# Parameters
data_name = "BL_CN_PHT_RCPTR;A;GEO"
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_153-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_153-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 19:14:25,428 [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	blue cone photoreceptors/NrlKO
Cell Group	Neural Cells and Tissues
Experiment Name	ATAC
Experiment Group	GEO

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	107979	81948	15.8234	33944189	4510005	0.1329	4119486	0.1214	11144629	0.3285
rep2	107979	81948	18.2086	33564826	7560932	0.2254	5691806	0.1697	12009097	0.358

Metric	Value
auPRC	0.6652
Calibrated Recall at 50% FDR	0.206
Number of Positive Examples in Test Data	89699
Number of Negative Examples in Test Data	7981152
Imbalance Ratio in Test Data	0.0111
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 6327 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 3566 SequenceContrib ScoresHyp_Contrib Scores	Crx, Otx2, Otx1, Obox6, Pax7, Dmbx1, Obox1
metacluster_1/pattern_2 # seqlets: 2775 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Klf3, Sp1, Sp4, Klf6, E2f4, Klf4, Egr1, Klf7, Klf5, Zbtb17, Sp5, Klf8, Klf12, Egr2, Wt1, Klf1, Zfp281, Maz, E2f1, Klf15, Srebf2, Egr3, Zfp740, Sall4
metacluster_1/pattern_3 # seqlets: 1269 SequenceContrib ScoresHyp_Contrib Scores	Nrf1, Zfx
metacluster_1/pattern_4 # seqlets: 1222 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Foxi1, Nfyc, Nfya, Pbx3
metacluster_1/pattern_5 # seqlets: 960 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Fli1, Elk4, Elk1, Ets1, Elf1, Erg, Elk3, Etv4, Etv1, Fev, Etv5, Etv6, Etv2, Ehf, Etv3, XP_911724.4, Elf5, Elf4, Elf2, Elf3, Spdef, Spi1
metacluster_1/pattern_6 # seqlets: 707 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_7 # seqlets: 651 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf7, Jdp2, Atf2, Creb5, Crem, Mafb, Atf1, Atf3, Nfil3, Tef, Fosl1, Fosl2, Jun, Dbp, Hlf, Gmeb2, Cebpg, Tfe3, Cebpb, Cebpa, Cebpd, Gmeb1, Rorb, Junb, Atf4
metacluster_1/pattern_8 # seqlets: 647 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Rfx1, Mxi1
metacluster_1/pattern_9 # seqlets: 561 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Usf2, Tfeb, Arntl, Tfec, Mitf, Clock, Bhlhe40, Srebf1, Arnt, Mlx, Npas2, Tcfl5, Creb3l2, Mycn, Max, Bhlhe41, Myc, Xbp1, Mlxip
metacluster_1/pattern_10 # seqlets: 496 SequenceContrib ScoresHyp_Contrib Scores	Ptf1a, Rela, Bcl6, Ets2, E2f7, E2f3
metacluster_1/pattern_11 # seqlets: 418 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_12 # seqlets: 336 SequenceContrib ScoresHyp_Contrib Scores	Neurod1, Neurod2, Olig2, Neurog2, Atoh1, Msgn1, Msc, Bhlhe22, Neurog1, Tcf21, Bhlha15, Twist2, Ascl2, Ascl1, Lyl1
metacluster_1/pattern_13 # seqlets: 236 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_14 # seqlets: 158 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_15 # seqlets: 121 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_16 # seqlets: 119 SequenceContrib ScoresHyp_Contrib Scores	Jund, Fos, Fosb, Batf, Bach2, Bach1, Nfe2l2, Mafk, Mafa, Nfe2, Mafg
metacluster_1/pattern_17 # seqlets: 85 SequenceContrib ScoresHyp_Contrib Scores	Rorc, Pparg, Rora, Nr1d2
metacluster_1/pattern_18 # seqlets: 84 SequenceContrib ScoresHyp_Contrib Scores	Lhx2, Phox2b, En2, Nkx1-2, Phox2a, Vsx2, Lhx8, Gbx1, Hoxd3, Evx2, Isx, Nkx1-1, Prrx2, Gbx2, Alx3, Rax, Emx2, Pou1f1, Lhx9, Prrx1, Lhx6, Rhox6, Otp, Pdx1, Evx1, Gsx2, Hoxa2, Lhx4, Prop1, Dlx3, Uncx, En1, Esx1, Shox2, Msx3, Arx, Barhl1, Lhx3, Vax2, Dlx5, Vsx1, Vax1, Lbx2, Alx1, Pax6, Hoxc6, Msx1, Pou6f1, Hoxa1, Pax4, Lmx1b, Hoxa3, Barx1, Mnx1, Hoxb3, Hoxd1, Alx4, Nobox, Hoxa5, Meox2, Msx2, Noto, Meox1, Dbx2, Dlx4, Pou2f1, Hoxb4, Sebox, Hoxb5, Isl1, Esr2, Hoxc5, Pou2f3, Dlx1, Lhx5, Nr2f6, Hlx
metacluster_1/pattern_19 # seqlets: 78 SequenceContrib ScoresHyp_Contrib Scores	Irf2, Irf1, Prdm1, Irf7, Stat1, Irf8, Stat2, Irf9, Irf4, Irf3, Spib, Batf3
metacluster_1/pattern_20 # seqlets: 54 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_21 # seqlets: 52 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_22 # seqlets: 44 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_23 # seqlets: 39 SequenceContrib ScoresHyp_Contrib Scores