# Parameters
data_name = "wES;FaceP;E11.5;D;En"
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_261-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_261-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 19:39:07,419 [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	embryonic facial prominence(e11.5)
Cell Group	ES cells and embryonic tissues
Experiment Name	DHS
Experiment Group	ENCODE

Metric	Value
auPRC	0.6746
Calibrated Recall at 50% FDR	0.184
Number of Positive Examples in Test Data	110256
Number of Negative Examples in Test Data	7960595
Imbalance Ratio in Test Data	0.0137
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 5039 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 3662 SequenceContrib ScoresHyp_Contrib Scores	Sp1, Sp3, Sp2, Sp4, Zbtb17, Klf3, Sp5, Klf4, Zfp281, Klf5, Klf7, Egr1, Egr2, E2f4, Klf8, Klf6, Klf12, Wt1, E2f1, Maz, Klf15, Klf1, Srebf2, Zfp740, Sall4
metacluster_1/pattern_2 # seqlets: 1942 SequenceContrib ScoresHyp_Contrib Scores	Twist1, Tcf21, Bhlha15, Msc, Olig2, Neurog1, Lhx3, Lhx1, Lhx5, Bhlhe22, Atoh1, Tfap4, Neurod1, Tal1, Tcf12, Twist2, Tcf3, Tcf4
metacluster_1/pattern_3 # seqlets: 1878 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_1/pattern_4 # seqlets: 1810 SequenceContrib ScoresHyp_Contrib Scores	Alx3, Lmx1b, Prrx2, Prop1, Lhx4, Arid3a, Uncx, Arx, Alx1, En1, Tlx2, Dbx1, Alx4, Shox2, Pax6, Dbx2, Vsx1, Hoxc6, Pax7, Lmx1a, Lhx2, Gbx2
metacluster_1/pattern_5 # seqlets: 1790 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Gabpa, Fli1, Elk4, Elk1, Etv5, Etv4, Etv2, Elk3, Fev, Etv6, Etv1, Etv3, Elf2, XP_911724.4, Spi1, Elf1, Ehf, Elf4, Elf5, Elf3, Spib, Spdef, Spic, Irf8, Irf4
metacluster_1/pattern_6 # seqlets: 1285 SequenceContrib ScoresHyp_Contrib Scores	Sox3, Sox4, Sox9, Sox2, Sox6, Sox17, Foxd1
metacluster_1/pattern_7 # seqlets: 1058 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx1, Rfx2, Rfx4, Rfx6, Rfx7
metacluster_1/pattern_8 # seqlets: 1016 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_9 # seqlets: 951 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_10 # seqlets: 859 SequenceContrib ScoresHyp_Contrib Scores	Mxi1
metacluster_1/pattern_11 # seqlets: 691 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Creb1, Jdp2, Creb5, Atf1, Atf3, Crem, Mafb, Fosl2, Fosl1, Nfil3, Jun, Hlf, Tef, Dbp, Creb3l2, Usf1, Tfe3, Srebf1, Cebpb, Rxrb, Cebpa, Tfec, Cebpg
metacluster_1/pattern_12 # seqlets: 607 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead2, Tead1
metacluster_1/pattern_13 # seqlets: 516 SequenceContrib ScoresHyp_Contrib Scores	Tfeb, Mitf, Usf2, Bhlhe40, Arntl, Mlx, Arnt, Clock, Npas2, Tcfl5, Bhlhe41, Xbp1, Mlxip, Mycn
metacluster_1/pattern_14 # seqlets: 365 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_1/pattern_15 # seqlets: 355 SequenceContrib ScoresHyp_Contrib Scores	Yy1, Taf1, Zfx, Zfp42
metacluster_1/pattern_16 # seqlets: 309 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_17 # seqlets: 213 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_1/pattern_18 # seqlets: 212 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_19 # seqlets: 164 SequenceContrib ScoresHyp_Contrib Scores	Tfap2c, Tfap2a, Tfap2b, Tfap2e, Prdm16
metacluster_1/pattern_20 # seqlets: 96 SequenceContrib ScoresHyp_Contrib Scores