Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386095640> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4386095640 abstract "Abstract The genetic code for many different proteins can be found in biological sequencing data, which offers vital insight into the genetic evolution of viruses. While machine learning approaches are becoming increasingly popular for many “Big Data” situations, they have made little progress in comprehending the nature of such data. One such area is the t-distributed Stochastic Neighbour Embedding (t-SNE), a generalpurpose approach used to represent high dimensional data in low dimensional (LD) space while preserving similarity between data points. Traditionally, the Gaussian kernel is used with t-SNE. However, since the Gaussian kernel is not data-dependent, it determines each local bandwidth based on one local point only. This makes it computationally expensive, hence limited in scalability. Moreover, it can misrepresent some structures in the data. An alternative is to use the isolation kernel, which is a data-dependent method. However, it has a single parameter to tune in computing the kernel. Although the isolation kernel yields better performance in terms of scalability and preserving the similarity in LD space, it may still not perform optimally in some cases. This paper presents a perspective on improving the performance of t-SNE and argues that kernel selection could impact this performance. We use 9 different kernels to evaluate their impact on the performance of t-SNE, using SARS-CoV-2 “spike” protein sequences. With three different embedding methods, we show that the cosine similarity kernel gives the best results and enhances the performance of t-SNE." @default.
- W4386095640 created "2023-08-24" @default.
- W4386095640 creator A5017366862 @default.
- W4386095640 creator A5026228482 @default.
- W4386095640 creator A5029639938 @default.
- W4386095640 creator A5064858842 @default.
- W4386095640 date "2023-08-22" @default.
- W4386095640 modified "2023-09-26" @default.
- W4386095640 title "Enhancing t-SNE Performance for Biological Sequencing Data through Kernel Selection" @default.
- W4386095640 cites W2013736751 @default.
- W4386095640 cites W2057491655 @default.
- W4386095640 cites W2088247287 @default.
- W4386095640 cites W2104846587 @default.
- W4386095640 cites W2740590008 @default.
- W4386095640 cites W3080795476 @default.
- W4386095640 cites W3087224093 @default.
- W4386095640 cites W3188178217 @default.
- W4386095640 cites W3196141744 @default.
- W4386095640 cites W3198971816 @default.
- W4386095640 cites W3207849004 @default.
- W4386095640 cites W3216778212 @default.
- W4386095640 cites W3217347027 @default.
- W4386095640 cites W4214918942 @default.
- W4386095640 cites W4220693339 @default.
- W4386095640 cites W4312788309 @default.
- W4386095640 cites W4318955533 @default.
- W4386095640 cites W4320024298 @default.
- W4386095640 doi "https://doi.org/10.1101/2023.08.21.554138" @default.
- W4386095640 hasPublicationYear "2023" @default.
- W4386095640 type Work @default.
- W4386095640 citedByCount "0" @default.
- W4386095640 crossrefType "posted-content" @default.
- W4386095640 hasAuthorship W4386095640A5017366862 @default.
- W4386095640 hasAuthorship W4386095640A5026228482 @default.
- W4386095640 hasAuthorship W4386095640A5029639938 @default.
- W4386095640 hasAuthorship W4386095640A5064858842 @default.
- W4386095640 hasBestOaLocation W43860956401 @default.
- W4386095640 hasConcept C114614502 @default.
- W4386095640 hasConcept C119857082 @default.
- W4386095640 hasConcept C122280245 @default.
- W4386095640 hasConcept C12267149 @default.
- W4386095640 hasConcept C124101348 @default.
- W4386095640 hasConcept C154945302 @default.
- W4386095640 hasConcept C201797286 @default.
- W4386095640 hasConcept C2775941552 @default.
- W4386095640 hasConcept C33923547 @default.
- W4386095640 hasConcept C41008148 @default.
- W4386095640 hasConcept C41608201 @default.
- W4386095640 hasConcept C48044578 @default.
- W4386095640 hasConcept C54355233 @default.
- W4386095640 hasConcept C74193536 @default.
- W4386095640 hasConcept C77088390 @default.
- W4386095640 hasConcept C80444323 @default.
- W4386095640 hasConcept C81917197 @default.
- W4386095640 hasConcept C86803240 @default.
- W4386095640 hasConcept C89423630 @default.
- W4386095640 hasConceptScore W4386095640C114614502 @default.
- W4386095640 hasConceptScore W4386095640C119857082 @default.
- W4386095640 hasConceptScore W4386095640C122280245 @default.
- W4386095640 hasConceptScore W4386095640C12267149 @default.
- W4386095640 hasConceptScore W4386095640C124101348 @default.
- W4386095640 hasConceptScore W4386095640C154945302 @default.
- W4386095640 hasConceptScore W4386095640C201797286 @default.
- W4386095640 hasConceptScore W4386095640C2775941552 @default.
- W4386095640 hasConceptScore W4386095640C33923547 @default.
- W4386095640 hasConceptScore W4386095640C41008148 @default.
- W4386095640 hasConceptScore W4386095640C41608201 @default.
- W4386095640 hasConceptScore W4386095640C48044578 @default.
- W4386095640 hasConceptScore W4386095640C54355233 @default.
- W4386095640 hasConceptScore W4386095640C74193536 @default.
- W4386095640 hasConceptScore W4386095640C77088390 @default.
- W4386095640 hasConceptScore W4386095640C80444323 @default.
- W4386095640 hasConceptScore W4386095640C81917197 @default.
- W4386095640 hasConceptScore W4386095640C86803240 @default.
- W4386095640 hasConceptScore W4386095640C89423630 @default.
- W4386095640 hasLocation W43860956401 @default.
- W4386095640 hasOpenAccess W4386095640 @default.
- W4386095640 hasPrimaryLocation W43860956401 @default.
- W4386095640 hasRelatedWork W1535023044 @default.
- W4386095640 hasRelatedWork W1932525473 @default.
- W4386095640 hasRelatedWork W1996278890 @default.
- W4386095640 hasRelatedWork W2092483655 @default.
- W4386095640 hasRelatedWork W2094900960 @default.
- W4386095640 hasRelatedWork W2103553152 @default.
- W4386095640 hasRelatedWork W2140758628 @default.
- W4386095640 hasRelatedWork W4207080266 @default.
- W4386095640 hasRelatedWork W4285600494 @default.
- W4386095640 hasRelatedWork W4386159866 @default.
- W4386095640 isParatext "false" @default.
- W4386095640 isRetracted "false" @default.
- W4386095640 workType "article" @default.