In [1]:
# Parameters
sample_name = "MCRPHG_BMD.UnStmltd;A;GEO"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_142-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_142-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 22:17:54,343 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typebone marrow-derived macrophages (Unstimulated)
    Cell GroupOther Immune 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
    rep1692934235710.6363111970646483490.0588463650.075740925750.3661
    rep269293423579.93081761077915404040.087614537970.082663414070.3605
    rep369293423577.6328261877528995450.034414875950.056886048440.3288
    Modelling Metadata
    MetricValue
    auPRC0.584
    Calibrated Recall at 50% FDR0.248
    Number of Positive Examples in Test Data50238
    Number of Negative Examples in Test Data8020613
    Imbalance Ratio in Test Data0.0062
    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
Nfe2l2
Ctcf
Pbx3
Sp3
Tcfec
Creb3
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Mbtps2absent
Smarcc2absent
Sfpi1absent
Runx2absent
Cebpbabsent
Rfx1absent
Bcl11aabsent
Mef2aabsent
Unique Homer Motifs
Motif NameModiscoHomer
Cebpgabsent
Mef2babsent
Zfp143absent
Etv6absent
Yy1absent
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_142-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_142-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_142-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_1, # patterns: 17, # seqlets: 25012, Positive for: MCRPHG_BMD.UnStmltd;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_142-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_142-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_142-naivegw
Displaying motifs which has negative importances for the cell type
metacluster_0, # patterns: 16, # seqlets: 7846, Negative for: MCRPHG_BMD.UnStmltd;A;GEO