# HG changeset patch # User greg # Date 1489687460 14400 # Node ID 443c8e1fd8aa17d0c2d4274b87fc4cc3c866e4e9 # Parent eda72de4717127bca65ed4485a40db6dcf6e1a9e Uploaded diff -r eda72de47171 -r 443c8e1fd8aa assembly_post_processor.xml --- a/assembly_post_processor.xml Thu Mar 16 12:54:45 2017 -0400 +++ b/assembly_post_processor.xml Thu Mar 16 14:04:20 2017 -0400 @@ -136,14 +136,14 @@ * **Transcriptome assembly fasta file** - either de novo or reference-guided transcriptome assembly fasta file selected from your history. * **Coding regions prediction method** - method for finding coding recions within transcripts. Available methods are TransDecoder[3] and ESTScan[4]. - * **Scores matrices** - Scores matrices, based on a related species, are required when ESTScan is ued to find coding regions. Details of how to create species-specific scores matrices can be found on the ESTScan website (http://estscan.sourceforge.net). Matrices of some organisms are also available to download. + * **Scores matrices** - scores matrices, based on a related species, are required when ESTScan is ued to find coding regions. Details of how to create species-specific scores matrices can be found on the ESTScan website (http://estscan.sourceforge.net). Matrices of some organisms are also available to download. **Other options** - * **Perform targeted gene assembly?** - Selecting 'Yes' enables local assembly of one or more targeted gene families in a specific scaffold. Scaffolds are defined in PlantTribes as clusters of paralogous/orthologous sequences from a specified set of proteomes[5-7]. - * **Targeted gene families** - A selected history item containing a list of targeted orthogroup identifiers corresponding to the gene family classification from a specified scaffold. Gene identifiers can be obtained from the function annotation table ("Orthogroup ID" field of *.summary file) of scaffold data installed into Galaxy via the PlantTribes Scaffolds Download Data Manager tool. + * **Perform targeted gene assembly?** - selecting 'Yes' enables local assembly of one or more targeted gene families in a specific scaffold. Scaffolds are defined in PlantTribes as clusters of paralogous/orthologous sequences from a specified set of proteomes[5-7]. + * **Targeted gene families** - select a history item containing a list of targeted orthogroup identifiers corresponding to the gene family classification from a specified scaffold. Gene identifiers can be obtained from the function annotation table ("Orthogroup ID" field of .summary file) of scaffold data installed into Galaxy via the PlantTribes Scaffolds Download Data Manager tool. * **Gene family scaffold** - one of the PlantTribes gene family scaffolds (installed into Galaxy by the PlantTribes Scaffolds Download Data Manager tool) whose orthogroups(s) are targeted for the localized assembly. - * **Protein clustering method** -gene family scaffold protein clustering method. Each PlantTribes scaffold data has up to three sets of clusters - GFam[8] (clusters of consensus domain architecture), OrthoFinder[9] (broadly defined clusters) or OrthoMCL[10] (narrowly defined clusters). You can also install your own data scaffold created using a different clustering method as long as it conforms to the PlantTribes scaffold data format. + * **Protein clustering method** - gene family scaffold protein clustering method. Each PlantTribes scaffold data has up to three sets of clusters - GFam[8] (clusters of consensus domain architecture), OrthoFinder[9] (broadly defined clusters) or OrthoMCL[10] (narrowly defined clusters). You can also install your own data scaffold created using a different clustering method as long as it conforms to the PlantTribes scaffold data format. * **Trim alignments** - trim gene family multiple sequence alignments that include scaffold backbone genes and locally assembled transcripts to remove non-conserved regions (gappy sites)[11]. The trimmed alignments are used in assigning scores to locally assembled transcripts to determine how well they compare to the backbones gene models. The default setting of 0.1 removes sites tha thave gaps in 90% of the sequences in the multiple sequence alignment. This option is restricted to the range 0.0 - 1.0. * **Strand-specific assembly?** - select 'Yes' if transcriptome library sequences were strand-specific. If 'Yes" is selected, transcripts from the minority strand (antisense) are removed. * **Remove duplicate sequences?** - select 'Yes' to remove duplicated and exact subsequences[12]. @@ -152,131 +152,120 @@ - @unpublished{None, - key = {1}, - author = {Eric Wafula}, + @article{None, + journal = {None}, + author = {1. Wafula EK}, title = {Manuscript in preparation}, year = {None}, - url = {https://github.com/dePamphilis/PlantTribes} - } + url = {https://github.com/dePamphilis/PlantTribes},} - @published{PloS one, - key = {2}, - author = {Honaas, L.A., Wafula, E.K., Wickett, N.J., Der, J.P., Zhang, Y., Edger, P.P., Altman, N.S., Pires, J.C. and Leebens-Mack, J.H.