In [1]:
# Parameters
sample_name = "MZ_B;A;CL"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_9-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_9-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 15:32:41,498 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typeMZ B cells
    Cell GroupB 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
    rep11243779987813.173945590671105004050.230462874260.138156508590.3434
    Modelling Metadata
    MetricValue
    auPRC0.5545
    Calibrated Recall at 50% FDR0.266
    Number of Positive Examples in Test Data106157
    Number of Negative Examples in Test Data7964694
    Imbalance Ratio in Test Data0.0132
    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
Common Motifs
Motif NameModiscoHomer
Pbx3
Sp3
Ctcf
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Ets1absent
Bcl11aabsent
Relbabsent
Irf1absent
Runx1absent
Rfx1absent
Smarcc2absent
Fli1absent
Spibabsent
Unique Homer Motifs
Motif NameModiscoHomer
Zfp143absent
Pax1absent
Mbtps2absent
Sfpi1absent
Tbpl2absent
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_9-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_9-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_9-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_1, # patterns: 16, # seqlets: 21777, Positive for: MZ_B;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_9-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_9-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_9-naivegw
Displaying motifs which has negative importances for the cell type
metacluster_0, # patterns: 21, # seqlets: 6591, Negative for: MZ_B;A;CL