################
# Matlab files #
################

# Expression data:
## Reference genome counts matrix
counts.mat
- counts: 33471 by 60
## Personal genomes counts matrix
personal_counts.mat
- counts_per: 33374 by 60
#### note: no ERCCs in this matrix, hence different dimensions

# Phenotype data:
pData.mat
- pData: 60 by 10
- describes the columns in the counts matrices
- age, sex, lane/batch, individual, and all versions of sample IDs that were used (based on library preps and armadillo labels)

# Gene data:
attr.mat
- attr: 33471 by 11
- gene IDs and their locations on the scaffolds
- ordered same way as in counts matrix
- human homologs are in the name column
- genes: 33374
- ERCC spikeins: 97

# GO:
GO.arm.mat
# GO terms and genes as text files
GO.arm.genes
GO.arm.terms

# Homologs: 
homologs.mat
- homologs : 11012 by 5 
- Mouse genes name and entrez ID, human gene name and entrez ID, and armadillo ensemblID




##################
# R binary files #
##################

# Expression and gene data:
## Reference genome counts
counts.Rdata
- counts_exp : 33471 by 60
- pData : 60 by 10
- attr: 33471 by 11

## Personal genomes counts
personal_counts.Rdata
- counts_per : 33374 by 60

# GO:
GO.arm.Rdata
- GO.arm :  2014800 by 4
- GO.arm.nonIEA : 12828 by 21421
- genes.id: 12828 by 2

# Homologs:
homologs.Rdata
- genes.id2ids : 11012 by 5
- Mouse genes name and entrez ID, human gene name and entrez ID, and armadillo ensemblID