# Parameters
data_name = "ES;E14;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_99-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_99-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 19:02:11,765 [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	E14 ES cells
Cell Group	ES cells and embryonic 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	194614	118824	12.5591	17916047	2615659	0.1462	1978782	0.1106	6804941	0.3802
rep2	194614	118824	12.269	14528181	1573807	0.1085	1558330	0.1074	5490298	0.3784
rep3	194614	118824	11.4434	13200179	1177504	0.0893	1411794	0.1071	5002151	0.3795
rep4	194614	118824	9.7165	11893788	619657	0.0522	1099351	0.0926	4343737	0.3658

Metric	Value
auPRC	0.5846
Calibrated Recall at 50% FDR	0.233
Number of Positive Examples in Test Data	126558
Number of Negative Examples in Test Data	7944293
Imbalance Ratio in Test Data	0.0157
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 2636 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_1 # seqlets: 1996 SequenceContrib ScoresHyp_Contrib Scores	Sp5, Sp1, Sp2, Wt1, Sp3, Maz, Zbtb17, Sp4, Klf15, Klf3, Klf5, Egr1, Zfp281, Klf4, Rela, Klf7, Klf6, E2f4, Klf8, Klf12, Zfx, E2f1, Egr2, Fli1, Sall4, Klf1, Usf2, E2f3, Egr3, E2f7, Srebf2, Mxi1
metacluster_0/pattern_2 # seqlets: 1611 SequenceContrib ScoresHyp_Contrib Scores	Zfp740, Bcl6
metacluster_0/pattern_3 # seqlets: 1421 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_4 # seqlets: 1266 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_5 # seqlets: 1239 SequenceContrib ScoresHyp_Contrib Scores	Pou5f1, Nanog, Sox2, Pou2f2, Lef1
metacluster_0/pattern_6 # seqlets: 1125 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_7 # seqlets: 995 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead2, Tead1
metacluster_0/pattern_8 # seqlets: 746 SequenceContrib ScoresHyp_Contrib Scores	Elk4, Gabpa, Elk1, Erg, Ets1, Elk3, Etv5, Fev, Elf1, Etv4, Etv1, Etv6, Elf2, Etv3, XP_911724.4, Ehf, Etv2, Elf5, Spi1, Elf4, Elf3, Spdef, Spic
metacluster_0/pattern_9 # seqlets: 654 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_10 # seqlets: 637 SequenceContrib ScoresHyp_Contrib Scores	Sox17, Sox3, Sox4, Sox6, Sox9, Sox12, Sox13
metacluster_0/pattern_11 # seqlets: 585 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_12 # seqlets: 482 SequenceContrib ScoresHyp_Contrib Scores	Fosb, Atf3, Junb, Fosl1, Fosl2, Fos, Jun, Jund, Batf, Jdp2, Bach2, Nfe2, Nfe2l2, Bach1, Mafk, Mafa, Mafb, Mafg, Maf, Maff, Nfatc1
metacluster_0/pattern_13 # seqlets: 427 SequenceContrib ScoresHyp_Contrib Scores	Yy1, Taf1, Zfp42, Rfx1
metacluster_0/pattern_14 # seqlets: 389 SequenceContrib ScoresHyp_Contrib Scores	Zic2, Zic3
metacluster_0/pattern_15 # seqlets: 311 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_0/pattern_16 # seqlets: 278 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_17 # seqlets: 270 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_18 # seqlets: 222 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfe3, Tfeb, Arntl, Tfec, Mitf, Clock, Srebf1, Bhlhe40, Arnt, Mlx, Npas2, Rxrg, Tcfl5, Rxrb, Mycn, Myc, Max, Creb3l2, Atf1, Bhlhe41, Atf7, Creb1, Nr2f1, Atf2, Hlf
metacluster_0/pattern_19 # seqlets: 210 SequenceContrib ScoresHyp_Contrib Scores	Lhx3, Lhx2, Pax6, Prrx2, Pou1f1, Vsx2, Lhx9, Mnx1, Esx1, Shox2, Gbx1, Rhox6, Gbx2, Sebox, Lbx2, Arx, Lhx8, Nobox, Prrx1, Msx3, Alx1, Uncx, Vsx1, Otp, Lhx1, Hoxd3, Hand1, Lhx5, Msx2, Alx4, Hoxa3, Alx3, Lhx4, Emx2, En1, Hoxa1, Prop1, Nkx1-1, Rax, Lhx6, Pou3f4, Lmx1b, Evx1, Hoxd1, En2, Pax4, Gsx2, Phox2b, Hmx2
metacluster_0/pattern_20 # seqlets: 185 SequenceContrib ScoresHyp_Contrib Scores	Crem, Creb5, Nfil3, Nr1h4
metacluster_0/pattern_21 # seqlets: 182 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_22 # seqlets: 128 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_23 # seqlets: 119 SequenceContrib ScoresHyp_Contrib Scores	Grhl2
metacluster_0/pattern_24 # seqlets: 97 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_0/pattern_25 # seqlets: 89 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_26 # seqlets: 72 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_0/pattern_27 # seqlets: 57 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_28 # seqlets: 46 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_29 # seqlets: 36 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_30 # seqlets: 33 SequenceContrib ScoresHyp_Contrib Scores