In [1]:
# Parameters
sample_name = "Adipose;D;En"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_233-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_233-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 03:06:12,603 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typeAdipose tissue
    Cell GroupOther 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
    rep1120040747138.46841839583227492500.149614780770.080480583250.4383
    rep2120040747136.48912140586930614230.143114598350.068292720480.4335
    Modelling Metadata
    MetricValue
    auPRC0.4905
    Calibrated Recall at 50% FDR0.274
    Number of Positive Examples in Test Data88896
    Number of Negative Examples in Test Data7981955
    Imbalance Ratio in Test Data0.011
    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
Trp73
Fos
Tcfap2a
Ctcf
Sp3
Grhl1
Nfia
Hoxc9
Gabpa
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Pbx3absent
Mbtps2absent
Egr2absent
Pitx2absent
Sox9absent
Gata4absent
Tcfebabsent
Cebpbabsent
Smarcc2absent
Klf16absent
Cebpaabsent
Nr3c1absent
Unique Homer Motifs
Motif NameModiscoHomer
Zfp143absent
Egr3absent
E4f1absent
AC189028.1absent
Cebpgabsent
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_233-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_233-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_233-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_0, # patterns: 25, # seqlets: 22037, Positive for: Adipose;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_233-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_233-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_233-naivegw
No motifs with negative importance