From b4011e5a30363696abcda95e51e0ccc617a70c34 Mon Sep 17 00:00:00 2001 From: "Documenter.jl" Date: Mon, 29 Jul 2024 20:05:57 +0000 Subject: [PATCH] build based on c388afd --- dev/.documenter-siteinfo.json | 2 +- dev/api/index.html | 2 +- dev/features/index.html | 2 +- dev/index.html | 2 +- dev/iodocs/index.html | 2 +- dev/naivefinder/index.html | 2 +- dev/roadmap/index.html | 2 +- dev/simplecodingrule/index.html | 2 +- 8 files changed, 8 insertions(+), 8 deletions(-) diff --git a/dev/.documenter-siteinfo.json b/dev/.documenter-siteinfo.json index 74aea1a..6b7197e 100644 --- a/dev/.documenter-siteinfo.json +++ b/dev/.documenter-siteinfo.json @@ -1 +1 @@ -{"documenter":{"julia_version":"1.10.4","generation_timestamp":"2024-07-29T19:55:44","documenter_version":"1.5.0"}} \ No newline at end of file +{"documenter":{"julia_version":"1.10.4","generation_timestamp":"2024-07-29T20:05:54","documenter_version":"1.5.0"}} \ No newline at end of file diff --git a/dev/api/index.html b/dev/api/index.html index 3b4157b..c653eb7 100644 --- a/dev/api/index.html +++ b/dev/api/index.html @@ -44,4 +44,4 @@ open(filename, "w") do file write_orfs_fna(seq, file, NaiveFinder()) endsource
GeneFinder.write_orfs_gff — Method
write_orfs_gff(input::NucleicSeqOrView{DNAAlphabet{N}}, output::Union{IOStream, IOBuffer}, finder::F; kwargs...)
-write_orfs_gff(input::NucleicSeqOrView{DNAAlphabet{N}}, output::String, finder::F; kwargs...)

Write GFF data to a file.

Arguments

  • input: The input DNA sequence NucSeq or a view.
  • output: The otput format, it can be a file (String) or a buffer (IOStream or `IOBuffer)
  • finder: The algorithm used to find ORFs. It can be either NaiveFinder() or NaiveFinderScored().

Keywords

  • code::GeneticCode=BioSequences.standard_genetic_code: The genetic code by which codons will be translated. See BioSequences.ncbi_trans_table for more info.
  • alternative_start::Bool=false: If true will pass the extended start codons to search. This will increase 3x the exec. time.
  • minlen::Int64=6: Length of the allowed ORF. Default value allow aa"M*" a posible encoding protein from the resulting ORFs.
source
+write_orfs_gff(input::NucleicSeqOrView{DNAAlphabet{N}}, output::String, finder::F; kwargs...)

Write GFF data to a file.

Arguments

Keywords

source diff --git a/dev/features/index.html b/dev/features/index.html index e9f8fb7..2e06985 100644 --- a/dev/features/index.html +++ b/dev/features/index.html @@ -117,4 +117,4 @@ axislegend(ax) -f

What this plot shows is that the ORFs in the lambda genome have a higher scores than random sequences of the same length. The score is a measure of how likely a sequence given the coding model is compared to the non-coding model. In other words, the higher the score the more likely the sequence is coding. So, the plot shows that the ORFs in the lambda genome are more likely to be coding regions than random sequences. It also shows that the longer the ORF the higher the score, which is expected since longer ORFs are more likely to be coding regions than shorter ones.

+f

What this plot shows is that the ORFs in the lambda genome have a higher scores than random sequences of the same length. The score is a measure of how likely a sequence given the coding model is compared to the non-coding model. In other words, the higher the score the more likely the sequence is coding. So, the plot shows that the ORFs in the lambda genome are more likely to be coding regions than random sequences. It also shows that the longer the ORF the higher the score, which is expected since longer ORFs are more likely to be coding regions than shorter ones.

diff --git a/dev/index.html b/dev/index.html index f0ccfe4..b169e56 100644 --- a/dev/index.html +++ b/dev/index.html @@ -41,4 +41,4 @@ version = {v0.3.0}, year = {2024}, month = {04} -} +} diff --git a/dev/iodocs/index.html b/dev/iodocs/index.html index d7066cc..9543352 100644 --- a/dev/iodocs/index.html +++ b/dev/iodocs/index.html @@ -31,4 +31,4 @@ >seq id=11 start=581 stop=601 strand=+ frame=2 features=[] ATGTGTCCAACGGCAGCCTGA >seq id=12 start=695 stop=706 strand=+ frame=2 features=[] -ATGCAACCCTGA

This could also be done to writting a FASTA file with the nucleotide sequences of the ORFs using the write_orfs_fna function. Similarly for the BED and GFF files using the write_orfs_bed and write_orfs_gff functions respectively.

