Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285388924> ?p ?o ?g. }
- W4285388924 abstract "Computational methods in protein engineering often require encoding amino acid sequences, i.e., converting them into numeric arrays. Physicochemical properties are a typical choice to define encoders, where we replace each amino acid by its value for a given property. However, what property (or group thereof) is best for a given predictive task remains an open problem. In this work, we generalize property-based encoding strategies to maximize the performance of predictive models in protein engineering. First, combining text mining and unsupervised learning, we partitioned the AAIndex database into eight semantically-consistent groups of properties. We then applied a non-linear PCA within each group to define a single encoder to represent it. Then, in several case studies, we assess the performance of predictive models for protein and peptide function, folding, and biological activity, trained using the proposed encoders and classical methods (One Hot Encoder and TAPE embeddings). Models trained on datasets encoded with our encoders and converted to signals through the Fast Fourier Transform (FFT) increased their precision and reduced their overfitting substantially, outperforming classical approaches in most cases. Finally, we propose a preliminary methodology to create de novo sequences with desired properties. All these results offer simple ways to increase the performance of general and complex predictive tasks in protein engineering without increasing their complexity." @default.
- W4285388924 created "2022-07-14" @default.
- W4285388924 creator A5027484011 @default.
- W4285388924 creator A5028738007 @default.
- W4285388924 creator A5051722276 @default.
- W4285388924 creator A5061327016 @default.
- W4285388924 creator A5069731582 @default.
- W4285388924 creator A5079714890 @default.
- W4285388924 creator A5081291938 @default.
- W4285388924 date "2022-07-14" @default.
- W4285388924 modified "2023-09-26" @default.
- W4285388924 title "Generalized Property-Based Encoders and Digital Signal Processing Facilitate Predictive Tasks in Protein Engineering" @default.
- W4285388924 cites W1973460506 @default.
- W4285388924 cites W1989362683 @default.
- W4285388924 cites W1998064689 @default.
- W4285388924 cites W2010289445 @default.
- W4285388924 cites W2012408028 @default.
- W4285388924 cites W2014731953 @default.
- W4285388924 cites W2035498051 @default.
- W4285388924 cites W2044056407 @default.
- W4285388924 cites W2048902851 @default.
- W4285388924 cites W2053154939 @default.
- W4285388924 cites W2060238374 @default.
- W4285388924 cites W2084067528 @default.
- W4285388924 cites W2086565769 @default.
- W4285388924 cites W2094889474 @default.
- W4285388924 cites W2103918159 @default.
- W4285388924 cites W2106822551 @default.
- W4285388924 cites W2118714546 @default.
- W4285388924 cites W2132136181 @default.
- W4285388924 cites W2168749685 @default.
- W4285388924 cites W2278606577 @default.
- W4285388924 cites W2340970647 @default.
- W4285388924 cites W2342249984 @default.
- W4285388924 cites W2470414691 @default.
- W4285388924 cites W2559191318 @default.
- W4285388924 cites W2734861826 @default.
- W4285388924 cites W2791796577 @default.
- W4285388924 cites W2793434995 @default.
- W4285388924 cites W2804549231 @default.
- W4285388924 cites W2887566220 @default.
- W4285388924 cites W2895810213 @default.
- W4285388924 cites W2896384790 @default.
- W4285388924 cites W2897098357 @default.
- W4285388924 cites W2900113977 @default.
- W4285388924 cites W2901093961 @default.
- W4285388924 cites W2943935116 @default.
- W4285388924 cites W2949250633 @default.
- W4285388924 cites W2951433247 @default.
- W4285388924 cites W2956569764 @default.
- W4285388924 cites W2971227267 @default.
- W4285388924 cites W3005910971 @default.
- W4285388924 cites W3025560490 @default.
- W4285388924 cites W3034479940 @default.
- W4285388924 cites W3134185574 @default.
- W4285388924 cites W3163970098 @default.
- W4285388924 cites W3178295718 @default.
- W4285388924 cites W3183920302 @default.
- W4285388924 cites W3197075585 @default.
- W4285388924 cites W4213345021 @default.
- W4285388924 doi "https://doi.org/10.3389/fmolb.2022.898627" @default.
- W4285388924 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35911960" @default.
- W4285388924 hasPublicationYear "2022" @default.
- W4285388924 type Work @default.
- W4285388924 citedByCount "5" @default.
- W4285388924 countsByYear W42853889242023 @default.
- W4285388924 crossrefType "journal-article" @default.
- W4285388924 hasAuthorship W4285388924A5027484011 @default.
- W4285388924 hasAuthorship W4285388924A5028738007 @default.
- W4285388924 hasAuthorship W4285388924A5051722276 @default.
- W4285388924 hasAuthorship W4285388924A5061327016 @default.
- W4285388924 hasAuthorship W4285388924A5069731582 @default.
- W4285388924 hasAuthorship W4285388924A5079714890 @default.
- W4285388924 hasAuthorship W4285388924A5081291938 @default.
- W4285388924 hasBestOaLocation W42853889241 @default.
- W4285388924 hasConcept C101738243 @default.
- W4285388924 hasConcept C108583219 @default.
- W4285388924 hasConcept C111472728 @default.
- W4285388924 hasConcept C111919701 @default.
- W4285388924 hasConcept C11413529 @default.
- W4285388924 hasConcept C118505674 @default.
- W4285388924 hasConcept C119857082 @default.
- W4285388924 hasConcept C125411270 @default.
- W4285388924 hasConcept C138885662 @default.
- W4285388924 hasConcept C153180895 @default.
- W4285388924 hasConcept C154945302 @default.
- W4285388924 hasConcept C189950617 @default.
- W4285388924 hasConcept C22019652 @default.
- W4285388924 hasConcept C41008148 @default.
- W4285388924 hasConcept C50644808 @default.
- W4285388924 hasConceptScore W4285388924C101738243 @default.
- W4285388924 hasConceptScore W4285388924C108583219 @default.
- W4285388924 hasConceptScore W4285388924C111472728 @default.
- W4285388924 hasConceptScore W4285388924C111919701 @default.
- W4285388924 hasConceptScore W4285388924C11413529 @default.
- W4285388924 hasConceptScore W4285388924C118505674 @default.
- W4285388924 hasConceptScore W4285388924C119857082 @default.
- W4285388924 hasConceptScore W4285388924C125411270 @default.
- W4285388924 hasConceptScore W4285388924C138885662 @default.
- W4285388924 hasConceptScore W4285388924C153180895 @default.