[Bioperl-l] Proposal for AI methods in Bioperl

[Matthew Betts]

There is also a perl library for genetic programming:

http://perlgp.org/



> Date: Wed, 12 Oct 2005 17:59:57 +0100
> From: Paulo Almeida <palmeida at igc.gulbenkian.pt>
> Subject: Re: [Bioperl-l] Proposal for AI methods in Bioperl
> To: bioperl-l at portal.open-bio.org
> Message-ID: <200510121759.58082.palmeida at igc.gulbenkian.pt>
> Content-Type: text/plain;  charset="iso-8859-1"
> 
> I have used GALib in the past, a C++ library for Genetic Algorithms, which 
> could give you some ideas.
> 
> It is located here: http://lancet.mit.edu/ga/
> There is an overview here: http://lancet.mit.edu/galib-2.4/Overview.html
> 
> -Paulo
> 
> On Wednesday 12 October 2005 17:09, Hilmar Lapp wrote:
> > You might want to look at the WEKA project for some design guidance and
> > inspiration. The home page is at http://www.cs.waikato.ac.nz/ml/weka/
> > and the API is documented at http://weka.sourceforge.net/doc/
> >
> > Something that's equally well structured I think could be a generally
> > useful contribution. I'd expect that to use a lot of compiled code
> > though, number crunching just isn't what perl is best at.
> >
> > Also, it may be worth checking out the dp package in Biojava for
> > dynamic programming algorithms.
> >
> >  -hilmar
> >
> > On Oct 12, 2005, at 12:05 AM, Mauricio Herrera Cuadra wrote:
> > > Hi all,
> > >
> > > As far as I know, there aren't any modules in Bioperl providing access
> > > to Artificial Intelligence (AI) methods such as neural networks,
> > > genetic algorithms, cellular automata, among others.
> > >
> > > At the moment, I'm interested in developing some interface for using
> > > genetic algorithms. By using the interface, users could access these
> > > methods for generating optimized schemes based on sets of homologous
> > > sequences. I think that the generated results could be a nice
> > > alternative for motif/pattern searching in diverse novel sequences
> > > (instead of regular expressions, HMM's and other methods). What do you
> > > think?
> > >
> > > Any guidance would be really helpful. If you know of any external
> > > application that you can recomend for using with the interface, a
> > > suggested location in the code tree, etc., please let me know. I've
> > > thought of something like a Bio::AI family that can be included in the
> > > bioperl-live or maybe as a bioperl-ai package. I'm open to all kind of
> > > thoughts. Thanks in advance.
> > >
> > > Regards,
> > > Mauricio.
> > > --
> > > MAURICIO HERRERA CUADRA
> > > arareko at campus.iztacala.unam.mx
> > > Laboratorio de Genética
> > > Unidad de Morfofisiología y Función
> > > Facultad de Estudios Superiores Iztacala, UNAM
> > >
> > > _______________________________________________
> > > Bioperl-l mailing list
> > > Bioperl-l at portal.open-bio.org
> > > http://portal.open-bio.org/mailman/listinfo/bioperl-l
> 
> -- 
> Paulo Almeida
> Tel: +351 21 4464635, Fax: +351 21 4407970
> Instituto Gulbenkian de Ciência
> Rua da Quinta Grande, 6
> P-2780-156 Oeiras
> Portugal
> http://www.igc.gulbenkian.pt