# Parameters
data_name = "wCH12;A;CL"
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_91-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_91-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 19:00:33,050 [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	ch12 wt
Cell Group	Cancer or Immortalized cells
Experiment Name	ATAC
Experiment Group	Casellas Lab

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	94226	61670	12.4737	28679103	3288364	0.1147	3191941	0.1114	9859901	0.344
rep2	94226	61670	15.8856	21608006	3203941	0.1484	2985364	0.1383	7532765	0.3489

Metric	Value
auPRC	0.5868
Calibrated Recall at 50% FDR	0.23
Number of Positive Examples in Test Data	66776
Number of Negative Examples in Test Data	8004075
Imbalance Ratio in Test Data	0.0083
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 3991 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 3370 SequenceContrib ScoresHyp_Contrib Scores	Spib, Spi1, Irf8, Irf4, Prdm1, Irf3, Spic, Elf3, Ehf, Irf2, Etv2, Irf1, Ets1, Etv6, Erg, Etv4, Elf5, Gabpa, Elk1, Elf4, Elf1, Etv3, Elf2, XP_911724.4, Fli1, Elk4, Elk3, Etv1, Stat1
metacluster_1/pattern_2 # seqlets: 2617 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Klf3, Sp4, Sp1, Klf6, E2f4, Klf1, Wt1, Sp5, Klf4, Egr1, Klf7, Klf5, Maz, Klf8, Zfx, Klf12, Egr2, Zbtb17, Zfp281, Klf15, E2f1, E2f7
metacluster_1/pattern_3 # seqlets: 1835 SequenceContrib ScoresHyp_Contrib Scores	Mxi1, Usf2, Etv5, Fev, Spdef, Rfx1, Nr1h4, Myc, Mecp2, Mbd2, Tfap2c
metacluster_1/pattern_4 # seqlets: 1802 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_5 # seqlets: 1776 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_6 # seqlets: 1350 SequenceContrib ScoresHyp_Contrib Scores	Nfkb2, Nfkb1, Rela, Relb, Rel
metacluster_1/pattern_7 # seqlets: 1013 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_1/pattern_8 # seqlets: 841 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_9 # seqlets: 813 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Jdp2, Atf7, Crem, Creb5, Atf1, Atf3, Fosl2, Jun, Fosl1, Nfil3, Tef
metacluster_1/pattern_10 # seqlets: 801 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Pou2f1
metacluster_1/pattern_11 # seqlets: 734 SequenceContrib ScoresHyp_Contrib Scores	Stat2, Irf5, Irf7
metacluster_1/pattern_12 # seqlets: 663 SequenceContrib ScoresHyp_Contrib Scores	Hes7, Hes1
metacluster_1/pattern_13 # seqlets: 629 SequenceContrib ScoresHyp_Contrib Scores	Zfp740, Sall4, Bcl6, Zscan10
metacluster_1/pattern_14 # seqlets: 555 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfec, Tfeb, Arntl, Mitf, Srebf1, Bhlhe40, Tfe3, Clock, Mlx, Arnt, Npas2, Srebf2, Tcfl5, Creb3l2, Bhlhe41, Xbp1, Hlf, Dbp
metacluster_1/pattern_15 # seqlets: 434 SequenceContrib ScoresHyp_Contrib Scores	Fosb, Junb, Jund, Fos, Batf, Bach2, Nfe2, Nfe2l2, Bach1, Mafk, Mafb, Mafa, Maf, Mafg
metacluster_1/pattern_16 # seqlets: 317 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_17 # seqlets: 253 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb
metacluster_1/pattern_18 # seqlets: 207 SequenceContrib ScoresHyp_Contrib Scores	Ebf1, Prdm16
metacluster_1/pattern_19 # seqlets: 121 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_20 # seqlets: 95 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_21 # seqlets: 84 SequenceContrib ScoresHyp_Contrib Scores	Pgr
metacluster_1/pattern_22 # seqlets: 90 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_23 # seqlets: 61 SequenceContrib ScoresHyp_Contrib Scores