In [1]:
# Parameters
sample_name = "MCRPHG;A;CL"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_44-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_44-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 17:19:20,545 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typemacrophage
    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
    rep117203813539511.904161426065197592250.321894312750.1536263388180.4289
    Modelling Metadata
    MetricValue
    auPRC0.6318
    Calibrated Recall at 50% FDR0.211
    Number of Positive Examples in Test Data156524
    Number of Negative Examples in Test Data7914327
    Imbalance Ratio in Test Data0.0194
    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
Smarcc2
Sfpi1
Ctcf
Fos
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Sp3absent
Cebpbabsent
Atf7absent
Mef2aabsent
Rfx1absent
Nfibabsent
Runx1absent
Hsf1absent
Smarcc1absent
Bcl11aabsent
Gabpaabsent
Pbx3absent
Tcfecabsent
Unique Homer Motifs
Motif NameModiscoHomer
Cebpgabsent
Mef2dabsent
Sohlh2absent
Tcfebabsent
Sp2absent
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_44-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_44-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_44-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_1, # patterns: 23, # seqlets: 27300, Positive for: MCRPHG;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_44-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_44-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_44-naivegw
Displaying motifs which has negative importances for the cell type
metacluster_0, # patterns: 14, # seqlets: 11597, Negative for: MCRPHG;A;CL