In [1]:
# Parameters
sample_name = "Fr_BRN;P0;D;En"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_246-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_246-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 03:42:27,214 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typeforebrain(P0)
    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
    rep124096416229911.0576117710072300067340.255150493550.1279501298600.4259
    Modelling Metadata
    MetricValue
    auPRC0.6542
    Calibrated Recall at 50% FDR0.185
    Number of Positive Examples in Test Data142042
    Number of Negative Examples in Test Data7928809
    Imbalance Ratio in Test Data0.0176
    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
Sp3
Ctcf
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Mef2aabsent
Fosabsent
Pbx3absent
Sox3absent
Sp2absent
Gabpaabsent
Wt1absent
Nfiaabsent
Rfx1absent
Prrx1absent
Tbpl2absent
Smarcc2absent
Creb3absent
Mbtps2absent
Rfx8absent
Tal1absent
Ascl2absent
Unique Homer Motifs
Motif NameModiscoHomer
Rfx2absent
E4f1absent
Ehfabsent
Zfp143absent
Rfx5absent
Bhlhe22absent
Raxabsent
Tcfebabsent
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_246-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_246-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_246-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_1, # patterns: 19, # seqlets: 20292, Positive for: Fr_BRN;P0;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_246-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_246-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_246-naivegw
Displaying motifs which has negative importances for the cell type
metacluster_0, # patterns: 15, # seqlets: 9193, Negative for: Fr_BRN;P0;D;En