# Parameters
data_name = "FBRBLST;8wks;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_220-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_220-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 19:30:08,559 [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 (adult-8wks)
Cell Group	Other 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	167148	109230	14.9712	23906962	7742366	0.3241	3229253	0.1352	12067123	0.5052
rep2	167148	109230	11.9516	20450877	5645287	0.2763	1916060	0.0938	9797634	0.4795

Metric	Value
auPRC	0.5443
Calibrated Recall at 50% FDR	0.258
Number of Positive Examples in Test Data	154561
Number of Negative Examples in Test Data	7916290
Imbalance Ratio in Test Data	0.0192
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 3065 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 2729 SequenceContrib ScoresHyp_Contrib Scores	Junb, Fosl1, Fosb, Fos, Jund, Atf3, Fosl2, Jun, Jdp2, Batf, Bach2, Nfe2, Nfe2l2, Bach1, Mafa
metacluster_1/pattern_2 # seqlets: 2297 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Klf3, Sp2, Sp3, Sp1, Klf6, Klf7, Klf4, E2f4, Klf1, Klf8, Klf12, Egr1, Zbtb17, Egr2, Klf5, E2f1, Sp5, Zfp281
metacluster_1/pattern_3 # seqlets: 1994 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Cebpd, Dbp, Nfil3, Cebpg, Atf4, Ddit3, Hlf, Cebpe, Tef, Pou3f3
metacluster_1/pattern_4 # seqlets: 1418 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Elk1, Gabpa, Fli1, Elk4, Etv2, Etv4, Elk3, Etv5, Etv6, Spi1, Fev, Etv1, XP_911724.4, Etv3, Elf2, Elf1, Elf4, Elf5, Spib, Ehf, Spdef, Elf3, Spic, Irf8, Irf4, Zscan10, Stat3
metacluster_1/pattern_5 # seqlets: 1281 SequenceContrib ScoresHyp_Contrib Scores	Nfic
metacluster_1/pattern_6 # seqlets: 1166 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia
metacluster_1/pattern_7 # seqlets: 945 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_8 # seqlets: 920 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_9 # seqlets: 905 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_10 # seqlets: 697 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Creb1, Creb5, Atf1, Crem, Mafb, Creb3l2, Srebf1, Tfec, Usf1, Tfe3, Mlx, Rxrb
metacluster_1/pattern_11 # seqlets: 646 SequenceContrib ScoresHyp_Contrib Scores	Sox9, Sox10, Sox2, Sox3, Sox4, Sox6, Sox17
metacluster_1/pattern_12 # seqlets: 612 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead1
metacluster_1/pattern_13 # seqlets: 594 SequenceContrib ScoresHyp_Contrib Scores	Tfeb, Usf2, Mitf, Arntl, Bhlhe40, Clock, Arnt, Npas2, Srebf2, Tcfl5, Bhlhe41, Mycn, Max, Xbp1, Mlxip, Arnt2
metacluster_1/pattern_14 # seqlets: 333 SequenceContrib ScoresHyp_Contrib Scores	Yy1, Taf1, Zfx, Zfp42, Rfx1, Wt1, Maz
metacluster_1/pattern_15 # seqlets: 327 SequenceContrib ScoresHyp_Contrib Scores	Twist1, Bhlha15, Tcf21, Lhx3, Lhx5, Lhx1, Msc, Olig2
metacluster_1/pattern_16 # seqlets: 295 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_17 # seqlets: 288 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_18 # seqlets: 255 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx4, Rfx6, Rfx7
metacluster_1/pattern_19 # seqlets: 238 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_1/pattern_20 # seqlets: 236 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Stat1, Irf2, Irf7, Stat2, Prdm1, Irf9, Irf3, Batf3, Irf5
metacluster_1/pattern_21 # seqlets: 146 SequenceContrib ScoresHyp_Contrib Scores	Nfatc2, Nfatc1
metacluster_1/pattern_22 # seqlets: 121 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_23 # seqlets: 100 SequenceContrib ScoresHyp_Contrib Scores	Rela, Nfkb1, Nfkb2, Relb, Rel
metacluster_1/pattern_24 # seqlets: 93 SequenceContrib ScoresHyp_Contrib Scores