In [1]:
# Parameters
sample_name = "AML;AE9a;A;GEO"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_145-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_145-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 22:27:32,735 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typeCkit Mice cells AE9a (AML)
    Cell GroupCancer or Immortalized cells
    Experiment NameATAC
    Experiment GroupGEO
    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
    rep11918601542618.780169330884155877850.224980446240.1161268746630.3877
    rep219186015426110.365758011754164244510.283278721480.1357238172430.4107
    Modelling Metadata
    MetricValue
    auPRC0.5125
    Calibrated Recall at 50% FDR0.271
    Number of Positive Examples in Test Data161644
    Number of Negative Examples in Test Data7909207
    Imbalance Ratio in Test Data0.02
    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
Pbx3
Nfe2l2
Ets1
Ctcf
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Nfiaabsent
Creb3absent
Restabsent
Runx2absent
Ergabsent
Tcfebabsent
Sfpi1absent
Gata2absent
Irf1absent
Sp3absent
Smarcc2absent
Sp5absent
Unique Homer Motifs
Motif NameModiscoHomer
Gata6absent
Sp2absent
Zfp143absent
Zfp637absent
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_145-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_145-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_145-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_1, # patterns: 19, # seqlets: 23576, Positive for: AML;AE9a;A;GEO
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_145-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_145-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_145-naivegw
Displaying motifs which has negative importances for the cell type
metacluster_0, # patterns: 19, # seqlets: 10753, Negative for: AML;AE9a;A;GEO