In [1]:
# Parameters
sample_name = "ESNPHL_ex-vivo_BlbC;A;CL"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_20-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_20-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 16:07:59,720 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typeeosinphils (ex-vivo, BalbC)
    Cell GroupOther Immune 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
    rep1540152991217.4516103301457558920.073310035190.097331774710.3081
    rep2540152991214.33172025744613391130.066217248380.085262722480.3099
    rep3540152991217.4028148212669766070.06612389140.083743989430.2972
    rep4540152991214.06412219892613829550.062418762040.084668788970.3101
    Modelling Metadata
    MetricValue
    auPRC0.6945
    Calibrated Recall at 50% FDR0.17
    Number of Positive Examples in Test Data35834
    Number of Negative Examples in Test Data8035017
    Imbalance Ratio in Test Data0.0044
    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
Etv6absent
Jdp2absent
Gata2absent
Runx1absent
Irf1absent
Smarcc2absent
Sfpi1absent
Mbtps2absent
Tbpl2absent
Tcfecabsent
Nfe2l2absent
Cebpbabsent
Unique Homer Motifs
Motif NameModiscoHomer
Zfp143absent
Yy1absent
Tcfebabsent
Cebpgabsent
Elk1absent
Smarcc1absent
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_20-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_20-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_20-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_0, # patterns: 19, # seqlets: 22682, Positive for: ESNPHL_ex-vivo_BlbC;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_20-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_20-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_20-naivegw
No motifs with negative importance