In [1]:
# Parameters
sample_name = "matureB;A;CL"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_8-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_8-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 15:30:40,033 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typemature B cells
    Cell GroupB cells
    Experiment NameATAC
    Experiment GroupCasellas Lab
    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
    rep1976147662710.53855073228081815830.161361345910.121160993880.3175
    Modelling Metadata
    MetricValue
    auPRC0.5881
    Calibrated Recall at 50% FDR0.232
    Number of Positive Examples in Test Data83836
    Number of Negative Examples in Test Data7987015
    Imbalance Ratio in Test Data0.0104
    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
Common Motifs
Motif NameModiscoHomer
Ctcf
Pbx3
Sfpi1
Mbtps2
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Jdp2absent
Ets1absent
Runx1absent
Gabpaabsent
Nfiaabsent
Sp3absent
Hsf1absent
Smarcc2absent
Tcfecabsent
Fosabsent
Relbabsent
Tbpl2absent
Ergabsent
Rfx8absent
Mef2aabsent
Bcl11aabsent
Creb3absent
Rfx1absent
Unique Homer Motifs
Motif NameModiscoHomer
Grhl1absent
Sp2absent
Zfp143absent
Atf6absent
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_8-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_8-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_8-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_0, # patterns: 24, # seqlets: 26316, Positive for: matureB;A;CL
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_8-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_8-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_8-naivegw
No motifs with negative importance