_Contrib Scores	Atoh1, Neurod2, Neurod1, Neurog2, Olig2, Lyl1, Ptf1a, Bhlha15, Ascl1, Tcf21, Myog, Tcf12, Tal1, Ascl2, Bhlhe22, Msc, Myod1, Neurog1, Msgn1, Tcf3, Tfap4, Myf5, Myf6, Tgif1, Twist1, Snai1, Myb, Figla, Tcf4, Snai2, Twist2
metacluster_0/pattern_1 # seqlets: 2383 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_2 # seqlets: 2354 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_3 # seqlets: 2101 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_0/pattern_4 # seqlets: 2042 SequenceContrib ScoresHyp_Contrib Scores	Sp1, Sp3, Sp2, Sp4, Zbtb17, Klf3, Sp5, Klf4, Zfp281, Klf5, E2f4, Egr1, Klf7, Wt1, Klf6, Egr2, Klf8, Klf12, Maz, E2f1, Klf15, Srebf2, Sall4, Klf1, Bcl6, Egr3, Zfp740
metacluster_0/pattern_5 # seqlets: 877 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx1, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_0/pattern_6 # seqlets: 832 SequenceContrib ScoresHyp_Contrib Scores	Sebox, Alx1, Lhx2, Uncx, Prrx2, Pax6, Prrx1, Otp, Esx1, En2, Alx3, Lhx3, Phox2b, Vsx2, Prop1, Pou1f1, Lhx4, Arx, Shox2, Lhx8, Vsx1, Emx2, Phox2a, Noto, Rhox6, Lhx9, Alx4, Pou2f2, En1, Gsx2, Rax, Gbx1, Hoxd3, Lmx1b, Lbx2, Msx1, Hoxa2, Pou2f1, Evx1, Isx, Lhx5, Pou3f1, Gbx2, Lhx1, Vax2, Vax1, Hoxd1, Msx3, Nobox, Hoxa1, Evx2, Hoxc6, Lhx6, Hoxc5, Msx2, Pdx1, Nkx1-2, Lmx1a, Pou3f2, Hoxa4, Hoxa3, Mnx1, Nkx1-1, Dbx1, Pou2f3, Hoxb3, Hoxa5, Tlx2, Pax7, Pou3f4, Pax4, Meox2, Hlx, Hoxb4, Pou6f1, Meox1, Hoxb5, Arid3b, Hoxc9, Pou4f3, Hoxc4, Nkx6-3, Dlx1, Dlx3, Dbx2, Nkx6-1, Dlx4, Dlx5, Dlx2, Hoxa7, Barhl1, Bsx, Barx2, Isl2, Hoxa6, Isl1, Sp7, Hoxc10, Barx1, Hnf1a, Barhl2, Hnf1b, Duxbl1
metacluster_0/pattern_7 # seqlets: 680 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_8 # seqlets: 594 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elk1, Ets1, Fli1, Elf1, Elk4, Erg, Elk3, Etv6, Etv5, Etv1, Etv3, Etv4, XP_911724.4, Etv2, Elf4, Spi1, Elf2, Ehf, Irf8, Elf5, Elf3, Irf2, Spib, Prdm1, Spdef, Irf1, Fev, Irf4, Spic, Irf3, Irf9, Irf5, Irf7
metacluster_0/pattern_9 # seqlets: 560 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Jdp2, Creb5, Creb1, Atf1, Crem, Nfil3, Dbp, Atf3, Cebpb, Hlf, Cebpa, Jun, Srebf1, Mlx, Tef, Tfec, Fosl2, Ddit3, Fosl1, Mafb, Atf4
metacluster_0/pattern_10 # seqlets: 505 SequenceContrib ScoresHyp_Contrib Scores	Pax5
metacluster_0/pattern_11 # seqlets: 382 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_12 # seqlets: 233 SequenceContrib ScoresHyp_Contrib Scores	Fos, Junb, Jund, Batf, Fosb, Bach2, Bach1, Nfe2l2, Nfe2, Mafa, Mafk
metacluster_0/pattern_13 # seqlets: 198 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Usf2, Tfeb, Arntl, Mitf, Bhlhe40, Tfe3, Clock, Arnt, Npas2, Creb3l2, Tcfl5, Bhlhe41, Mlxip, Xbp1, Hes1, Mycn, Max, Myc
metacluster_0/pattern_14 # seqlets: 177 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_0/pattern_15 # seqlets: 70 SequenceContrib ScoresHyp_Contrib Scores	Sox9, Sox4, Sox3, Sox17, Tcf7, Sox6, Sox2
metacluster_0/pattern_16 # seqlets: 58 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_17 # seqlets: 47 SequenceContrib ScoresHyp_Contrib Scores	Mef2c, Mef2d, Mef2a, Pou5f1
metacluster_0/pattern_18 # seqlets: 32 SequenceContrib ScoresHyp_Contrib Scores	Foxj3, Foxj1