# Parameters
data_name = "BRN;SNSR_MTR_CRTX;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_71-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_71-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 18:56:25,668 [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- Sensorimotor Cortex
Cell Group	Neural Cells and Tissues
Experiment Name	ATAC
Experiment Group	Casellas Lab

Metric	Value
auPRC	0.5747
Calibrated Recall at 50% FDR	0.258
Number of Positive Examples in Test Data	106022
Number of Negative Examples in Test Data	7964829
Imbalance Ratio in Test Data	0.0131
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 3573 SequenceContrib ScoresHyp_Contrib Scores	Egr2, Egr3, Zbtb17, Zfp281, Egr1, Gli3
metacluster_1/pattern_1 # seqlets: 2922 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp3, Sp2, Sp1, Klf3, E2f4, Klf7, Klf8, Klf12, Klf6, E2f1, Klf1, Klf4, Sp5, Klf5, Klf15, Wt1, Maz, Zfp740, E2f7, Zbtb1
metacluster_1/pattern_2 # seqlets: 2851 SequenceContrib ScoresHyp_Contrib Scores	Mef2a, Mef2c, Mef2d
metacluster_1/pattern_3 # seqlets: 2299 SequenceContrib ScoresHyp_Contrib Scores	Fosl2, Batf, Fos, Jdp2, Jund, Fosb, Junb, Fosl1, Atf3, Jun, Bach2, Nfe2, Nfe2l2, Bach1, Mafa, Mafk
metacluster_1/pattern_4 # seqlets: 1770 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_5 # seqlets: 1658 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx1, Rfx4, Rfx6, Rfx7
metacluster_1/pattern_6 # seqlets: 1585 SequenceContrib ScoresHyp_Contrib Scores	Neurod2, Neurod1, Neurog2, Atoh1, Olig2, Tcf21, Bhlhe22, Lyl1, Msc, Neurog1, Bhlha15, Msgn1, Tal1, Twist1, Ascl1, Tcf12, Twist2, Ptf1a, Myog, Ascl2, Snai1, Tfap4
metacluster_1/pattern_7 # seqlets: 1509 SequenceContrib ScoresHyp_Contrib Scores	Nrf1, Zfx
metacluster_1/pattern_8 # seqlets: 1355 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_9 # seqlets: 1263 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfic, Nfia
metacluster_1/pattern_10 # seqlets: 1126 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Creb1, Creb5, Atf1, Crem, Nfil3, Mafb, Tef, Dbp, Rxrb, Cebpb, Gmeb2
metacluster_1/pattern_11 # seqlets: 929 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Fli1, Ets1, Elk4, Elk1, Elf1, Erg, Elk3, Etv4, Etv2, Etv1, Etv5, Fev, Etv3, XP_911724.4, Etv6, Ehf, Elf3, Elf4, Elf5, Spi1, Elf2, Spdef, Irf8, Spib
metacluster_1/pattern_12 # seqlets: 552 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_1/pattern_13 # seqlets: 531 SequenceContrib ScoresHyp_Contrib Scores	Hlf
metacluster_1/pattern_14 # seqlets: 500 SequenceContrib ScoresHyp_Contrib Scores	Yy1, Taf1, Zfp42
metacluster_1/pattern_15 # seqlets: 473 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Usf2, Tfeb, Tfe3, Tfec, Arntl, Mitf, Bhlhe40, Srebf1, Arnt, Mlx, Clock, Srebf2, Npas2, Tcfl5, Mycn, Bhlhe41, Max, Creb3l2, Myc
metacluster_1/pattern_16 # seqlets: 471 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Pou2f1, Pou5f1
metacluster_1/pattern_17 # seqlets: 178 SequenceContrib ScoresHyp_Contrib Scores	Sox9, Sox2, Sox3, Sox10, Sox6, Sox4, Sox17
metacluster_1/pattern_18 # seqlets: 57 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33