In [1]:
# Parameters
sample_name = "placenta;A;CL"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_61-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_61-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 18:10:56,105 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typeplacenta
    Cell GroupOther Tissues
    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
    rep11169975394912.16841082881928230.04714664530.11414674810.3588
    rep2116997539498.34813986315234269230.08636404790.0914144068480.3616
    rep31169975394911.1197107672118187560.076211657880.108538644460.3595
    Modelling Metadata
    MetricValue
    auPRC0.6163
    Calibrated Recall at 50% FDR0.201
    Number of Positive Examples in Test Data67987
    Number of Negative Examples in Test Data8002864
    Imbalance Ratio in Test Data0.0084
    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
Nr1h2
Sp3
Pbx3
Mbtps2
Ctcf
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Foxa2absent
Fosabsent
Irf1absent
Rfx1absent
Gata4absent
Klf16absent
Cebpbabsent
Bach2absent
9430076C15Rikabsent
Mef2cabsent
Erfabsent
Smarcc2absent
Grhl1absent
Gata2absent
Tcfap2aabsent
Unique Homer Motifs
Motif NameModiscoHomer
Tcfebabsent
E4f1absent
Nfe2l2absent
Mbd2absent
Sohlh2absent
Gabpaabsent
Zfp143absent
Cebpeabsent
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_61-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_61-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_61-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_0, # patterns: 24, # seqlets: 20276, Positive for: placenta;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_61-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_61-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_61-naivegw
No motifs with negative importance