In [1]:
# Parameters
sample_name = "WHL_BRN;8wks;D;En"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_254-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_254-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 04:07:28,876 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typeWhole Brain(adult-8wks)
    Cell GroupNeural Cells and Tissues
    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
    rep127284218288310.6566118051699359610140.3047137073050.1161594216810.5034
    rep227284218288322.80792687522986982780.323937428160.1394136712820.5091
    rep327284218288321.59562739982183738660.305836700970.134136948990.5002
    rep427284218288321.60812341318467437690.288331016760.1326117868460.5038
    rep527284218288312.41274557077670233030.154244524350.0977191844810.4211
    rep627284218288315.99482114303136121090.170928309340.13492198370.4363
    Modelling Metadata
    MetricValue
    auPRC0.6124
    Calibrated Recall at 50% FDR0.229
    Number of Positive Examples in Test Data228417
    Number of Negative Examples in Test Data7842434
    Imbalance Ratio in Test Data0.0283
    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
Fos
Pbx3
Egr2
Atoh1
Ctcf
Dbp
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Sox3absent
Mef2aabsent
Nfiaabsent
Smarcc2absent
Tal1absent
Bach2absent
Elk1absent
Rorcabsent
Mbtps2absent
Sp3absent
Atf2absent
Rfx1absent
Unique Homer Motifs
Motif NameModiscoHomer
E4f1absent
Gabpaabsent
Nfatc2absent
Nfibabsent
Mef2cabsent
Rfx2absent
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_254-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_254-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_254-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_1, # patterns: 19, # seqlets: 26622, Positive for: WHL_BRN;8wks;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_254-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_254-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_254-naivegw
Displaying motifs which has negative importances for the cell type
metacluster_0, # patterns: 11, # seqlets: 6749, Negative for: WHL_BRN;8wks;D;En