In [1]:
# Parameters
sample_name = "wES;FaceP;E14.5;D;En"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_260-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_260-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 04:24:42,978 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typeembryonic facial prominence(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
    rep13682762289909.0167159460017NANANANANANA
    rep226094416612113.019185916743169470280.197395093040.1107382729240.4456
    Modelling Metadata
    MetricValue
    auPRC0.6297
    Calibrated Recall at 50% FDR0.226
    Number of Positive Examples in Test Data171709
    Number of Negative Examples in Test Data7899142
    Imbalance Ratio in Test Data0.0213
    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
Grhl1
Rest
Tcfeb
Rfx1
Nfia
Ascl2
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Runx2absent
Hsf1absent
Mef2aabsent
Nficabsent
Zfp281absent
Mbtps2absent
9430076C15Rikabsent
Smarcc2absent
Sox3absent
Lhx3absent
Pax6absent
Sp3absent
Pbx3absent
Ebf1absent
Erfabsent
Fosabsent
Foxp4absent
Unique Homer Motifs
Motif NameModiscoHomer
E2f4absent
Phox2babsent
Stat1absent
Zfp143absent
Sp2absent
Elk3absent
Creb3absent
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_260-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_260-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_260-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_0, # patterns: 30, # seqlets: 20185, Positive for: wES;FaceP;E14.5;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_260-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_260-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_260-naivegw
No motifs with negative importance