In [1]:
# Parameters
sample_name = "CRBL_GRNL_Precrsr;A;GEO"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_105-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_105-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 20:28:21,708 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typecerebellar granule cell precursors(wt)
    Cell GroupNeural Cells and Tissues
    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
    rep123462916766811.331280617334159596180.19886409830.1072316193120.3923
    rep223462916766814.7313731377480104740.214852665380.1412149710210.4014
    rep323462916766814.756244515539102350500.2360365910.1357181327590.4075
    Modelling Metadata
    MetricValue
    auPRC0.6606
    Calibrated Recall at 50% FDR0.206
    Number of Positive Examples in Test Data191604
    Number of Negative Examples in Test Data7879247
    Imbalance Ratio in Test Data0.0237
    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
Sp2
Ctcf
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Foxd3absent
Elk1absent
Creb3absent
Pbx3absent
Nfiaabsent
Mef2dabsent
Smarcc2absent
Seboxabsent
Rfx1absent
Tal1absent
Sox3absent
Foxp4absent
Pax1absent
Fosabsent
Tcfecabsent
Unique Homer Motifs
Motif NameModiscoHomer
Zfp143absent
Stat1absent
Zfp161absent
Egr4absent
Atoh1absent
Mbd1absent
Gabpaabsent
Prrx1absent
E4f1absent
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_105-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_105-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_105-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_0, # patterns: 19, # seqlets: 18023, Positive for: CRBL_GRNL_Precrsr;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_105-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_105-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_105-naivegw
No motifs with negative importance