# Parameters
data_name = "MEL_Znc_di-cl;24h;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_274-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_274-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 19:42:35,748 [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	MEL cell line treated with 125 uM zinc dichloride for 24 hours
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	232192	183630	7.0139	133546065	38436806	0.2879	13432508	0.1006	57965465	0.4341
rep2	232192	183630	14.2448	21127964	6231228	0.2952	3089735	0.1464	9913767	0.4696

Metric	Value
auPRC	0.5677
Calibrated Recall at 50% FDR	0.24
Number of Positive Examples in Test Data	166831
Number of Negative Examples in Test Data	7904020
Imbalance Ratio in Test Data	0.0207
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 12212 SequenceContrib ScoresHyp_Contrib Scores	Spi1, Spib, Irf8, Irf4, Spic, Irf3, Etv6, Etv4, Elf3, Prdm1, Etv2
metacluster_1/pattern_1 # seqlets: 6128 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_2 # seqlets: 1211 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Klf3, Sp2, Sp3, Sp1, Klf7, Klf6, Klf4, E2f4, Klf8, Klf12, Klf1, Egr1, Egr2, Zbtb17, Klf5, E2f1, Sp5, Zfp281, Egr3, Zfp740
metacluster_1/pattern_3 # seqlets: 757 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic, Zfp322a
metacluster_1/pattern_4 # seqlets: 440 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_5 # seqlets: 405 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_6 # seqlets: 379 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_7 # seqlets: 345 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Stat1, Irf7, Stat2, Irf9, Batf3
metacluster_1/pattern_8 # seqlets: 339 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_9 # seqlets: 283 SequenceContrib ScoresHyp_Contrib Scores	Bcl6, Rela, Elf5, Ets2, Maz, Gabpa, Wt1, Ets1, Elk4
metacluster_1/pattern_10 # seqlets: 255 SequenceContrib ScoresHyp_Contrib Scores	Nfyc, Nfya, Nfyb, Foxi1, Pbx3
metacluster_1/pattern_11 # seqlets: 208 SequenceContrib ScoresHyp_Contrib Scores	Nfe2, Bach2, Nfe2l2, Bach1, Mafa, Mafk, Jun, Mafb, Atf3, Fosl2, Batf, Mafg, Fosb, Junb, Maff, Fosl1, Jund, Jdp2, Fos, Maf
metacluster_1/pattern_12 # seqlets: 193 SequenceContrib ScoresHyp_Contrib Scores	Elk1, Fli1, Elf1, Erg, Elk3, Etv1, Etv5, Zfx, Etv3, Elf4, XP_911724.4, Elf2, Ehf, Fev, Spdef, Usf2, Mxi1
metacluster_1/pattern_13 # seqlets: 134 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_14 # seqlets: 134 SequenceContrib ScoresHyp_Contrib Scores	Nr1d2
metacluster_1/pattern_15 # seqlets: 106 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_16 # seqlets: 76 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_17 # seqlets: 67 SequenceContrib ScoresHyp_Contrib Scores	Runx1
metacluster_1/pattern_18 # seqlets: 66 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_19 # seqlets: 62 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_20 # seqlets: 62 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpd, Cebpg, Cebpa, Cebpe, Dbp, Nfil3, Hlf, Tef, Atf4, Ddit3, Creb1, Gmeb2, Atf2, Crem, Atf7, Mypop
metacluster_1/pattern_21 # seqlets: 56 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_22 # seqlets: 50 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfe3, Tfeb, Arntl, Tfec, Mitf, Bhlhe40, Srebf1, Clock, Arnt, Mlx, Srebf2, Npas2, Tcfl5, Bhlhe41, Rxrg, Nr1h4, Creb3l2, Rxrb, Mycn, Atf1, Max
metacluster_1/pattern_23 # seqlets: 48 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_24 # seqlets: 45 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_25 # seqlets: 46 SequenceContrib ScoresHyp_Contrib Scores	Cbfb, Runx2
metacluster_1/pattern_26 # seqlets: 36 SequenceContrib ScoresHyp_Contrib Scores	Creb5, Rfx1, Tal1, Gata1