Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202848468> ?p ?o ?g. }
- W3202848468 abstract "Machine learning has been increasingly used for protein engineering. However, because the general sequence contexts they capture are not specific to the protein being engineered, the accuracy of existing machine learning algorithms is rather limited. Here, we report ECNet (evolutionary context-integrated neural network), a deep-learning algorithm that exploits evolutionary contexts to predict functional fitness for protein engineering. This algorithm integrates local evolutionary context from homologous sequences that explicitly model residue-residue epistasis for the protein of interest with the global evolutionary context that encodes rich semantic and structural features from the enormous protein sequence universe. As such, it enables accurate mapping from sequence to function and provides generalization from low-order mutants to higher-order mutants. We show that ECNet predicts the sequence-function relationship more accurately as compared to existing machine learning algorithms by using ~50 deep mutational scanning and random mutagenesis datasets. Moreover, we used ECNet to guide the engineering of TEM-1 β-lactamase and identified variants with improved ampicillin resistance with high success rates." @default.
- W3202848468 created "2021-10-11" @default.
- W3202848468 creator A5011865422 @default.
- W3202848468 creator A5014465828 @default.
- W3202848468 creator A5023363049 @default.
- W3202848468 creator A5033160658 @default.
- W3202848468 creator A5044232156 @default.
- W3202848468 creator A5046029570 @default.
- W3202848468 creator A5058112632 @default.
- W3202848468 creator A5059197338 @default.
- W3202848468 creator A5061177999 @default.
- W3202848468 creator A5071054254 @default.
- W3202848468 date "2021-09-30" @default.
- W3202848468 modified "2023-10-15" @default.
- W3202848468 title "ECNet is an evolutionary context-integrated deep learning framework for protein engineering" @default.
- W3202848468 cites W1721447212 @default.
- W3202848468 cites W1969012077 @default.
- W3202848468 cites W1976410590 @default.
- W3202848468 cites W2013425283 @default.
- W3202848468 cites W2014159272 @default.
- W3202848468 cites W2016185554 @default.
- W3202848468 cites W2023490488 @default.
- W3202848468 cites W2059145105 @default.
- W3202848468 cites W2060130700 @default.
- W3202848468 cites W2061042699 @default.
- W3202848468 cites W2085144875 @default.
- W3202848468 cites W2103385859 @default.
- W3202848468 cites W2107867854 @default.
- W3202848468 cites W2114340287 @default.
- W3202848468 cites W2117235735 @default.
- W3202848468 cites W2118265845 @default.
- W3202848468 cites W2120836664 @default.
- W3202848468 cites W2134757533 @default.
- W3202848468 cites W2136848157 @default.
- W3202848468 cites W2137566700 @default.
- W3202848468 cites W2144893575 @default.
- W3202848468 cites W2160995259 @default.
- W3202848468 cites W2245592118 @default.
- W3202848468 cites W2379594833 @default.
- W3202848468 cites W2401346147 @default.
- W3202848468 cites W2412207659 @default.
- W3202848468 cites W2765744127 @default.
- W3202848468 cites W2774216375 @default.
- W3202848468 cites W2780845733 @default.
- W3202848468 cites W2782613909 @default.
- W3202848468 cites W2791796577 @default.
- W3202848468 cites W2797104734 @default.
- W3202848468 cites W2805822903 @default.
- W3202848468 cites W2885204620 @default.
- W3202848468 cites W2890223884 @default.
- W3202848468 cites W2898402099 @default.
- W3202848468 cites W2905452503 @default.
- W3202848468 cites W2917580301 @default.
- W3202848468 cites W2928861204 @default.
- W3202848468 cites W2943203634 @default.
- W3202848468 cites W2945726413 @default.
- W3202848468 cites W2951433247 @default.
- W3202848468 cites W2952214667 @default.
- W3202848468 cites W2953085814 @default.
- W3202848468 cites W2956569764 @default.
- W3202848468 cites W2972411752 @default.
- W3202848468 cites W2972671276 @default.
- W3202848468 cites W2979343028 @default.
- W3202848468 cites W2980789587 @default.
- W3202848468 cites W3009806336 @default.
- W3202848468 cites W3010387158 @default.
- W3202848468 cites W3016443350 @default.
- W3202848468 cites W3048714202 @default.
- W3202848468 cites W3094032126 @default.
- W3202848468 cites W3098238469 @default.
- W3202848468 cites W3121000782 @default.
- W3202848468 cites W3136918052 @default.
- W3202848468 cites W3139654928 @default.
- W3202848468 cites W3144239152 @default.
- W3202848468 cites W3146944767 @default.
- W3202848468 cites W3154275519 @default.
- W3202848468 cites W3169392527 @default.
- W3202848468 cites W3177500196 @default.
- W3202848468 cites W3179485843 @default.
- W3202848468 cites W3194729882 @default.
- W3202848468 doi "https://doi.org/10.1038/s41467-021-25976-8" @default.
- W3202848468 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8484459" @default.
- W3202848468 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34593817" @default.
- W3202848468 hasPublicationYear "2021" @default.
- W3202848468 type Work @default.
- W3202848468 sameAs 3202848468 @default.
- W3202848468 citedByCount "47" @default.
- W3202848468 countsByYear W32028484682021 @default.
- W3202848468 countsByYear W32028484682022 @default.
- W3202848468 countsByYear W32028484682023 @default.
- W3202848468 crossrefType "journal-article" @default.
- W3202848468 hasAuthorship W3202848468A5011865422 @default.
- W3202848468 hasAuthorship W3202848468A5014465828 @default.
- W3202848468 hasAuthorship W3202848468A5023363049 @default.
- W3202848468 hasAuthorship W3202848468A5033160658 @default.
- W3202848468 hasAuthorship W3202848468A5044232156 @default.
- W3202848468 hasAuthorship W3202848468A5046029570 @default.
- W3202848468 hasAuthorship W3202848468A5058112632 @default.
- W3202848468 hasAuthorship W3202848468A5059197338 @default.
- W3202848468 hasAuthorship W3202848468A5061177999 @default.