# Parameters
data_name = "wES;5th_Rhmbmr;E9.5;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_159-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_159-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 19:15:20,993 [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	embryo_5th rhombomere(e9.5, wt)
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	191346	132393	8.7151	84805477	9828902	0.1159	7550333	0.0891	30967591	0.3652
rep2	191346	132393	10.1416	73957427	11268311	0.1524	7919144	0.1071	28771660	0.3891

Metric	Value
auPRC	0.6705
Calibrated Recall at 50% FDR	0.189
Number of Positive Examples in Test Data	123796
Number of Negative Examples in Test Data	7947055
Imbalance Ratio in Test Data	0.0153
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 3087 SequenceContrib ScoresHyp_Contrib Scores	Sp1, Sp5, Sp4, Sp3, Wt1, Sp2, Maz, Zbtb17, Klf3, Zfp281, Klf15, Rela, Egr1, Klf6, Klf5, Klf1, Klf4, E2f4, Klf7, Klf8, Klf12, Egr2, Zfx, E2f1, Bcl6, Sall4, E2f7, Ctcfl, E2f3, Ptf1a, Fli1, Srebf2, Mxi1
metacluster_0/pattern_1 # seqlets: 2960 SequenceContrib ScoresHyp_Contrib Scores	Ctcf
metacluster_0/pattern_2 # seqlets: 2356 SequenceContrib ScoresHyp_Contrib Scores	Usf2
metacluster_0/pattern_3 # seqlets: 2308 SequenceContrib ScoresHyp_Contrib Scores	Sox3, Sox17, Sox4, Sox9, Sox2, Sox6, Nanog, Sox12, Lef1, Foxd1, Sry, Tcf7
metacluster_0/pattern_4 # seqlets: 1508 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx1, Rfx4, Rfx6, Rfx7
metacluster_0/pattern_5 # seqlets: 897 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_6 # seqlets: 733 SequenceContrib ScoresHyp_Contrib Scores	Hoxb4, Pdx1, Hoxa2, Hoxb7, Hoxb8, Meis1, Hoxa9, Evx1, Hoxc9, Hoxa1, Cdx4, Pbx2
metacluster_0/pattern_7 # seqlets: 700 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead2, Tead1
metacluster_0/pattern_8 # seqlets: 580 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_9 # seqlets: 533 SequenceContrib ScoresHyp_Contrib Scores	Zic3, Zic2
metacluster_0/pattern_10 # seqlets: 531 SequenceContrib ScoresHyp_Contrib Scores	Nr2f6, Rxra, Rxrb, Nr2c2, Nr2f2, Rarg, Nr1h3, Vdr, Nr1d2, Nr1i3, Rara, Rxrg, Nr1d1, Ppara, Hnf4a, Rora, Rarb, Nr1h4, Pparg, Hnf4g
metacluster_0/pattern_11 # seqlets: 522 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elk1, Elk4, Erg, Elk3, Ets1, Etv5, Etv4, Etv1, Etv6, Fev, Elf1, XP_911724.4, Etv3, Etv2, Elf4, Elf5, Spi1, Elf2, Ehf, Spdef, Spic, Elf3, Spib
metacluster_0/pattern_12 # seqlets: 380 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfec, Tfeb, Arntl, Mitf, Bhlhe40, Srebf1, Tfe3, Mlx, Arnt, Clock, Npas2, Tcfl5, Creb3l2, Bhlhe41, Atf1, Hlf, Dbp
metacluster_0/pattern_13 # seqlets: 331 SequenceContrib ScoresHyp_Contrib Scores	Foxd3, Foxj3, Foxc2, Foxc1, Foxa1, Foxj2, Foxb1, Foxa2, Foxj1, Foxp2, Foxa3, Foxl1, Gm5294, Foxk1, Foxo3, Foxl2, Foxg1, Foxp1, Foxo4, Foxm1, Foxq1, Foxo1
metacluster_0/pattern_14 # seqlets: 309 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_0/pattern_15 # seqlets: 308 SequenceContrib ScoresHyp_Contrib Scores	Ascl1, Ascl2, Olig2, Tcf12, Myog, Bhlha15, Atoh1, Myod1, Lyl1, Tal1, Tcf3, Neurod2, Myf5, Neurod1, Neurog2, Tcf21, Myf6, Tfap4, Snai2, Msc, Tcf4, Tcf7l1, Tgif1, Figla, Bhlhe22, Twist1, Meis2, Nhlh2, Nhlh1, Neurog1, Snai1
metacluster_0/pattern_16 # seqlets: 287 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf7, Atf2, Jdp2, Creb5, Crem, Mafb, Atf3, Fosl2, Nfil3, Fosl1, Tef, Jun
metacluster_0/pattern_17 # seqlets: 271 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Pou5f1, Pou2f1
metacluster_0/pattern_18 # seqlets: 263 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_0/pattern_19 # seqlets: 180 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_20 # seqlets: 92 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_0/pattern_21 # seqlets: 74 SequenceContrib ScoresHyp_Contrib Scores	Lhx3, Alx3, Prrx2, Lhx1, Lhx5, Lhx4, Prop1, Pax7, Arx, Lmx1b, Pou3f4, Lhx8, Uncx, Alx4, Pou3f2, Lhx2, Alx1, Lbx2, Lhx9, Shox2, Pax6, Rhox6, Barhl1, En1, Msx1, Rax, Emx2, Barhl2
metacluster_0/pattern_22 # seqlets: 66 SequenceContrib ScoresHyp_Contrib Scores	Msgn1, Twist2, Olig3, Myb, Smad4
metacluster_0/pattern_23 # seqlets: 58 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_24 # seqlets: 53 SequenceContrib ScoresHyp_Contrib Scores