In [1]:
# Parameters
sample_name = "aB_LPS+IL21;A;CL"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_15-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_15-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 15:52:50,318 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typeaB LPS+IL21
    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
    rep1431022878013.7624573474938315170.083842268700.0925144054500.3151
    Modelling Metadata
    MetricValue
    auPRC0.7158
    Calibrated Recall at 50% FDR0.175
    Number of Positive Examples in Test Data37148
    Number of Negative Examples in Test Data8033703
    Imbalance Ratio in Test Data0.0046
    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
Mbtps2
Tbpl2
Ctcf
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Tcfecabsent
Nfkb1absent
Fosabsent
Smarcc2absent
Bcl11aabsent
Hsf1absent
Nfiaabsent
Sp3absent
Atf7absent
Mef2babsent
Foxi1absent
Ebf1absent
Irf1absent
Unique Homer Motifs
Motif NameModiscoHomer
Klf5absent
Elk1absent
Jdp2absent
E4f1absent
Pbx3absent
Zfp143absent
Relabsent
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_15-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_15-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_15-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_1, # patterns: 18, # seqlets: 25061, Positive for: aB_LPS+IL21;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_15-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_15-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_15-naivegw
Displaying motifs which has negative importances for the cell type
metacluster_0, # patterns: 14, # seqlets: 5752, Negative for: aB_LPS+IL21;A;CL