In [1]:
# Parameters
sample_name = "DC_pBMD;A;GEO"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_148-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_148-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.
2019-07-22 22:37:14,353 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typePrimary bone marrow derived dendritic cells (DCs, control vector)
    Cell GroupOther Immune Cells
    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
    rep115446910345614.53282493118077362620.310534456000.1383115397030.4632
    rep215446910345616.74852189738883416150.381339645710.1812106670670.4876
    Modelling Metadata
    MetricValue
    auPRC0.6119
    Calibrated Recall at 50% FDR0.238
    Number of Positive Examples in Test Data134344
    Number of Negative Examples in Test Data7936507
    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
Sfpi1
Ctcf
Mbtps2
Cebpb
Creb3
Runx1
Tcfec
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Smarcc2absent
Bcl11aabsent
Hsf1absent
Mef2babsent
Fosabsent
Foxi1absent
Sp3absent
Unique Homer Motifs
Motif NameModiscoHomer
Tcfebabsent
Nfe2l2absent
Zfp143absent
Pbx3absent
Sp5absent
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_148-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_148-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_148-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_1, # patterns: 17, # seqlets: 25903, Positive for: DC_pBMD;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_148-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_148-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_148-naivegw
Displaying motifs which has negative importances for the cell type
metacluster_0, # patterns: 19, # seqlets: 14889, Negative for: DC_pBMD;A;GEO