{
"@context": "http://schema.org",
"@type": "MediaObject",
"@id": "https://doi.org/10.5258/soton/ai3sd0199",
"url": "https://eprints.soton.ac.uk/id/eprint/468641",
"additionalType": "Video",
"name": "AI3SD Video: Event detection in single-molecule data - how to find molecular signatures without (too many) prior assumptions",
"author": {
"name": "Tim Albrecht",
"givenName": "Tim",
"familyName": "Albrecht",
"affiliation": {
"@type": "Organization",
"@id": "https://ror.org/014ja3n03",
"name": "University Hospitals Birmingham NHS Foundation Trust"
},
"@type": "Person"
},
"editor": [
{
"name": "Jeremy G. Frey",
"givenName": "Jeremy G.",
"familyName": "Frey",
"affiliation": {
"@type": "Organization",
"@id": "https://ror.org/01ryk1543",
"name": "University of Southampton"
},
"contributorType": "Editor",
"@type": "Person",
"@id": "0000-0003-0842-4302"
},
{
"name": "Samantha Kanza",
"givenName": "Samantha",
"familyName": "Kanza",
"affiliation": {
"@type": "Organization",
"@id": "https://ror.org/01ryk1543",
"name": "University of Southampton"
},
"contributorType": "Editor",
"@type": "Person",
"@id": "0000-0002-4831-9489"
},
{
"name": "Mahesan Niranjan",
"givenName": "Mahesan",
"familyName": "Niranjan",
"affiliation": {
"@type": "Organization",
"@id": "https://ror.org/01ryk1543",
"name": "University of Southampton"
},
"contributorType": "Editor",
"@type": "Person",
"@id": "0000-0001-7021-140X"
}
],
"description": "Data from single-molecule experiments, such as from current-time or conductance-distance spectroscopy or sensors, are often \"noisy\" and characterised by complex molecular behaviour. In some cases, extracting the physically relevant information may be based on supervised approaches, i.e. where labelled data are available for training. In other cases, such data are either not available or it may simply be undesirable to make a priori assumptions about the molecular characteristics, for example to prevent loss of information and expectation bias.[1,2] This may require unsupervised methods or alternative approaches that put an emphasis on \"what is not background?\", rather than \"what does an event look like?\". In my talk, I will discuss some of the approaches we have taken, including some based on image recognition networks (AlexNet, VGG16),[3,4] and show those can be used to extract not only physically meaningful characteristics, but also previously unknown molecular behaviour.
[1] M. Lemmer et al., \"Unsupervised vector-based classification of single-molecule charge transport data\", Nat. Commun. 2016, 7, art. no. 12922
[2] T. Albrecht et al., \"Deep learning for single-molecule science\", Nanotechnol. 2017, 28, 423001.
[3] A. Vladyka, T. Albrecht, \"Unsupervised classification of single-molecule data with autoencoders and transfer learning\", Machin. Learn.: Sci. Technol. 2020, 1, 035013.
[4] C. Weaver et al., \"Unsupervised Classification of Voltammetric Data with Image Recognition and Dimensionality Reduction\" (in preparation)",
"license": "https://creativecommons.org/licenses/by/4.0/legalcode",
"inLanguage": "en",
"datePublished": "2022",
"schemaVersion": "http://datacite.org/schema/kernel-4",
"publisher": {
"@type": "Organization",
"name": "University of Southampton"
},
"provider": {
"@type": "Organization",
"name": "datacite"
}
}