In [1]:
# Parameters
sample_name = "LNG;8wks;D;En"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_227-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_227-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 02:48:14,040 [WARNING] git-lfs not installed
In [3]:
display_metadata(sample_name, perf_file, reportfile, sheetname)
    Sample Information
    MetaData NameDescription
    Cell typeLung(adult-8wks)
    Cell GroupOther 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
    rep12608571846466.1606230472976NANANANANANA
    rep226085718464612.11792229518538928580.174725131940.112897864890.4392
    rep326085718464612.5322224191632996400.148422135420.099695663840.4303
    Modelling Metadata
    MetricValue
    auPRC0.5492
    Calibrated Recall at 50% FDR0.253
    Number of Positive Examples in Test Data146818
    Number of Negative Examples in Test Data7924033
    Imbalance Ratio in Test Data0.0182
    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
Irf1
Ctcf
Unique TF-MoDISco Motifs
Motif NameModiscoHomer
Bach2absent
Figlaabsent
Sp3absent
Rfx8absent
Mbtps2absent
Grhl1absent
Pbx3absent
Jdp2absent
Etv6absent
Nkx2-6absent
Hsf1absent
Mef2aabsent
Gata1absent
Klf2absent
Cebpbabsent
Rfx1absent
Smarcc2absent
Foxc2absent
Fosabsent
Nfiaabsent
Unique Homer Motifs
Motif NameModiscoHomer
Smarcc1absent
Zfp143absent
Nkx2-9absent
Elk4absent
Cebpdabsent
Nficabsent
E4f1absent
Sp2absent
Foxb1absent
Nfyaabsent
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_227-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_227-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_227-naivegw
Displaying motifs which has positive importances for the cell type
metacluster_0, # patterns: 25, # seqlets: 22459, Positive for: LNG;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_227-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_227-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_227-naivegw
No motifs with negative importance