In [1]:
# Parameters
sample_name = "ILC1;A;CL"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_84-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_84-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 19:22:14,630 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typeILC1
    Cell GroupOther Immune 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
    rep11088528932812.203747688263126284430.264978960630.1656157524740.3305
    Modelling Metadata
    MetricValue
    auPRC0.5858
    Calibrated Recall at 50% FDR0.207
    Number of Positive Examples in Test Data108114
    Number of Negative Examples in Test Data7962737
    Imbalance Ratio in Test Data0.0134
    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
Pbx3
Ctcf
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Mbtps2absent
Creb3absent
Rfx1absent
Nfibabsent
Relbabsent
Irf1absent
Fosabsent
Runx2absent
Smarcc2absent
Sp3absent
Mef2aabsent
Ets1absent
Unique Homer Motifs
Motif NameModiscoHomer
Gabpaabsent
Sp5absent
Yy1absent
Irf2absent
Zfp143absent
Tbx3absent
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_84-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_84-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_84-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_1, # patterns: 18, # seqlets: 24337, Positive for: ILC1;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_84-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_84-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_84-naivegw
Displaying motifs which has negative importances for the cell type
metacluster_0, # patterns: 12, # seqlets: 4861, Negative for: ILC1;A;CL