Dear Prachi,
I'm happy to hear from you. Certainly your expertise in machine learning,
statistics, and graph theory are helpful for the fragment-based coordinate
generation project.
Every student interested in GSoC should apply as suggested on the Open
Chemistry wiki:
http://wiki.openchemistry.org/Applying_to_GSoC
There are a few general approaches to generating molecular coordinates,
including rule-based atom-by-atom approaches, distance-geometry (review article
attached) and fragment-based databases (also attached). Right now, Open Babel
uses atom-by-atom approaches combined with a small fragment database.
https://www.dropbox.com/s/jk3s6izmwpgiir7/Mol.%20Inf.%202010%20Agrafiotis.pdf?dl=0
https://www.dropbox.com/s/nywmn8sgfehfeyx/Reviews%20in%20Computational%20Chemistry%201994%20Blaney.PDF?dl=0
Fragment databases:
https://www.dropbox.com/s/7k5wd794zs4vjko/ci4005282.pdf?dl=0
Both approaches can be optimized using OpenCL or OpenMP implementations. Both
approaches could be highly augmented with machine learning or statistical
models (e.g., Bayesian inference). Those latter points would be research
projects - more than just a summer code project.
Please take a look at the wiki guide to an application, and we look forward to
reviewing your proposal. If you have questions, please ask.
Best regards,
-Geoff
http://doodle.com/geoffhutchison
> On Mar 7, 2016, at 3:32 PM, Prachi Agrawal <prachiagrawal...@gmail.com> wrote:
>
> Dear Dr. Hutchison,
>
> I am Prachi Agrawal, a final year student of Biotechnology enrolled in a dual
> degree (B.Tech + M.Tech) program at IIT Kharagpur, accredited to be the best
> technical institute in India. I have a CGPA of 8.75/10.00 and am currently
> ranked among top 5 students of the department.
>
> I am interested to apply for your project on Fragment based coordinates
> generation listed in GSOC project ideas.
>
> I have completed a summer research internship (May-July, 2015) at the
> Department of Computing Science, University of Alberta where I worked on a
> project to forecast Blood Glucose level in T1D patients using machine
> learning. Also, I did an internship (May-July, 2015) as a Software Engineer
> at Works Applications, Japan and at Housing.com (May-June, 2014).
> I have done other projects on Machine learning and Bioinformatics as
> mentioned in my resume (attached). This semester I have taken Computational
> Phylogenetics and Molecular Evolution course and have completed courses on
> Computational and Structural Biology, Bioinformatics, Machine Learning,
> Algorithms design and analysis, Graph theory and algorithms, Software
> engineering, Programming & data structures, Probability and statistics.
> I would be thankful to you if you provide me an opportunity to work under
> your guidance on the above mentioned project. I would contribute my best
> efforts while learning invaluable skills and experience.
>
> I have included my curriculum vitae for your kind perusal.
>
> Kindly apprise me of my chances of obtaining this project. I eagerly await a
> reply from your side.
> Kind regards,
> Prachi Agrawal
> <Prachi Agrawal.pdf>
------------------------------------------------------------------------------
Transform Data into Opportunity.
Accelerate data analysis in your applications with
Intel Data Analytics Acceleration Library.
Click to learn more.
http://pubads.g.doubleclick.net/gampad/clk?id=278785111&iu=/4140
_______________________________________________
OpenBabel-Devel mailing list
OpenBabel-Devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/openbabel-devel
