# Parameters
data_name = "BRN;MDL_OBLNGT;A;CL"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
tomtom_report_root = "http://mitra.stanford.edu/kundaje/msharmin/report/tomtom_outs/cells"
task_dir = "task_70-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_70-naivegw/NaiveauPRC.txt"
homer_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_scans"
reportfile = "/mnt/lab_data/kundaje/msharmin/annotations/filtering samples_MS2.xlsx"
sheetname = "filter23"

from matlas.reports import display_metadata

load data from labcluster

Using TensorFlow backend.
2019-08-30 18:56:01,731 [WARNING] git-lfs not installed

display_metadata(data_name, perf_file, reportfile, sheetname)

from matlas.reports import display_paiwise_pattern_comparison
from matlas.reports import display_denovo_patterns

display_denovo_patterns(data_name, modisco_root=modisco_root)

TF-MoDISco is using the TensorFlow backend.

display_paiwise_pattern_comparison(data_name, modisco_root, homer_root)

MetaData Name	Description
Cell type	Brain- Medulla Oblongata
Cell Group	Neural Cells and Tissues
Experiment Name	ATAC
Experiment Group	Casellas Lab

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	87447	47590	9.4114	11977761	355140	0.0297	876467	0.0733	3913495	0.3273
rep2	87447	47590	11.4626	41196844	3759560	0.0913	3908200	0.0949	14884486	0.3615

Metric	Value
auPRC	0.671
Calibrated Recall at 50% FDR	0.182
Number of Positive Examples in Test Data	56390
Number of Negative Examples in Test Data	8014461
Imbalance Ratio in Test Data	0.007
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 4772 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 2188 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Klf3, Sp1, Sp4, Klf6, Klf4, E2f4, Klf5, Egr1, Klf7, Sp5, Zbtb17, Klf8, Klf12, Egr2, Zfp281, Klf1, Wt1, Maz, E2f1, Egr3, Klf15, Srebf2, Sall4, Zfp740
metacluster_1/pattern_2 # seqlets: 1763 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_3 # seqlets: 1630 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_4 # seqlets: 1578 SequenceContrib ScoresHyp_Contrib Scores	Sox9, Sox10, Sox2, Sox3, Sox6, Sox17, Sox4
metacluster_1/pattern_5 # seqlets: 1354 SequenceContrib ScoresHyp_Contrib Scores	Rela, Ets2, Ptf1a, E2f7, E2f3
metacluster_1/pattern_6 # seqlets: 1352 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_1/pattern_7 # seqlets: 1207 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Fli1, Elk4, Ets1, Elk1, Erg, Elf1, Elk3, Etv4, Etv1, Etv2, Fev, Etv5, Etv3, Ehf, Etv6, XP_911724.4, Elf3, Elf5, Elf4, Spi1, Elf2, Spdef, Mbd2, Irf8
metacluster_1/pattern_8 # seqlets: 938 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Atf7, Jdp2, Creb5, Crem, Atf1, Atf3, Mafb, Fosl2, Fosl1, Nfil3, Jun, Tef, Tfe3, Hlf, Dbp
metacluster_1/pattern_9 # seqlets: 793 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfx, Rfx1, Zfp42
metacluster_1/pattern_10 # seqlets: 684 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx6, Rfx7
metacluster_1/pattern_11 # seqlets: 656 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_12 # seqlets: 602 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Usf2, Tfec, Tfeb, Arntl, Mitf, Srebf1, Bhlhe40, Clock, Mlx, Arnt, Npas2, Tcfl5, Creb3l2, Max, Mycn, Myc, Bhlhe41, Xbp1, Mlxip
metacluster_1/pattern_13 # seqlets: 470 SequenceContrib ScoresHyp_Contrib Scores	Fos, Jund, Fosb, Junb, Batf, Mafa, Mafk, Bach2, Mafg, Maf, Nfe2l2, Nfe2, Maff, Bach1
metacluster_1/pattern_14 # seqlets: 395 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Pou2f1, Pou5f1, Nanog
metacluster_1/pattern_15 # seqlets: 286 SequenceContrib ScoresHyp_Contrib Scores	Mxi1
metacluster_1/pattern_16 # seqlets: 259 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_17 # seqlets: 189 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_18 # seqlets: 113 SequenceContrib ScoresHyp_Contrib Scores	Irf2, Irf1, Irf7, Prdm1, Irf9, Stat1, Stat2, Irf4, Irf3, Spib
metacluster_1/pattern_19 # seqlets: 102 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_20 # seqlets: 97 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_21 # seqlets: 94 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_22 # seqlets: 78 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_23 # seqlets: 42 SequenceContrib ScoresHyp_Contrib Scores