In [1]:
# Parameters
sample_name = "Mammary_BptfKO;A;GEO"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_188-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_188-naivegw/NaiveauPRC.txt"
homer_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_scans"
In [2]:
from matlas.modisco_report import modisco_report_pipeline, display_metadata
reportfile= "/mnt/lab_data/kundaje/msharmin/mouse_hem/with_tfd/full_mouse50/filtering samples_MS2.xlsx"
sheetname = "filter23"

load data from labcluster

Using TensorFlow backend.
2019-07-23 00:53:31,470 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typeBptfKO Mammary Cells
    Cell GroupOther Tissues
    Experiment NameATAC
    Experiment GroupGEO
    Pipeline Output
    replicateNaïve overlap peaksIDR peaksTSS enrichment (< 8 is very poor <10 is low)Final number of unique mapping, dup-filtered, chrM filtered readsNumber of reads in called peak regionsFraction of reads in called peak regionsNumber of reads in promoter regionsFraction of reads in promoter regionsNumber of reads in enhancer regionsFraction of reads in enhancer regions
    rep11251038309018.78412490353639342750.158127241480.109582229930.3304
    rep21251038309015.513649338552325510.04733993180.081215549410.3162
    rep31251038309018.08352517249953884440.214235429560.140890599250.3602
    rep41251038309022.0198805650111618880.14459315230.115926600180.3309
    rep51251038309021.239366312938440550.12768449250.127722963930.3472
    Modelling Metadata
    MetricValue
    auPRC0.6299
    Calibrated Recall at 50% FDR0.221
    Number of Positive Examples in Test Data107015
    Number of Negative Examples in Test Data7963836
    Imbalance Ratio in Test Data0.0133
    Test Chromosomeschr2, chr3, chr19
In [4]:
from matlas.modisco_report import display_comparative_motif_sets
display_comparative_motif_sets(sample_name, homer_root, modisco_root)

TF-MoDISco is using the TensorFlow backend.
Number of CISBP motifs obtained by TF-MoDISco and Homer-denovo
Shared Motifs
Motif NameModiscoHomer
Smarcc2
9430076C15Rik
Ctcf
Fos
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Irf1absent
Rfx1absent
Tcfebabsent
Cebpbabsent
Trp73absent
Pbx3absent
Nfiaabsent
Tcfap2aabsent
Creb1absent
Srfabsent
Sp3absent
Gabpaabsent
Nfkb1absent
Runx2absent
Sox3absent
Unique Homer Motifs
Motif NameModiscoHomer
Nfyaabsent
Cebpdabsent
Sp2absent
Relaabsent
In [5]:
modisco_report_pipeline(sample_name, modisco_root, mitra_subdir, task_dir, database_name, 
                        importance=True, render=True)

rsync -t -av /srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019/task_188-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_188-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_188-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_0, # patterns: 27, # seqlets: 18776, Positive for: Mammary_BptfKO;A;GEO
In [6]:
modisco_report_pipeline(sample_name, modisco_root, mitra_subdir, task_dir, database_name, 
                        importance=False, render=True)

rsync -t -av /srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019/task_188-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_188-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_188-naivegw
No motifs with negative importance