Version 6.1 by emacasali on 2023/01/11 11:03
Hide last authors
emacasali 1.1 1 (% class="jumbotron" %)
2 (((
3 (% class="container" %)
4 (((
emacasali 5.1 5 = MEDIUM - Machine lEarning Drug dIscovery throUgh dynaMics =
emacasali 1.1 6
emacasali 6.1 7 = =
emacasali 5.1 8
emacasali 6.1 9 Giorgio Colombo Group (UNIPV)
emacasali 1.1 10 )))
11 )))
12
13 (% class="row" %)
14 (((
15 (% class="col-xs-12 col-sm-8" %)
16 (((
emacasali 6.1 17 = Why this tool is useful? =
emacasali 1.1 18
emacasali 6.1 19 The prediction of the best ligand for a specific protein could be a huge challenge using the classical approaches like molecular docking and stabilisation energy calculations.
emacasali 1.1 20
emacasali 6.1 21 Here we report on a fast and solid workflow which starts from our DF-matrix method to analyse how the protein globally behaves in the presence of a ligand. Machine Learning (ML) trains a Convolutional Neural Network (CNN) model directly on the pixel images of DF: train is preformed using a known ligand and the different behaviour of the protein is evaluated in the presence and in absence of it.
22
23 With the so trained model further predictions can be performed using different ligands.
24
emacasali 1.1 25 = Who has access? =
26
27 Describe the audience of this collab.
28 )))
29
30
31 (% class="col-xs-12 col-sm-4" %)
32 (((
33 {{box title="**Contents**"}}
34 {{toc/}}
35 {{/box}}
36
37
38 )))
39 )))