In [1]:
# Parameters
sample_name = "3T3-L1;FBRBLST;D;En"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_221-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_221-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.
2019-07-23 02:28:53,397 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typemouse embryo fibroblasts/3T3-L1
    Cell GroupCancer or Immortalized cells
    Experiment NameDHS
    Experiment GroupENCODE
    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
    rep12228111796684.7801249521428NANANANANANA
    Modelling Metadata
    MetricValue
    auPRC0.4785
    Calibrated Recall at 50% FDR0.293
    Number of Positive Examples in Test Data94966
    Number of Negative Examples in Test Data7975885
    Imbalance Ratio in Test Data0.0118
    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
Creb3
Ctcf
Fos
Mbtps2
Pbx3
Cebpb
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Sp2absent
Bhlha15absent
Hsf1absent
Erfabsent
Tcfap2eabsent
Irf1absent
Tcfecabsent
Smarcc2absent
Nfiaabsent
Ebf1absent
Runx2absent
Mef2dabsent
Rfx1absent
Unique Homer Motifs
Motif NameModiscoHomer
Runx1absent
Klf2absent
Zfp238absent
Gabpaabsent
Zfp143absent
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_221-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_221-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_221-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_1, # patterns: 23, # seqlets: 23511, Positive for: 3T3-L1;FBRBLST;D;En
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_221-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_221-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_221-naivegw
Displaying motifs which has negative importances for the cell type
metacluster_0, # patterns: 22, # seqlets: 10014, Negative for: 3T3-L1;FBRBLST;D;En