Exploring protein folding space with neural network guided simulations

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60461373%3A22330%2F20%3A43920919" target="_blank" >RIV/60461373:22330/20:43920919 - isvavai.cz</a>
Alternative codes found
RIV/00216224:14610/20:00114384
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Exploring protein folding space with neural network guided simulations
Original language description
We introduce a novel computationally feasible method of exploring protein folding spaces, while working without any a priori knowledge of the space, hence overcoming a drawback of previous methods. Since our approach uses random landmark structures without any guarantee of chemical or biological meaning, we use neural networks to extract meaningful features to guide the simulation. The method is described in detail, and its implementation is publicly available. We demonstrate the feasibility of this approach by accelerating the folding of the Trp-Cage miniprotein 20 times.
Czech name
—
Czech description
—

Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10602 - Biology (theoretical, mathematical, thermal, cryobiology, biological rhythm), Evolutionary biology

Project
<a href="/en/project/GA19-16857S" target="_blank" >GA19-16857S: Correction of molecular mechanics potentials of drug-like molecules by property map</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)