# Parameters
data_name = "3T3-L1;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_278-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_278-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 19:43:03,755 [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	3T3-L1
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	218252	172233	12.4829	27634745	6283522	0.2275	3319961	0.1202	12010843	0.4349
rep2	218252	172233	4.9727	231392363	44355100	0.1917	16988140	0.0734	91212806	0.3942

Metric	Value
auPRC	0.575
Calibrated Recall at 50% FDR	0.204
Number of Positive Examples in Test Data	152449
Number of Negative Examples in Test Data	7918402
Imbalance Ratio in Test Data	0.0189
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 5533 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 4504 SequenceContrib ScoresHyp_Contrib Scores	Fos, Fosl1, Fosl2, Jund, Fosb, Junb, Atf3, Batf, Jdp2, Jun, Bach2, Mafa, Mafk, Nfe2l2, Nfe2, Mafb, Bach1, Maf, Mafg, Maff
metacluster_1/pattern_2 # seqlets: 2482 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, Klf7, Klf4, E2f4, Klf6, Klf8, Klf1, Klf12, Egr1, Egr2, Zbtb17, Klf5, E2f1, Sp5, Zfp281, Egr3, Zfp740, Zfx
metacluster_1/pattern_3 # seqlets: 2127 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic
metacluster_1/pattern_4 # seqlets: 1784 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elk1, Fli1, Elk4, Ets1, Erg, Elk3, Etv5, Fev, Elf1, Etv4, Etv1, Etv6, Etv3, XP_911724.4, Etv2, Ehf, Elf4, Elf2, Elf5, Spi1, Spdef, Elf3, Spib, Spic
metacluster_1/pattern_5 # seqlets: 1194 SequenceContrib ScoresHyp_Contrib Scores	Tead4
metacluster_1/pattern_6 # seqlets: 1091 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_7 # seqlets: 711 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Creb5, Creb1, Atf1, Crem, Nfil3, Hlf, Dbp, Tef, Creb3l2, Tfec, Srebf1, Cebpa, Cebpb, Mlx, Tfe3, Atf4, Cebpg
metacluster_1/pattern_8 # seqlets: 696 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_9 # seqlets: 597 SequenceContrib ScoresHyp_Contrib Scores	Ddit3, Cebpd, Cebpe
metacluster_1/pattern_10 # seqlets: 553 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Cbfb, Runx3
metacluster_1/pattern_11 # seqlets: 532 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_12 # seqlets: 488 SequenceContrib ScoresHyp_Contrib Scores	Twist1, Bhlha15, Tcf21, Olig2, Msc, Neurog1, Lhx3, Bhlhe22, Lhx1, Atoh1, Lhx5
metacluster_1/pattern_13 # seqlets: 356 SequenceContrib ScoresHyp_Contrib Scores	Yy1, Taf1, Zfp42, Rfx1, Maz, Wt1
metacluster_1/pattern_14 # seqlets: 319 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx6, Rfx7
metacluster_1/pattern_15 # seqlets: 276 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_1/pattern_16 # seqlets: 266 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf8, Prdm1, Irf3, Irf7, Stat2, Stat1, Irf9, Irf4, Batf3
metacluster_1/pattern_17 # seqlets: 218 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_18 # seqlets: 155 SequenceContrib ScoresHyp_Contrib Scores	Rela, Nfkb1, Relb, Nfkb2, Rel
metacluster_1/pattern_19 # seqlets: 113 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_20 # seqlets: 106 SequenceContrib ScoresHyp_Contrib Scores	Usf2, Usf1, Tfeb, Arntl, Mitf, Arnt, Bhlhe40, Clock, Srebf2, Npas2, Rxrg, Tcfl5, Mxi1, Bhlhe41, Rxrb, Mycn, Nhlh1, Nr1h4, Myc, Max
metacluster_1/pattern_21 # seqlets: 75 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_22 # seqlets: 70 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2c, Mef2a
metacluster_1/pattern_23 # seqlets: 37 SequenceContrib ScoresHyp_Contrib Scores	Prdm16, Ebf1, Sp110