# Parameters
data_name = "Muller;P12;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_244-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_244-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 19:35:03,217 [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	Muller cell(P12)
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	277130	206968	9.2293	157227576	NA	NA	NA	NA	NA	NA
rep2	277130	206968	12.0745	109702032	31529181	0.2875	10237389	0.0933	50715528	0.4624
rep3	277130	206968	8.4813	172661149	NA	NA	NA	NA	NA	NA

Metric	Value
auPRC	0.6502
Calibrated Recall at 50% FDR	0.214
Number of Positive Examples in Test Data	252010
Number of Negative Examples in Test Data	7818841
Imbalance Ratio in Test Data	0.0312
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 2978 SequenceContrib ScoresHyp_Contrib Scores	Junb, Fos, Fosl1, Fosb, Jund, Atf3, Fosl2, Jdp2, Jun, Batf, Bach2, Nfe2, Nfe2l2, Bach1
metacluster_1/pattern_1 # seqlets: 2865 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead2, Tead1
metacluster_1/pattern_2 # seqlets: 2197 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_3 # seqlets: 1751 SequenceContrib ScoresHyp_Contrib Scores	Sp3, Sp1, Sp4, Sp2, Klf3, E2f4, Egr1, Zbtb17, Klf7, Klf12, Klf8, Klf6, Egr2, E2f1, Klf4, Sp5, Klf1, Klf5, Zfp281, Klf15, Wt1, Maz, Egr3, Zfp740, E2f7, Sall4, Zbtb1
metacluster_1/pattern_4 # seqlets: 1278 SequenceContrib ScoresHyp_Contrib Scores	Nfic
metacluster_1/pattern_5 # seqlets: 1265 SequenceContrib ScoresHyp_Contrib Scores	Lhx2, Lhx9, Prrx2, Emx2, Lhx8, Vsx2, Shox2, En2, Lbx2, Arx, Rax, Alx1, Rhox6, Pou1f1, Uncx, Vsx1, Pax6, Gbx1, Lhx3, Hoxa2, Alx4, Nkx1-2, Gbx2, Evx1, Vax2, Gsx2, Lhx4, Noto, Msx3, Alx3, Nkx1-1, Lhx6, Vax1, Sebox, Hoxa1, Prop1, Hoxd3, Pdx1, En1, Prrx1, Nobox, Otp, Pax4, Phox2b, Esx1, Phox2a, Hoxb3, Hoxa3, Msx1, Pax7, Mnx1, Hoxc5, Pou2f2, Pou2f3, Lmx1b, Hoxa5, Evx2, Isx, Hoxd1, Pou3f1, Msx2, Hoxb5, Pou3f2, Dlx5, Lmx1a, Pou2f1, Barhl1, Meox1, Hlx, Bsx, Hoxb4, Barhl2, Lhx1, Lhx5, Pou6f1, Isl2, Isl1, Nkx6-3, Hoxc6, Barx1, Dlx3, Nkx6-1, Meox2, Dbx2, Pou4f3, Dbx1, Pou3f4, Hoxa4, Tlx2, Dlx2, Duxbl1, Barx2, Dlx4, Hoxc10, Hoxa7, Hoxb6, Hnf1b, Hoxa6, Arid3b, Hoxb7, Dlx1, Hnf1a, Hmbox1, Hoxc4, Twist1
metacluster_1/pattern_6 # seqlets: 1215 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib
metacluster_1/pattern_7 # seqlets: 1129 SequenceContrib ScoresHyp_Contrib Scores	Sox9, Sox2, Sox3, Sox17, Sox10, Sox6, Sox4, Sox12
metacluster_1/pattern_8 # seqlets: 904 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Cebpd, Nfil3, Dbp, Hlf, Ddit3, Atf4, Cebpg, Cebpe, Tef, Pou3f3
metacluster_1/pattern_9 # seqlets: 829 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Gabpa, Etv6, Etv4, Elk1, Fli1, Spi1, Etv2, Etv3, XP_911724.4, Elk4, Spib, Etv5, Etv1, Elk3, Elf4, Elf2, Elf1, Spic, Irf4, Irf8, Elf5, Ehf, Elf3, Fev, Spdef, Zscan10
metacluster_1/pattern_10 # seqlets: 807 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_11 # seqlets: 713 SequenceContrib ScoresHyp_Contrib Scores	Atf2, Atf7, Creb5, Creb1, Atf1, Crem, Srebf1, Mlx, Tfec, Rxrb
metacluster_1/pattern_12 # seqlets: 571 SequenceContrib ScoresHyp_Contrib Scores	Nrf1, Usf2, Zfx, Mxi1
metacluster_1/pattern_13 # seqlets: 536 SequenceContrib ScoresHyp_Contrib Scores	Rorc, Pparg, Rora, Esr2
metacluster_1/pattern_14 # seqlets: 495 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx1, Rfx4, Rfx6, Rfx7
metacluster_1/pattern_15 # seqlets: 469 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Pbx3, Foxi1
metacluster_1/pattern_16 # seqlets: 222 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Prdm1, Irf7, Stat1, Stat2, Irf3, Irf9, Batf3
metacluster_1/pattern_17 # seqlets: 199 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Arntl, Tfeb, Mitf, Tfe3, Bhlhe40, Clock, Arnt, Npas2, Creb3l2, Srebf2, Tcfl5, Bhlhe41, Xbp1, Mycn, Max, Hes1, Mlxip
metacluster_1/pattern_18 # seqlets: 128 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_19 # seqlets: 120 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_20 # seqlets: 110 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_1/pattern_21 # seqlets: 70 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_22 # seqlets: 50 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_23 # seqlets: 48 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_24 # seqlets: 38 SequenceContrib ScoresHyp_Contrib Scores	Srf
metacluster_1/pattern_25 # seqlets: 42 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4