In [1]:
# Parameters
sample_name = "gamma_delta_TCR;A;CL"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_77-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_77-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 19:00:37,765 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typegamma delta TCR wt
    Cell GroupT 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
    rep11061467316611.57465291564387013980.164567348300.1273183210540.3464
    Modelling Metadata
    MetricValue
    auPRC0.6352
    Calibrated Recall at 50% FDR0.196
    Number of Positive Examples in Test Data86218
    Number of Negative Examples in Test Data7984633
    Imbalance Ratio in Test Data0.0107
    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
Tcfeb
Ctcf
9430076C15Rik
Pbx3
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Smarcc2absent
Sp3absent
Runx2absent
Tcf7l2absent
Nfiaabsent
Relaabsent
Rfx1absent
Mbtps2absent
Tbpl2absent
Irf1absent
Ets1absent
Rfx8absent
Unique Homer Motifs
Motif NameModiscoHomer
Zfp143absent
Elk3absent
Zfp3absent
Sp2absent
Runx3absent
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_77-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_77-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_77-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_1, # patterns: 22, # seqlets: 22287, Positive for: gamma_delta_TCR;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_77-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_77-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_77-naivegw
Displaying motifs which has negative importances for the cell type
metacluster_0, # patterns: 23, # seqlets: 10772, Negative for: gamma_delta_TCR;A;CL