}, + @article{Honaas2016, + journal = {PloS one}, + author = {2. Honaas LA, Wafula EK, Wickett NJ, Der JP, Zhang Y, Edger PP, Altman NS, Pires JC, Leebens-Mack JH}, title = {Selecting superior de novo transcriptome assemblies: lessons learned by leveraging the best plant genome}, year = {2016}, volume = {11}, number = {1}, - pages = {e0146062} - } + pages = {e0146062},} - @published{Nature protocols, - key = {3}, - author = {Haas, B.J., Papanicolaou, A., Yassour, M., Grabherr, M., Blood, P.D., Bowden, J., Couger, M.B., Eccles, D., Li, B., Lieber, M. and MacManes, M.D.}, + @article{Haas2013, + journal = {Nature Protocols}, + author = {3. Haas BJ, Papanicolaou A, Yassour M, Grabherr M, Blood PD, Bowden J, Couger MB, Eccles D, Li B, Lieber M, MacManes MD}, title = {De novo transcript sequence reconstruction from RNA-seq using the Trinity platform for reference generation and analysis}, year = {2013}, volume = {8}, number = {8}, - pages = {1494-1512} - } + pages = {1494-1512},} - @published{ISMB, - key = {4}, - author = {Iseli C, Jongeneel CV, Bucher P.}, - title = {ESTScan: a program for detecting, evaluating, and reconstructing potential coding regions in EST sequences.}, + @article{Iseli1999, + journal = {ISMB}, + author = {4. Iseli C, Jongeneel CV, Bucher P}, + title = {ESTScan: a program for detecting, evaluating, and reconstructing potential coding regions in EST sequences}, year = {1999}, volume = {99}, - pages = {138-148} - url = {http://estscan.sourceforge.net} - } + pages = {138-148}, + url = {http://estscan.sourceforge.net},} - @published{Genome research, - key = {5}, - author = {Huang X, Madan A}, + @article{Huang1999, + journal = {Genome Research}, + author = {5. Huang X, Madan A}, title = {CAP3: A DNA sequence assembly program}, year = {1999}, volume = {9}, number = {9}, - pages = {868-877} - url = {http://seq.cs.iastate.edu/cap3.html} - } + pages = {868-877}, + url = {http://seq.cs.iastate.edu/cap3.html},} - @published{Genome Inform, - key = {6}, - author = {Eddy, S.R.}, + @article{Eddy2009, + journal = {Genome Inform}, + author = {6. Eddy SR}, title = {A new generation of homology search tools based on probabilistic inference}, year = {2009}, volume = {23}, number = {1}, - pages = {205-211} - } + pages = {205-211},} - @published{Nucleic acids research, - key = {7}, - author = {Sasidharan, R., Nepusz, T., Swarbreck, D., Huala, E. and Paccanaro, A.}, + @article{Sasidharan2012, + journal = {Nucleic Acids Research}, + author = {7. Sasidharan R, Nepusz T, Swarbreck D, Huala E, Paccanaro A}, title = {GFam: a platform for automatic annotation of gene families}, year = {2012}, - pages = {gks631} - } + pages = {gks631},} - @published{Genome research, - key = {8}, - author = {Li, L., Stoeckert, C.J. and Roos, D.S.}, + @article{Li2003, + journal = {Genome Research} + author = {8. Li L, Stoeckert CJ, Roos DS}, title = {OrthoMCL: identification of ortholog groups for eukaryotic genomes}, year = {2003}, volume = {13}, number = {9}, - pages = {2178-2189} - } + pages = {2178-2189},} - @published{Genome biology, - key = {9}, - author = {Emms, D.M. and Kelly, S.}, + @article{Emms2015, + journal = {Genome Biology} + author = {9. Emms DM, Kelly S}, title = {OrthoFinder: solving fundamental biases in whole genome comparisons dramatically improves orthogroup inference accuracy}, year = {2015}, volume = {16}, number = {1}, - pages = {157} - } + pages = {157},} - @published{Bioinformatics, - key = {10}, - author = {Capella-Gutiérrez, S., Silla-Martínez, J.M. and Gabaldón, T.}, + @article{Capella-Gutierrez2009, + journal = {Bioinformatics,}, + author = {10. Capella-Gutierrez S, Silla-Martínez JM, Gabaldón T}, title = {trimAl: a tool for automated alignment trimming in large-scale phylogenetic analyses}, year = {2009}, volume = {25}, number = {15}, - pages = {1972-1973} - } + pages = {1972-1973},} - @published{IEEE/ACM Transactions on Computational Biology and Bioinformatics, - key = {11}, - author = {Gremme, G., Steinbiss, S. and Kurtz, S.}, + @article{Gremme2013, + journal = {IEEE/ACM Transactions on Computational Biology and Bioinformatics}, + author = {11. Gremme G, Steinbiss S, Kurtz S}, title = {GenomeTools: a comprehensive software library for efficient processing of structured genome annotations}, year = {2013}, volume = {10}, number = {3}, - pages = {645-656} - } + pages = {645-656},} - @unpublished{None, - key = {12}, - author = {None}, + @article{None, + journal = {GitHub repository}, + author = {12. None}, title = {HMMER 3.1+ hmmscan search sequence(s) against a profile database}, year = {2013}, - url = {http://hmmer.org/} - } + url = {http://hmmer.org},} +