In [1]:
# Parameters
sample_name = "ILC1;A;GEO"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_107-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_107-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 20:35:15,722 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typeILC1(WT)
    Cell GroupOther Immune Cells
    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
    rep1970397360211.73393213247246253680.14434016260.1059113200820.3525
    rep2970397360215.54552771146460728220.219338373950.1386103840630.375
    Modelling Metadata
    MetricValue
    auPRC0.5906
    Calibrated Recall at 50% FDR0.209
    Number of Positive Examples in Test Data83947
    Number of Negative Examples in Test Data7986904
    Imbalance Ratio in Test Data0.0104
    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
Mbtps2
Ctcf
Fos
Pbx3
Rela
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Rorcabsent
Irf1absent
Smarcc2absent
Tcfebabsent
Nfiaabsent
Rfx8absent
Ergabsent
Ets1absent
Sp3absent
Runx1absent
9430076C15Rikabsent
Rfx2absent
Unique Homer Motifs
Motif NameModiscoHomer
Zfp143absent
Creb3absent
Sp5absent
Etv5absent
Runx2absent
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_107-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_107-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_107-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_1, # patterns: 20, # seqlets: 24371, Positive for: ILC1;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_107-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_107-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_107-naivegw
Displaying motifs which has negative importances for the cell type
metacluster_0, # patterns: 13, # seqlets: 8922, Negative for: ILC1;A;GEO