FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3187366930> ?p ?o ?g. }

• W3187366930 endingPage "758" @default.
• W3187366930 startingPage "758" @default.
• W3187366930 abstract "Methods for dimensionality reduction are showing significant contributions to knowledge generation in high-dimensional modeling scenarios throughout many disciplines. By achieving a lower dimensional representation (also called embedding), fewer computing resources are needed in downstream machine learning tasks, thus leading to a faster training time, lower complexity, and statistical flexibility. In this work, we investigate the utility of three prominent unsupervised embedding techniques (principal component analysis—PCA, uniform manifold approximation and projection—UMAP, and variational autoencoders—VAEs) for solving classification tasks in the domain of toxicology. To this end, we compare these embedding techniques against a set of molecular fingerprint-based models that do not utilize additional pre-preprocessing of features. Inspired by the success of transfer learning in several fields, we further study the performance of embedders when trained on an external dataset of chemical compounds. To gain a better understanding of their characteristics, we evaluate the embedders with different embedding dimensionalities, and with different sizes of the external dataset. Our findings show that the recently popularized UMAP approach can be utilized alongside known techniques such as PCA and VAE as a pre-compression technique in the toxicology domain. Nevertheless, the generative model of VAE shows an advantage in pre-compressing the data with respect to classification accuracy." @default.
• W3187366930 created "2021-08-16" @default.
• W3187366930 creator A5014398832 @default.
• W3187366930 creator A5014787077 @default.
• W3187366930 creator A5024306925 @default.
• W3187366930 creator A5041466600 @default.
• W3187366930 creator A5050384418 @default.
• W3187366930 creator A5075988052 @default.
• W3187366930 creator A5083476513 @default.
• W3187366930 date "2021-08-02" @default.
• W3187366930 modified "2023-10-06" @default.
• W3187366930 title "Should We Embed in Chemistry? A Comparison of Unsupervised Transfer Learning with PCA, UMAP, and VAE on Molecular Fingerprints" @default.
• W3187366930 cites W1516111018 @default.
• W3187366930 cites W1988037271 @default.
• W3187366930 cites W2046589863 @default.
• W3187366930 cites W2057069496 @default.
• W3187366930 cites W2071128523 @default.
• W3187366930 cites W2097308346 @default.
• W3187366930 cites W2110798204 @default.
• W3187366930 cites W2118527389 @default.
• W3187366930 cites W2122111042 @default.
• W3187366930 cites W2122538988 @default.
• W3187366930 cites W2165533158 @default.
• W3187366930 cites W2189911347 @default.
• W3187366930 cites W2276859037 @default.
• W3187366930 cites W2279004469 @default.
• W3187366930 cites W2518838044 @default.
• W3187366930 cites W2540970325 @default.
• W3187366930 cites W2552942965 @default.
• W3187366930 cites W2593512981 @default.
• W3187366930 cites W2620760558 @default.
• W3187366930 cites W2777416523 @default.
• W3187366930 cites W2803206732 @default.
• W3187366930 cites W2809595040 @default.
• W3187366930 cites W2886791556 @default.
• W3187366930 cites W2887381903 @default.
• W3187366930 cites W2889326414 @default.
• W3187366930 cites W2902652978 @default.
• W3187366930 cites W2911964244 @default.
• W3187366930 cites W2920795827 @default.
• W3187366930 cites W2922333374 @default.
• W3187366930 cites W2976332861 @default.
• W3187366930 cites W2981027525 @default.
• W3187366930 cites W2985382943 @default.
• W3187366930 cites W2990537780 @default.
• W3187366930 cites W2991736596 @default.
• W3187366930 cites W3006614102 @default.
• W3187366930 cites W3008588639 @default.
• W3187366930 cites W3087318293 @default.
• W3187366930 cites W3097920362 @default.
• W3187366930 cites W3101019807 @default.
• W3187366930 cites W3116202926 @default.
• W3187366930 cites W3136409400 @default.
• W3187366930 cites W3147221285 @default.
• W3187366930 cites W3159157674 @default.
• W3187366930 cites W4237591687 @default.
• W3187366930 doi "https://doi.org/10.3390/ph14080758" @default.
• W3187366930 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8400160" @default.
• W3187366930 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34451855" @default.
• W3187366930 hasPublicationYear "2021" @default.
• W3187366930 type Work @default.
• W3187366930 sameAs 3187366930 @default.
• W3187366930 citedByCount "7" @default.
• W3187366930 countsByYear W31873669302022 @default.
• W3187366930 countsByYear W31873669302023 @default.
• W3187366930 crossrefType "journal-article" @default.
• W3187366930 hasAuthorship W3187366930A5014398832 @default.
• W3187366930 hasAuthorship W3187366930A5014787077 @default.
• W3187366930 hasAuthorship W3187366930A5024306925 @default.
• W3187366930 hasAuthorship W3187366930A5041466600 @default.
• W3187366930 hasAuthorship W3187366930A5050384418 @default.
• W3187366930 hasAuthorship W3187366930A5075988052 @default.
• W3187366930 hasAuthorship W3187366930A5083476513 @default.
• W3187366930 hasBestOaLocation W31873669301 @default.
• W3187366930 hasConcept C105795698 @default.
• W3187366930 hasConcept C111030470 @default.
• W3187366930 hasConcept C11413529 @default.
• W3187366930 hasConcept C119857082 @default.
• W3187366930 hasConcept C124101348 @default.
• W3187366930 hasConcept C150899416 @default.
• W3187366930 hasConcept C151876577 @default.
• W3187366930 hasConcept C153180895 @default.
• W3187366930 hasConcept C154945302 @default.
• W3187366930 hasConcept C27438332 @default.
• W3187366930 hasConcept C2777826928 @default.
• W3187366930 hasConcept C2780598303 @default.
• W3187366930 hasConcept C33923547 @default.
• W3187366930 hasConcept C34736171 @default.
• W3187366930 hasConcept C41008148 @default.
• W3187366930 hasConcept C41608201 @default.
• W3187366930 hasConcept C57493831 @default.
• W3187366930 hasConcept C70518039 @default.
• W3187366930 hasConceptScore W3187366930C105795698 @default.
• W3187366930 hasConceptScore W3187366930C111030470 @default.
• W3187366930 hasConceptScore W3187366930C11413529 @default.
• W3187366930 hasConceptScore W3187366930C119857082 @default.
• W3187366930 hasConceptScore W3187366930C124101348 @default.
• W3187366930 hasConceptScore W3187366930C150899416 @default.

• next