Grant: Research Tools and Instruments - Category 1 (<$150,000)
McMaster University
$146,325.00
Computational resources to model biochemical binding affinities and reaction networks
EF 2010-11
Résumé
In the last decade, computational chemistry has evolved from a tool primarily used by specialists to a commodity used across chemistry and related disciplines. Computational chemistry is in danger of regressing, however, as today's software becomes increasingly ill-suited to modern computer hardware and experimental chemists shift their interests towards complex chemical phenomena that are not amenable to straightforward computational modeling. Machine learning methods overcome both issues. Machine learning algorithms move beyond the ""one calculation, one number"" paradigm of conventional computational chemistry and instead synthesize chemical knowledge from the results of many different computations and/or experiments. This allows one to address complex chemical phenomena like protein binding affinities, small-molecule inhibition of microRNA, and combustion.
This proposal is for a computer cluster that will be used to develop new machine learning software for chemical and biochemical problems. Developing models of chemical phenomena from machine learning is inherently computationally demanding: thousands of high-level computations are sometimes required. In addition, because machine-learning methods for chemistry are in their infancy, it is very difficult to anticipate which types of computational data will be most useful for building a model ahead of time; trial and error is required. The requested equipment will provide the resources needed to design, implement, test, and refine machine learning methods for chemical problems.
Programme
Research Tools and Instruments - Category 1 (<$150,000)
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
407072-2011
Name nom
Ayers, Paul
Department département
Chemistry & Chemical Biology
Organization id
27
Institution établissement
McMaster University
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2010
Competition year année de concours
2011
Award amount
146325
Program id
EQPEQ
Program name en
Research Tools and Instruments - Category 1 (<$150,000)
Program name fr
Outils et instruments de recherche - catégorie 1 (<150 000$)
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
1504
Committee name en
Chemistry
Committee name fr
Chimie
Area of application code
405
Area of application group en
Environment
Area of application group fr
Environnement
Area of application en
Modelling and mathematical simulation of natural processes
Area of application fr
Modélisation et simulation mathématique des processus naturels
Research subject code
3156
Research subject group en
Theoretical physics and chemistry
Research subject group fr
Physique et chimie théoriques
Research subject en
Quantum and/or computational chemistry
Research subject fr
Chimie quantique ou par modélisation numérique
Partie
1
Nb partie
1
Application title
Computational resources to model biochemical binding affinities and reaction networks
Keyword
NSERC
Application summary
In the last decade, computational chemistry has evolved from a tool primarily used by specialists to a commodity used across chemistry and related disciplines. Computational chemistry is in danger of regressing, however, as today's software becomes increasingly ill-suited to modern computer hardware and experimental chemists shift their interests towards complex chemical phenomena that are not amenable to straightforward computational modeling. Machine learning methods overcome both issues. Machine learning algorithms move beyond the ""one calculation, one number"" paradigm of conventional computational chemistry and instead synthesize chemical knowledge from the results of many different computations and/or experiments. This allows one to address complex chemical phenomena like protein binding affinities, small-molecule inhibition of microRNA, and combustion.
This proposal is for a computer cluster that will be used to develop new machine learning software for chemical and biochemical problems. Developing models of chemical phenomena from machine learning is inherently computationally demanding: thousands of high-level computations are sometimes required. In addition, because machine-learning methods for chemistry are in their infancy, it is very difficult to anticipate which types of computational data will be most useful for building a model ahead of time; trial and error is required. The requested equipment will provide the resources needed to design, implement, test, and refine machine learning methods for chemical problems.