In [1]:
# Parameters
sample_name = "apTreg;8wk;D;En"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_239-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_239-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 03:22:51,824 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typeActivated primary T regulatory cells(adult-8wks)
    Cell GroupT cells
    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
    rep11432181183865.9786143352065331364530.2312185304690.1293531614560.3709
    rep214321811838613.18112556725553118310.207946158650.180688249460.3453
    Modelling Metadata
    MetricValue
    auPRC0.6326
    Calibrated Recall at 50% FDR0.191
    Number of Positive Examples in Test Data120395
    Number of Negative Examples in Test Data7950456
    Imbalance Ratio in Test Data0.0149
    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
Smarcc2
Ctcf
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Restabsent
Rfx1absent
Irf1absent
Foxi1absent
Ergabsent
Unique Homer Motifs
Motif NameModiscoHomer
Erfabsent
Sp3absent
Pbx3absent
Yy1absent
Relaabsent
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_239-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_239-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_239-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_1, # patterns: 10, # seqlets: 22811, Positive for: apTreg;8wk;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_239-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_239-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_239-naivegw
Displaying motifs which has negative importances for the cell type
metacluster_0, # patterns: 10, # seqlets: 5173, Negative for: apTreg;8wk;D;En