FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3126848411> ?p ?o ?g. }

• W3126848411 abstract "As an essential task in protein structure and function prediction, protein fold recognition has attracted increasing attention. The majority of the existing machine learning-based protein fold recognition approaches strongly rely on handcrafted features, which depict the characteristics of different protein folds; however, effective feature extraction methods still represent the bottleneck for further performance improvement of protein fold recognition. As a powerful feature extractor, deep convolutional neural network (DCNN) can automatically extract discriminative features for fold recognition without human intervention, which has demonstrated an impressive performance on protein fold recognition. Despite the encouraging progress, DCNN often acts as a black box, and as such, it is challenging for users to understand what really happens in DCNN and why it works well for protein fold recognition. In this study, we explore the intrinsic mechanism of DCNN and explain why it works for protein fold recognition using a visual explanation technique. More specifically, we first trained a VGGNet-based DCNN model, termed VGGNet-FE, which can extract fold-specific features from the predicted protein residue-residue contact map for protein fold recognition. Subsequently, based on the trained VGGNet-FE, we implemented a new contact-assisted predictor, termed VGGfold, for protein fold recognition; we then visualized what features were extracted by each of the convolutional layers in VGGNet-FE using a deconvolution technique. Furthermore, we visualized the high-level semantic information, termed fold-discriminative region, of a predicted contact map from the localization map obtained from the last convolutional layer of VGGNet-FE. It is visually confirmed that VGGNet-FE could effectively extract distinct fold-discriminative regions for different types of protein folds, thereby accounting for the improved performance of VGGfold for protein fold recognition. In summary, this study is of great significance for both understanding the working principle of DCNNs in protein fold recognition and exploring the relationship between the predicted protein contact map and protein tertiary structure. This proposed visualization method is flexible and applicable to address other DCNN-based bioinformatics and computational biology questions. The online web server of VGGfold is freely available at http://csbio.njust.edu.cn/bioinf/vggfold/." @default.
• W3126848411 created "2021-02-15" @default.
• W3126848411 creator A5008960436 @default.
• W3126848411 creator A5012709797 @default.
• W3126848411 creator A5027029132 @default.
• W3126848411 creator A5052610760 @default.
• W3126848411 creator A5088632918 @default.
• W3126848411 date "2021-02-04" @default.
• W3126848411 modified "2023-10-16" @default.
• W3126848411 title "Why can deep convolutional neural networks improve protein fold recognition? A visual explanation by interpretation" @default.
• W3126848411 cites W1578951231 @default.
• W3126848411 cites W1979081881 @default.
• W3126848411 cites W1996357466 @default.
• W3126848411 cites W2047672715 @default.
• W3126848411 cites W2064675550 @default.
• W3126848411 cites W2082667898 @default.
• W3126848411 cites W2084131216 @default.
• W3126848411 cites W2089954482 @default.
• W3126848411 cites W2097606916 @default.
• W3126848411 cites W2098884353 @default.
• W3126848411 cites W2105099387 @default.
• W3126848411 cites W2114340287 @default.
• W3126848411 cites W2119331235 @default.
• W3126848411 cites W2141200610 @default.
• W3126848411 cites W2145541064 @default.
• W3126848411 cites W2146084306 @default.
• W3126848411 cites W2151180344 @default.
• W3126848411 cites W2152770371 @default.
• W3126848411 cites W2153187042 @default.
• W3126848411 cites W2154855927 @default.
• W3126848411 cites W2158714788 @default.
• W3126848411 cites W2161072217 @default.
• W3126848411 cites W2163957306 @default.
• W3126848411 cites W2166701319 @default.
• W3126848411 cites W2190008860 @default.
• W3126848411 cites W2243910093 @default.
• W3126848411 cites W2308318555 @default.
• W3126848411 cites W2423124209 @default.
• W3126848411 cites W2599048725 @default.
• W3126848411 cites W2605650084 @default.
• W3126848411 cites W2607160074 @default.
• W3126848411 cites W2747370968 @default.
• W3126848411 cites W2765207150 @default.
• W3126848411 cites W2801109052 @default.
• W3126848411 cites W2889498145 @default.
• W3126848411 cites W2914272550 @default.
• W3126848411 cites W2944535254 @default.
• W3126848411 cites W2971719842 @default.
• W3126848411 cites W2982608875 @default.
• W3126848411 cites W2989977616 @default.
• W3126848411 cites W2999653953 @default.
• W3126848411 cites W3021053579 @default.
• W3126848411 cites W3102564565 @default.
• W3126848411 cites W4229922087 @default.
• W3126848411 doi "https://doi.org/10.1093/bib/bbab001" @default.
• W3126848411 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8425391" @default.
• W3126848411 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33537753" @default.
• W3126848411 hasPublicationYear "2021" @default.
• W3126848411 type Work @default.
• W3126848411 sameAs 3126848411 @default.
• W3126848411 citedByCount "7" @default.
• W3126848411 countsByYear W31268484112021 @default.
• W3126848411 countsByYear W31268484112022 @default.
• W3126848411 countsByYear W31268484112023 @default.
• W3126848411 crossrefType "journal-article" @default.
• W3126848411 hasAuthorship W3126848411A5008960436 @default.
• W3126848411 hasAuthorship W3126848411A5012709797 @default.
• W3126848411 hasAuthorship W3126848411A5027029132 @default.
• W3126848411 hasAuthorship W3126848411A5052610760 @default.
• W3126848411 hasAuthorship W3126848411A5088632918 @default.
• W3126848411 hasBestOaLocation W31268484112 @default.
• W3126848411 hasConcept C117978034 @default.
• W3126848411 hasConcept C119857082 @default.
• W3126848411 hasConcept C127413603 @default.
• W3126848411 hasConcept C153180895 @default.
• W3126848411 hasConcept C154945302 @default.
• W3126848411 hasConcept C199360897 @default.
• W3126848411 hasConcept C21880701 @default.
• W3126848411 hasConcept C41008148 @default.
• W3126848411 hasConcept C53942344 @default.
• W3126848411 hasConcept C81363708 @default.
• W3126848411 hasConcept C95623464 @default.
• W3126848411 hasConcept C97931131 @default.
• W3126848411 hasConceptScore W3126848411C117978034 @default.
• W3126848411 hasConceptScore W3126848411C119857082 @default.
• W3126848411 hasConceptScore W3126848411C127413603 @default.
• W3126848411 hasConceptScore W3126848411C153180895 @default.
• W3126848411 hasConceptScore W3126848411C154945302 @default.
• W3126848411 hasConceptScore W3126848411C199360897 @default.
• W3126848411 hasConceptScore W3126848411C21880701 @default.
• W3126848411 hasConceptScore W3126848411C41008148 @default.
• W3126848411 hasConceptScore W3126848411C53942344 @default.
• W3126848411 hasConceptScore W3126848411C81363708 @default.
• W3126848411 hasConceptScore W3126848411C95623464 @default.
• W3126848411 hasConceptScore W3126848411C97931131 @default.
• W3126848411 hasFunder F4320321001 @default.
• W3126848411 hasFunder F4320332161 @default.
• W3126848411 hasFunder F4320334704 @default.
• W3126848411 hasFunder F4320335787 @default.
• W3126848411 hasFunder F4320337355 @default.

• next