In [1]:
# Parameters
sample_name = "GCN_PHT_RCPTR;A;GEO"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_152-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_152-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 22:48:30,586 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typegreen cone photoreceptors
    Cell GroupNeural Cells and Tissues
    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
    rep11052207320512.77794906160373030540.148960008250.1224164294910.335
    rep21052207320513.8543484128343776920.125739935410.1147114803460.3297
    Modelling Metadata
    MetricValue
    auPRC0.6379
    Calibrated Recall at 50% FDR0.21
    Number of Positive Examples in Test Data85562
    Number of Negative Examples in Test Data7985289
    Imbalance Ratio in Test Data0.0106
    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
Ctcf
Gabpa
Creb3
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Rfx8absent
Mef2dabsent
Smarcc2absent
Foxi1absent
Hsf1absent
Tbpl2absent
Dbpabsent
Sp3absent
Neurod1absent
Mbtps2absent
Fosabsent
Rfx2absent
Tcfebabsent
Crxabsent
Unique Homer Motifs
Motif NameModiscoHomer
Zfp143absent
Tcfap2dabsent
Pbx3absent
Sp5absent
Gsc2absent
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_152-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_152-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_152-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_1, # patterns: 19, # seqlets: 21158, Positive for: GCN_PHT_RCPTR;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_152-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_152-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_152-naivegw
Displaying motifs which has negative importances for the cell type
metacluster_0, # patterns: 20, # seqlets: 10011, Negative for: GCN_PHT_RCPTR;A;GEO