In [1]:
# Parameters
sample_name = "wES;limb;E11.5;D;En"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_257-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_257-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 04:15:43,628 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typemixed embryonic mouse limb(E11.5)
    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
    rep12264331560456.7951174399423NANANANANANA
    rep22264331560459.5655113243454193565990.171116667800.103434595930.3838
    Modelling Metadata
    MetricValue
    auPRC0.6701
    Calibrated Recall at 50% FDR0.196
    Number of Positive Examples in Test Data134282
    Number of Negative Examples in Test Data7936569
    Imbalance Ratio in Test Data0.0166
    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
Rfx1
Rest
Tcf21
Pbx3
Mbtps2
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Smarcc2absent
Zfp148absent
Sp3absent
Tcfebabsent
Hsf1absent
Lhx9absent
Tcf7l2absent
Nfiaabsent
E2f1absent
Ascl2absent
Hoxd13absent
Erfabsent
Creb3absent
Sox3absent
Unique Homer Motifs
Motif NameModiscoHomer
Nr2c2absent
Hoxc9absent
E2f8absent
Zfp143absent
Prrx2absent
Sp2absent
E4f1absent
Ctcflabsent
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_257-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_257-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_257-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_0, # patterns: 25, # seqlets: 20394, Positive for: wES;limb;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_257-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_257-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_257-naivegw
No motifs with negative importance