In [1]:
# Parameters
sample_name = "RTN;D1;D;En"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_234-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_234-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 03:08:11,417 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typeRetina(newborn 1 day)
    Cell GroupNeural Cells and 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
    rep11969201383319.6586153553824357487640.2328174231450.1135639807730.4167
    Modelling Metadata
    MetricValue
    auPRC0.653
    Calibrated Recall at 50% FDR0.192
    Number of Positive Examples in Test Data127996
    Number of Negative Examples in Test Data7942855
    Imbalance Ratio in Test Data0.0159
    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
Atoh1
Pparg
Pbx3
Rfx1
Smarcc2
Sp3
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Tcfap2aabsent
Crxabsent
Tcfebabsent
Mef2dabsent
Atf7absent
Sox3absent
Pax5absent
Smarcc1absent
Mbtps2absent
Gabpaabsent
Lhx2absent
E2f1absent
Pax1absent
Tbpl2absent
Nfiaabsent
Unique Homer Motifs
Motif NameModiscoHomer
Mazabsent
Atf6absent
Meis1absent
Yy1absent
Raxabsent
E2f4absent
Obox6absent
Erfabsent
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_234-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_234-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_234-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_0, # patterns: 26, # seqlets: 19296, Positive for: RTN;D1;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_234-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_234-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_234-naivegw
No motifs with negative importance