In [1]:
# Parameters
sample_name = "wES;RTN;E11.5;D;En"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_235-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_235-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 03:10:59,956 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typemixed embryonic mouse retina(E14.5)
    Cell GroupES cells and embryonic tissues
    Experiment NameDHS
    Experiment GroupENCODE
    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
    rep121153414577111.945479534550149191710.1876101384370.1275304204500.3826
    rep22115341457717.7652167475968NANANANANANA
    Modelling Metadata
    MetricValue
    auPRC0.6772
    Calibrated Recall at 50% FDR0.154
    Number of Positive Examples in Test Data155919
    Number of Negative Examples in Test Data7914932
    Imbalance Ratio in Test Data0.0193
    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
Ctcf
Sp3
Tcfeb
Neurod1
Rfx1
Rest
Mbtps2
Smarcc2
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Tbpl2absent
Zfp143absent
Sox17absent
Gabpaabsent
Zfp281absent
Hsf1absent
Roraabsent
Pax1absent
Pbx3absent
Ebf1absent
Nfiaabsent
Lhx2absent
Lhx3absent
Creb3absent
Unique Homer Motifs
Motif NameModiscoHomer
E4f1absent
Sox3absent
Emx2absent
Rorcabsent
Sp2absent
Elk3absent
Tcfl5absent
Hmga2absent
E2f8absent
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_235-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_235-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_235-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_0, # patterns: 33, # seqlets: 18139, Positive for: wES;RTN;E11.5;D;En
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_235-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_235-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_235-naivegw
No motifs with negative importance