# Parameters
data_name = "NIH3T3_FBROBLST;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_219-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_219-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 19:29:52,976 [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	Fibroblast/NIH3T3
Cell Group	Cancer or Immortalized cells
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	181864	127493	9.0817	137526751	29397205	0.2138	13986315	0.1017	56959888	0.4142
rep2	181864	127493	16.2121	20385797	4614921	0.2266	2287952	0.1123	9120750	0.4478

Metric	Value
auPRC	0.5662
Calibrated Recall at 50% FDR	0.236
Number of Positive Examples in Test Data	127320
Number of Negative Examples in Test Data	7943531
Imbalance Ratio in Test Data	0.0158
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 5828 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 3423 SequenceContrib ScoresHyp_Contrib Scores	Fos, Fosl1, Jund, Fosl2, Fosb, Junb, Atf3, Batf, Jdp2, Jun, Mafa, Bach2, Mafk, Nfe2, Nfe2l2, Mafb, Bach1, Maf, Mafg
metacluster_1/pattern_2 # seqlets: 1673 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Klf3, Sp3, Sp1, Klf6, E2f4, Klf7, Klf4, Klf8, Klf12, Klf1, Egr1, Egr2, Zbtb17, Klf5, Sp5, E2f1, Zfp281, Egr3, Zfp740, Zfx
metacluster_1/pattern_3 # seqlets: 1536 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Cebpd, Nfil3, Cebpg, Dbp, Atf4, Ddit3, Hlf, Cebpe, Tef
metacluster_1/pattern_4 # seqlets: 1391 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib
metacluster_1/pattern_5 # seqlets: 1099 SequenceContrib ScoresHyp_Contrib Scores	Nfic
metacluster_1/pattern_6 # seqlets: 921 SequenceContrib ScoresHyp_Contrib Scores	Tead4
metacluster_1/pattern_7 # seqlets: 859 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Creb1, Creb5, Atf1, Crem, Creb3l2, Srebf1, Tfec, Rxrb, Tfe3, Usf1, Mlx
metacluster_1/pattern_8 # seqlets: 802 SequenceContrib ScoresHyp_Contrib Scores	Twist1, Tcf21, Bhlha15, Lhx3, Lhx5, Lhx1, Msc, Lmx1b, Neurog1, Olig2, Alx3, Arid3a, Bhlhe22, Prop1, Lhx4, Atoh1, Prrx2, Tfap4
metacluster_1/pattern_9 # seqlets: 792 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_10 # seqlets: 775 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Foxi1, Nfya, Pbx3
metacluster_1/pattern_11 # seqlets: 624 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Fli1, Ets1, Elk1, Elk4, Elf1, Erg, Elk3, Etv2, Etv4, Etv1, Etv5, Fev, Etv3, Etv6, XP_911724.4, Ehf, Elf5, Elf4, Elf3, Elf2, Spi1, Spdef, Spib, Irf2
metacluster_1/pattern_12 # seqlets: 387 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_13 # seqlets: 383 SequenceContrib ScoresHyp_Contrib Scores	Yy1, Taf1, Zfp42, Rfx1, Wt1
metacluster_1/pattern_14 # seqlets: 345 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_1/pattern_15 # seqlets: 282 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Cbfb, Runx3
metacluster_1/pattern_16 # seqlets: 235 SequenceContrib ScoresHyp_Contrib Scores	Usf2, Tfeb, Arntl, Mitf, Bhlhe40, Clock, Arnt, Npas2, Srebf2, Tcfl5, Bhlhe41, Xbp1, Mycn, Max, Mlxip, Hes1
metacluster_1/pattern_17 # seqlets: 214 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx6, Rfx7
metacluster_1/pattern_18 # seqlets: 201 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_19 # seqlets: 148 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_20 # seqlets: 147 SequenceContrib ScoresHyp_Contrib Scores	Hoxa9, Meis1, Evx1, Hoxc9, Cdx4, Pdx1, Hoxb4, Hoxa10, Hoxb7, Hoxa2, Cdx1, Pbx2, Hoxb8
metacluster_1/pattern_21 # seqlets: 58 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_22 # seqlets: 54 SequenceContrib ScoresHyp_Contrib Scores