# Parameters
data_name = "iVIP_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_176-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_176-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 19:20:01,799 [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	vasoactive intestinal peptide-positive (VIP) 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	242514	180616	12.774	64095408	16560106	0.2584	8197158	0.1279	26160763	0.4083
rep2	242514	180616	13.9045	55760003	14929829	0.2678	7788042	0.1397	22925761	0.4113

Metric	Value
auPRC	0.6056
Calibrated Recall at 50% FDR	0.257
Number of Positive Examples in Test Data	222584
Number of Negative Examples in Test Data	7848267
Imbalance Ratio in Test Data	0.0276
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 2552 SequenceContrib ScoresHyp_Contrib Scores	Tcf3, Ascl2, Myf6, Tcf7l1, Tal1, Nhlh2, Twist1, Tcf4, Tcf12, Bhlha15, Atoh1, Ptf1a, Myog, Ascl1
metacluster_1/pattern_1 # seqlets: 2357 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_1/pattern_2 # seqlets: 2111 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_3 # seqlets: 2008 SequenceContrib ScoresHyp_Contrib Scores	Sp3, Sp1, Sp4, Sp2, Klf3, E2f4, Zbtb17, Egr1, Klf7, Klf8, Klf6, Klf12, E2f1, Egr2, Sp5, Klf1, Klf4, Klf15, Wt1, Zfp281, Klf5, Maz, Egr3, E2f7, Zfp740, Sall4, Zbtb1
metacluster_1/pattern_4 # seqlets: 1364 SequenceContrib ScoresHyp_Contrib Scores	Mef2a, Mef2c, Mef2d
metacluster_1/pattern_5 # seqlets: 1319 SequenceContrib ScoresHyp_Contrib Scores	Pou2f1, Hoxc5, Pou3f1, Pou3f2, Phf21a
metacluster_1/pattern_6 # seqlets: 1311 SequenceContrib ScoresHyp_Contrib Scores	Hoxc6, Hoxc9, Dlx2, Dlx5, Hoxa2, Sp7, Meox2, Dlx3, Gsx2, Hoxd3, Dlx4, Meox1, Nkx6-1, Dlx1, Hoxa4, Hoxa6, Nkx6-3, Hoxc10, Hoxa3, Evx1, Hoxa1, Hoxa7, Hoxa5, Hoxb4, Vax1, Hoxb7, Pdx1, Mnx1, En2, Hoxc4, Otp, Esx1, Vax2, Hoxb5, Hoxc8, Lhx2, Alx3, Hoxb3, Barx2, Prrx2, Dbx1, Lhx6, Phox2b, Emx2, Hoxd9, Nobox, Phox2a, Prrx1, En1, Lhx4, Prop1, Lhx9, Gbx1, Alx1, Cdx1, Lhx3, Hoxd8, Tlx2, Hoxb8, Uncx, Dbx2, Lmx1b, Gbx2, Msx3, Msx1, Hoxa10, Lhx5, Msx2, Hoxd10, Cdx2, Nkx1-2, Hoxa9, Isx, Hmx1, Pax6, Nkx1-1, Barhl1, Lhx1
metacluster_1/pattern_7 # seqlets: 1299 SequenceContrib ScoresHyp_Contrib Scores	Zfx, Usf2, Mxi1, Rfx1, Myc
metacluster_1/pattern_8 # seqlets: 1023 SequenceContrib ScoresHyp_Contrib Scores	Jund, Fosb, Junb, Fos, Fosl1, Fosl2, Jdp2, Atf3, Jun, Batf, Bach2, Nfe2, Nfe2l2, Bach1, Mafa
metacluster_1/pattern_9 # seqlets: 830 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_10 # seqlets: 653 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Pou5f1, Nanog, Sox2, Pax7
metacluster_1/pattern_11 # seqlets: 638 SequenceContrib ScoresHyp_Contrib Scores	Pou3f3, Pou1f1
metacluster_1/pattern_12 # seqlets: 631 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_13 # seqlets: 582 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elf1, Elk1, Fli1, Elk4, Elk3, Erg, Ets1, Elf5, Etv5, Fev, Etv1, Elf2, Etv4, Elf4, Etv6, Ehf, XP_911724.4, Etv3, Spi1, Elf3, Etv2, Spdef
metacluster_1/pattern_14 # seqlets: 444 SequenceContrib ScoresHyp_Contrib Scores	Nfyc, Nfyb, Nfya, Foxi1, Pbx3
metacluster_1/pattern_15 # seqlets: 427 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Creb1, Creb5, Atf1, Crem, Mafb, Nfil3, Hlf, Tef, Dbp, Creb3l2, Cebpb, Cebpa, Rxrb, Cebpg, Atf4, Srebf1, Usf1, Gmeb2, Tfe3, Tfec
metacluster_1/pattern_16 # seqlets: 291 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_1/pattern_17 # seqlets: 273 SequenceContrib ScoresHyp_Contrib Scores	Tfeb, Arntl, Mitf, Bhlhe40, Clock, Mlx, Arnt, Srebf2, Npas2, Tcfl5, Mycn, Bhlhe41, Mlxip, Xbp1, Max
metacluster_1/pattern_18 # seqlets: 258 SequenceContrib ScoresHyp_Contrib Scores	Sox4, Sox3, Sox6, Sox17, Sox5, Sox12, Sox9, Sox14, Tcf7, Sry, Sox7, Sox8, Sox11, Sox18, Tcf7l2, Lef1, Sox21, Cux2, Sox30, Sox15, Sox13, Sox10
metacluster_1/pattern_19 # seqlets: 223 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_20 # seqlets: 219 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_21 # seqlets: 55 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_22 # seqlets: 55 SequenceContrib ScoresHyp_Contrib Scores	Foxj3
metacluster_1/pattern_23 # seqlets: 48 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_24 # seqlets: 48 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_25 # seqlets: 41 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_26 # seqlets: 34 SequenceContrib ScoresHyp_Contrib Scores