In [1]:
# Parameters
sample_name = "LNG;8wks;D;GEO"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_203-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_203-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 01:42:54,704 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typeLung (adult-8wks)
    Cell GroupOther Tissues
    Experiment NameDHS
    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
    rep12545931858726.1591230509593NANANANANANA
    Modelling Metadata
    MetricValue
    auPRC0.5162
    Calibrated Recall at 50% FDR0.263
    Number of Positive Examples in Test Data91988
    Number of Negative Examples in Test Data7978863
    Imbalance Ratio in Test Data0.0114
    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
Nfia
Smarcc1
Ctcf
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Klf14absent
Rfx1absent
Mbtps2absent
Grhl1absent
Sp3absent
Runx1absent
Gata1absent
Mef2aabsent
Foxa1absent
Cebpbabsent
Pbx3absent
Tcfecabsent
Nkx2-6absent
Klf5absent
Irf1absent
Gabpaabsent
Atoh1absent
Smarcc2absent
9430076C15Rikabsent
Unique Homer Motifs
Motif NameModiscoHomer
Foxb1absent
Cebpdabsent
Tbx2absent
Elk4absent
Yy1absent
Nkx2-1absent
Tcfebabsent
Sp2absent
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_203-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_203-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_203-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_0, # patterns: 25, # seqlets: 20150, Positive for: LNG;8wks;D;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_203-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_203-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_203-naivegw
No motifs with negative importance