In [1]:
# Parameters
sample_name = "Erythroblast;A;CL"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_45-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_45-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 17:22:14,287 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typeErythroblasts
    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
    rep1652405269010.20054333322870060110.161766706150.154144037410.3325
    Modelling Metadata
    MetricValue
    auPRC0.6192
    Calibrated Recall at 50% FDR0.185
    Number of Positive Examples in Test Data55205
    Number of Negative Examples in Test Data8015646
    Imbalance Ratio in Test Data0.0068
    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
Erf
Smarcc2
Ctcf
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Rfx2absent
Sp3absent
Klf2absent
Irf1absent
Nfe2absent
Gata6absent
Klf1absent
Mbtps2absent
Foxi1absent
Hsf1absent
Nfibabsent
Tcfebabsent
Rfx8absent
Jdp2absent
Klf14absent
Unique Homer Motifs
Motif NameModiscoHomer
Bach1absent
Pbx3absent
E4f1absent
Sp5absent
Yy1absent
Mbd2absent
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_45-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_45-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_45-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_1, # patterns: 21, # seqlets: 22520, Positive for: Erythroblast;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_45-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_45-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_45-naivegw
Displaying motifs which has negative importances for the cell type
metacluster_0, # patterns: 18, # seqlets: 9137, Negative for: Erythroblast;A;CL