# Parameters
data_name = "MN1;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_277-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_277-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 19:42:55,649 [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	MN1 cell line
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	182850	134190	8.0448	132797234	21003613	0.1582	12701199	0.0957	48405821	0.3646
rep2	182850	134190	20.8515	9177043	1806265	0.1972	1443158	0.1576	3415333	0.373
rep3	182850	134190	12.7254	50639908	8695691	0.1718	6202610	0.1225	18694936	0.3693
rep4	182850	134190	16.1059	49368768	14515866	0.2941	9008150	0.1825	19789715	0.401
rep5	182850	134190	36.3251	2981833	916801	0.3095	820438	0.2769	1168459	0.3944
rep6	182850	134190	36.6876	2113734	553459	0.2642	583356	0.2785	836972	0.3996
rep7	182850	134190	21.235	25274277	7900036	0.3128	5458655	0.2161	10295161	0.4077
rep8	182850	134190	25.4546	12721521	3690740	0.2906	2904236	0.2286	5145772	0.4051

Metric	Value
auPRC	0.5667
Calibrated Recall at 50% FDR	0.208
Number of Positive Examples in Test Data	152489
Number of Negative Examples in Test Data	7918362
Imbalance Ratio in Test Data	0.0189
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 3843 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 3338 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Klf3, Sp4, Sp1, Klf6, Klf15, Wt1, Zfx, Klf1, Maz, Sp5, Zbtb17, Zfp281, Egr1, Klf5, Klf4, E2f4, Egr2, Klf7, Usf2, Klf8, Klf12, Rela, Tfap2c, E2f1, Ptf1a, Nr1h4, Fli1, Mbd2, E2f7, Tfap2b, Sall4, Mxi1
metacluster_1/pattern_2 # seqlets: 1732 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elk1, Elk4, Ets1, Erg, Fev, Elk3, Elf1, Etv5, Etv4, Etv1, Etv6, Elf2, Ehf, Etv3, XP_911724.4, Etv2, Elf5, Elf4, Spdef, Spi1, Elf3
metacluster_1/pattern_3 # seqlets: 1201 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_4 # seqlets: 1151 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_1/pattern_5 # seqlets: 1113 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Creb1, Jdp2, Creb5, Atf1, Crem, Atf3, Fosl2, Tfec, Tfe3, Usf1, Srebf1, Creb3l2, Hlf, Nfil3, Mlx, Dbp, Fosl1, Mafb, Tef, Jun, Bhlhe40, Mitf, Tfeb, Cebpb, Rxrb, Atf4, Cebpa, Xbp1, Cebpg, Srebf2
metacluster_1/pattern_6 # seqlets: 1050 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_7 # seqlets: 1041 SequenceContrib ScoresHyp_Contrib Scores	Fos, Jund, Batf, Fosb, Junb, Mafa, Bach2, Nfe2, Nfe2l2, Mafk, Bach1, Mafg
metacluster_1/pattern_8 # seqlets: 866 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx1, Rfx4, Rfx6, Rfx7
metacluster_1/pattern_9 # seqlets: 858 SequenceContrib ScoresHyp_Contrib Scores	Arx, Phox2a, Prop1, Alx1, Uncx, Alx4, Lhx3, Alx3, Lhx1, Lhx5, Pax7, Lmx1b, Prrx2, Lhx4, Vsx2, Arid3a, Arid3b, Pou2f1, En1, Msx1, Otx1, Dbx1, Lhx2, Pax6
metacluster_1/pattern_10 # seqlets: 783 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_11 # seqlets: 726 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_1/pattern_12 # seqlets: 703 SequenceContrib ScoresHyp_Contrib Scores	Ebf1, Prdm16
metacluster_1/pattern_13 # seqlets: 593 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf7, Irf8, Stat1, Stat2, Prdm1, Irf9, Irf4, Irf5, Batf3, Irf3
metacluster_1/pattern_14 # seqlets: 520 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_1/pattern_15 # seqlets: 375 SequenceContrib ScoresHyp_Contrib Scores	Ddit3, Cebpd
metacluster_1/pattern_16 # seqlets: 291 SequenceContrib ScoresHyp_Contrib Scores	Atoh1, Neurod1, Neurod2, Olig2, Neurog2, Msc, Msgn1, Ascl1, Neurog1, Snai1, Ascl2, Clock
metacluster_1/pattern_17 # seqlets: 285 SequenceContrib ScoresHyp_Contrib Scores	Hand1
metacluster_1/pattern_18 # seqlets: 271 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_19 # seqlets: 202 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_20 # seqlets: 191 SequenceContrib ScoresHyp_Contrib Scores	Gata3, Gata1, Gata2, Gata4, Mecom, Gata6, Tal1
metacluster_1/pattern_21 # seqlets: 129 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c