# Parameters
sample_name = "DC;A;En"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
mitra_subdir = "report/version2"
task_dir = "task_197-naivegw"
database_name = "CISBP"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_197-naivegw/NaiveauPRC.txt"
homer_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_scans"

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 01:23:06,810 [WARNING] git-lfs not installed

display_metadata(sample_name, perf_file, reportfile, sheetname)

Sample Information

MetaData Name	Description
Cell type	dendritic in vitro differentiated cells
Cell Group	Cancer or Immortalized cells
Experiment Name	ATAC
Experiment Group	ENCODE

Pipeline Output

replicate	Naïve overlap peaks	IDR peaks	TSS enrichment (< 8 is very poor <10 is low)	Final number of unique mapping, dup-filtered, chrM filtered reads	Number of reads in called peak regions	Fraction of reads in called peak regions	Number of reads in promoter regions	Fraction of reads in promoter regions	Number of reads in enhancer regions	Fraction of reads in enhancer regions
rep1	142641	96656	17.1295	29455074	11012602	0.3741	6221938	0.2114	12810448	0.4352
rep2	142641	96656	6.515	78975437	4579277	0.058	4334155	0.0549	26057071	0.33

Modelling Metadata

Metric	Value
auPRC	0.6469
Calibrated Recall at 50% FDR	0.193
Number of Positive Examples in Test Data	120926
Number of Negative Examples in Test Data	7949925
Imbalance Ratio in Test Data	0.015
Test Chromosomes	chr2, chr3, chr19

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 Name	Modisco	Homer
Sfpi1
Ctcf

Unique TF-MoDISco Motifs

Motif Name	Modisco	Homer
Tcfec		absent
Cebpb		absent
Elk1		absent
Bcl11a		absent
Foxi1		absent
Hsf1		absent
Nfia		absent
Mbtps2		absent
Runx1		absent
Creb3		absent
Sp3		absent
Smarcc2		absent
Ets1		absent
Klf16		absent
Smarcc1		absent
Nfkb1		absent

Unique Homer Motifs

Motif Name	Modisco	Homer
Cebpg	absent
Fos	absent
Zfp143	absent
Rela	absent
E2f1	absent
Pbx3	absent
Yy1	absent
Sp2	absent
Bach2	absent
Runx2	absent

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_197-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_197-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_197-naivegw
Displaying motifs which has positive importances for the cell type

metacluster_1, # patterns: 19, # seqlets: 24930, Positive for: DC;A;En

• pattern_0: # seqlets: 5350

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Sfpi1, Bcl11a, Ets1, Spib, Spic

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_1: # seqlets: 4004

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Ctcf, Ctcfl

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_2: # seqlets: 2358

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Sp3, Sp5, Sp2, Klf16, Klf5

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_3: # seqlets: 1788

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Smarcc1, Fos, Nfe2, Nfe2l2, Fosb

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_4: # seqlets: 1783

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Bcl11a, Irf1, Prdm1, Irf2, Stat2

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_5: # seqlets: 1754

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Cebpb, Cebpa, Cebpd, Cebpg, Cebpe

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_6: # seqlets: 1548

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Nfkb1, Rela, Relb, Rel, Hivep1

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_7: # seqlets: 1366

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Creb3, 9430076C15Rik, Batf3, Atf7, Atf2

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_8: # seqlets: 861

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Runx1, Runx2, Runx3

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_9: # seqlets: 784

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Foxi1, Pbx3, Nfya, Ybx1

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_10: # seqlets: 696

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Elk1, Elk3, Erf, Etv4, Gm5454

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_11: # seqlets: 611

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Tcfec, Bach2, Tcfeb, Srebf1, Mitf

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_12: # seqlets: 571

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Mbtps2, Sp3, Yy1, Wt1, E2f1

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_13: # seqlets: 425

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Klf16, Klf14, Sp8, Sp5, Klf7

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_14: # seqlets: 397

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_15: # seqlets: 318

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Smarcc2, Tbx2, Zfp143, Zfp523, Six5

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_16: # seqlets: 157

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Ets1, Ets2, Erg, Sfpi1, Spic

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_17: # seqlets: 88

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Nfia, Nfix, Nfib

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_18: # seqlets: 71

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Hsf1

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  

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_197-naivegw/cisbp_tomtomout /srv/www/kundaje/msharmin/report/version2/task_197-naivegw/
chmod -R +755 /srv/www/kundaje/msharmin/report/version2/task_197-naivegw
Displaying motifs which has negative importances for the cell type

metacluster_0, # patterns: 29, # seqlets: 8923, Negative for: DC;A;En

• pattern_0: # seqlets: 1561

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_1: # seqlets: 1018

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Sp3, Sp2, Klf15, Maz, Zfp281

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_2: # seqlets: 995

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Glis2

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_3: # seqlets: 935

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Zeb1, Mga, Tbx4, Tcf4, Tbx1

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_4: # seqlets: 769

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_5: # seqlets: 695

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_6: # seqlets: 552

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_7: # seqlets: 535

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Gli3, Gli2, Gli1, Zbtb7c

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_8: # seqlets: 222

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Esrrb, Nr5a2, Nr5a1, Nr6a1, Esrrg

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_9: # seqlets: 198

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Nfe2l2, Nfe2, Jund, Batf, Fosb

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_10: # seqlets: 146

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Cebpd, Cebpe, Cebpg, Cebpa, Mypop

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_11: # seqlets: 137

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Cebpb, Cebpg, Cebpe, Cebpd, Sox2

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_12: # seqlets: 135

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Nr5a2

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_13: # seqlets: 142

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_14: # seqlets: 115

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_15: # seqlets: 104

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Nr5a2, Nr6a1, Esrrb, Hsf1, Nr5a1

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_16: # seqlets: 83

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Foxd3, Foxj1, Foxm1

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_17: # seqlets: 76

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_18: # seqlets: 73

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Nr5a2, Esrrb, Nr6a1, Nr5a1, Esrrg

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_19: # seqlets: 68

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_20: # seqlets: 63

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Nr5a2

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_21: # seqlets: 47

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_22: # seqlets: 44

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Nr5a2, Esrrb, Prdm4

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_23: # seqlets: 44

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Max, Hsf1

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_24: # seqlets: 36

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_25: # seqlets: 35

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  AC189028.1, Pitx2, Pitx3, Obox5, Ctcf

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_26: # seqlets: 33

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Nr5a2, Pitx2, AC189028.1, Pitx3, Obox5

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_27: # seqlets: 31

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Esrrb, Nr6a1, Nr5a1, Nr5a2, Esrrg

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores

  
• pattern_28: # seqlets: 31

  Cisbp matches (q-value>=0.01) using Tomtom (Full Report) :

  Onecut2

  Sequence

  

  Contrib Scores

  

  Hyp_Contrib Scores