In [1]:
# Parameters
sample_name = "3134_mammaryADNCRCNM;D;GE"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_204-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_204-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 01:46:15,143 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typemurine mammary adenocarcinoma cell line(3134 cell line)
    Cell GroupCancer or Immortalized cells
    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
    rep11383268714013.350572462209204568820.2824129174030.1783279063700.3852
    Modelling Metadata
    MetricValue
    auPRC0.6141
    Calibrated Recall at 50% FDR0.212
    Number of Positive Examples in Test Data110573
    Number of Negative Examples in Test Data7960278
    Imbalance Ratio in Test Data0.0137
    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
Fos
Nfia
Ctcf
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Smarcc2absent
Foxp4absent
Hsf1absent
Mef2aabsent
Rfx2absent
Atf6absent
Sp3absent
Cebpbabsent
Ebf1absent
Stat2absent
Foxd3absent
Ergabsent
Runx2absent
Creb3absent
Mbtps2absent
Irf1absent
Pbx3absent
Unique Homer Motifs
Motif NameModiscoHomer
E4f1absent
Sp5absent
Klf4absent
Etv2absent
Runx1absent
Zfp143absent
E2f7absent
Yy1absent
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_204-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_204-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_204-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_1, # patterns: 26, # seqlets: 17700, Positive for: 3134_mammaryADNCRCNM;D;GE
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_204-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_204-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_204-naivegw
Displaying motifs which has negative importances for the cell type
metacluster_0, # patterns: 15, # seqlets: 9862, Negative for: 3134_mammaryADNCRCNM;D;GE