FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3018074893> ?p ?o ?g. }

• W3018074893 endingPage "78752" @default.
• W3018074893 startingPage "78737" @default.
• W3018074893 abstract "Computational approaches for synthesizing new chemical compounds have resulted in a major explosion of chemical data in the field of drug discovery. The quantitative structure-activity relationship (QSAR) is a widely used classification and regression method used to represent the relationship between a chemical structure and its activities. This research focuses on the effect of dimensionality-reduction techniques on a high-dimensional QSAR dataset. Because of the multi-dimensional nature of QSAR, dimensionality-reduction techniques have become an integral part of its modeling process. Principal component analysis (PCA) is a feature extraction technique with several applications in exploratory data analysis, visualization and dimensionality reduction. However, linear PCA is inadequate to handle the complex structure of QSAR data. In light of the wide array of current feature-extraction techniques, we perform a comparative empirical study to investigate five feature-extraction techniques: PCA, kernel PCA, deep generalized autoencoder (dGAE), Gaussian random projection (GRP), and sparse random projection (SRP). The experiments are performed on a high-dimensional QSAR dataset, which comprises 6394 features. The transformed low-dimensional dataset is inputted into a deep learning classification model to predict a QSAR biological activity. Three approaches are adopted to validate and measure the proposed techniques: (i) comparing the performance of the classification models, (ii) visualizing the relationship (correlation) between features in the low-dimension Euclidean space, and (iii) validating the proposed techniques using an external dataset. To the best of our knowledge, this study is the first to investigate and compare the aforementioned feature-extraction techniques in QSAR modeling context. The results obtained provide invaluable insights regarding the behavior of different techniques with both negative and positive classes. With linear PCA as a baseline, we prove that the investigated techniques substantially outperform the baseline in multiple accuracy measures and demonstrate useful ways of extracting significant features." @default.
• W3018074893 created "2020-05-01" @default.
• W3018074893 creator A5041926767 @default.
• W3018074893 creator A5068512068 @default.
• W3018074893 creator A5080950722 @default.
• W3018074893 date "2020-01-01" @default.
• W3018074893 modified "2023-10-04" @default.
• W3018074893 title "Feature Extraction Methods in Quantitative Structure–Activity Relationship Modeling: A Comparative Study" @default.
• W3018074893 cites W108154941 @default.
• W3018074893 cites W1493357981 @default.
• W3018074893 cites W1569385724 @default.
• W3018074893 cites W1878565453 @default.
• W3018074893 cites W1990399577 @default.
• W3018074893 cites W1999798000 @default.
• W3018074893 cites W2001141328 @default.
• W3018074893 cites W2002563186 @default.
• W3018074893 cites W2002878672 @default.
• W3018074893 cites W2008997342 @default.
• W3018074893 cites W2014184703 @default.
• W3018074893 cites W2015755066 @default.
• W3018074893 cites W2017588182 @default.
• W3018074893 cites W2020149073 @default.
• W3018074893 cites W2022326777 @default.
• W3018074893 cites W2023937877 @default.
• W3018074893 cites W2027582327 @default.
• W3018074893 cites W2030827714 @default.
• W3018074893 cites W2035669331 @default.
• W3018074893 cites W2041602210 @default.
• W3018074893 cites W2042676708 @default.
• W3018074893 cites W2042970394 @default.
• W3018074893 cites W2049334526 @default.
• W3018074893 cites W2053171205 @default.
• W3018074893 cites W2053186076 @default.
• W3018074893 cites W2065411115 @default.
• W3018074893 cites W2078228628 @default.
• W3018074893 cites W2081320283 @default.
• W3018074893 cites W2082185517 @default.
• W3018074893 cites W2085965182 @default.
• W3018074893 cites W2087016914 @default.
• W3018074893 cites W2089497633 @default.
• W3018074893 cites W2096451472 @default.
• W3018074893 cites W2100495367 @default.
• W3018074893 cites W2130343586 @default.
• W3018074893 cites W2134262590 @default.
• W3018074893 cites W2142053997 @default.
• W3018074893 cites W2148143831 @default.
• W3018074893 cites W2156838815 @default.
• W3018074893 cites W2158698691 @default.
• W3018074893 cites W2180697714 @default.
• W3018074893 cites W2293600471 @default.
• W3018074893 cites W2294798173 @default.
• W3018074893 cites W2323909273 @default.
• W3018074893 cites W2406943157 @default.
• W3018074893 cites W2467309505 @default.
• W3018074893 cites W2549264034 @default.
• W3018074893 cites W2568027568 @default.
• W3018074893 cites W2729085143 @default.
• W3018074893 cites W2766736793 @default.
• W3018074893 cites W2790808809 @default.
• W3018074893 cites W2791315675 @default.
• W3018074893 cites W2791713605 @default.
• W3018074893 cites W2886791556 @default.
• W3018074893 cites W2887113605 @default.
• W3018074893 cites W2897131212 @default.
• W3018074893 cites W2902329228 @default.
• W3018074893 cites W2902852270 @default.
• W3018074893 cites W2911627187 @default.
• W3018074893 cites W2932154953 @default.
• W3018074893 cites W2937816774 @default.
• W3018074893 cites W2945915333 @default.
• W3018074893 cites W2949937757 @default.
• W3018074893 cites W2951747205 @default.
• W3018074893 cites W2979473749 @default.
• W3018074893 cites W2999468379 @default.
• W3018074893 cites W2999814961 @default.
• W3018074893 cites W3098269892 @default.
• W3018074893 cites W3104195492 @default.
• W3018074893 doi "https://doi.org/10.1109/access.2020.2990375" @default.
• W3018074893 hasPublicationYear "2020" @default.
• W3018074893 type Work @default.
• W3018074893 sameAs 3018074893 @default.
• W3018074893 citedByCount "20" @default.
• W3018074893 countsByYear W30180748932020 @default.
• W3018074893 countsByYear W30180748932021 @default.
• W3018074893 countsByYear W30180748932022 @default.
• W3018074893 countsByYear W30180748932023 @default.
• W3018074893 crossrefType "journal-article" @default.
• W3018074893 hasAuthorship W3018074893A5041926767 @default.
• W3018074893 hasAuthorship W3018074893A5068512068 @default.
• W3018074893 hasAuthorship W3018074893A5080950722 @default.
• W3018074893 hasBestOaLocation W30180748931 @default.
• W3018074893 hasConcept C111030470 @default.
• W3018074893 hasConcept C119857082 @default.
• W3018074893 hasConcept C124101348 @default.
• W3018074893 hasConcept C153180895 @default.
• W3018074893 hasConcept C154945302 @default.
• W3018074893 hasConcept C164126121 @default.
• W3018074893 hasConcept C27438332 @default.

• next