+ATGCAACCCTGA

This could also be done to writting a FASTA file with the nucleotide sequences of the ORFs using the write_orfs_fna function. Similarly for the BED and GFF files using the write_orfs_bed and write_orfs_gff functions respectively.

diff --git a/dev/naivefinder/index.html b/dev/naivefinder/index.html index bbe0459..8e88c4f 100644 --- a/dev/naivefinder/index.html +++ b/dev/naivefinder/index.html @@ -57,4 +57,4 @@ MSPHKAM* M* MCPTAA* - MQP* + MQP* diff --git a/dev/roadmap/index.html b/dev/roadmap/index.html index f79dc61..eb0cb0f 100644 --- a/dev/roadmap/index.html +++ b/dev/roadmap/index.html @@ -1,2 +1,2 @@ -- · GeneFinder.jl
GitHub

Roadmap

Coding genes (CDS - ORFs)

  • ☒ Finding ORFs
  • ☐ EasyGene
  • ☐ GLIMMER
  • ☐ Prodigal - Pyrodigal
  • ☐ PHANOTATE
  • ☐ k-mer based gene finders (?)
  • ☐ Augustus (?)

Non-coding genes (RNA)

  • ☐ Infernal
  • ☐ tRNAscan

Other features

  • ☐ parallelism SIMD ?
  • ☐ memory management (?)
  • ☐ incorporate Ribosime Binding Sites (RBS)
  • ☐ incorporate Programmed Reading Frame Shifting (PRFS)
  • ☐ specialized types
    • ☒ Gene
    • ☒ ORF
    • ☒ Codon
    • ☒ CDS
    • ☐ EukaryoticGene (?)
    • ☐ ProkaryoticGene (?)
    • ☐ Intron
    • ☐ Exon
    • ☐ GFF –\> See other packages
    • ☐ FASTX –\> See I/O in other packages

Compatibilities

Must interact with or extend:

  • GenomicAnnotations.jl
  • BioSequences.jl
  • SequenceVariation.jl
  • GenomicFeatures.jl
  • FASTX.jl
  • Kmers.jl
  • Graphs.jl
+- · GeneFinder.jl
GitHub

Roadmap

Coding genes (CDS - ORFs)

  • ☒ Finding ORFs
  • ☐ EasyGene
  • ☐ GLIMMER
  • ☐ Prodigal - Pyrodigal
  • ☐ PHANOTATE
  • ☐ k-mer based gene finders (?)
  • ☐ Augustus (?)

Non-coding genes (RNA)

  • ☐ Infernal
  • ☐ tRNAscan

Other features

  • ☐ parallelism SIMD ?
  • ☐ memory management (?)
  • ☐ incorporate Ribosime Binding Sites (RBS)
  • ☐ incorporate Programmed Reading Frame Shifting (PRFS)
  • ☐ specialized types
    • ☒ Gene
    • ☒ ORF
    • ☒ Codon
    • ☒ CDS
    • ☐ EukaryoticGene (?)
    • ☐ ProkaryoticGene (?)
    • ☐ Intron
    • ☐ Exon
    • ☐ GFF –\> See other packages
    • ☐ FASTX –\> See I/O in other packages

Compatibilities

Must interact with or extend:

  • GenomicAnnotations.jl
  • BioSequences.jl
  • SequenceVariation.jl
  • GenomicFeatures.jl
  • FASTX.jl
  • Kmers.jl
  • Graphs.jl
diff --git a/dev/simplecodingrule/index.html b/dev/simplecodingrule/index.html index 4caf7f2..3afb072 100644 --- a/dev/simplecodingrule/index.html +++ b/dev/simplecodingrule/index.html @@ -94,4 +94,4 @@ ORF{NaiveFinder}(4540:4644, '+', 1) ORF{NaiveFinder}(4690:4866, '+', 1) ORF{NaiveFinder}(4741:4866, '+', 1) - ORF{NaiveFinder}(4744:4866, '+', 1) + ORF{NaiveFinder}(4744:4866, '+', 1)