Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385310178> ?p ?o ?g. }
- W4385310178 endingPage "11948" @default.
- W4385310178 startingPage "11948" @default.
- W4385310178 abstract "In this study, we introduce semi-supervised machine learning models designed to predict molecular properties. Our model employs a two-stage approach, involving pre-training and fine-tuning. Particularly, our model leverages a substantial amount of labeled and unlabeled data consisting of SMILES strings, a text representation system for molecules. During the pre-training stage, our model capitalizes on the Masked Language Model, which is widely used in natural language processing, for learning molecular chemical space representations. During the fine-tuning stage, our model is trained on a smaller labeled dataset to tackle specific downstream tasks, such as classification or regression. Preliminary results indicate that our model demonstrates comparable performance to state-of-the-art models on the chosen downstream tasks from MoleculeNet. Additionally, to reduce the computational overhead, we propose a new approach taking advantage of 3D compound structures for calculating the attention score used in the end-to-end transformer model to predict anti-malaria drug candidates. The results show that using the proposed attention score, our end-to-end model is able to have comparable performance with pre-trained models." @default.
- W4385310178 created "2023-07-28" @default.
- W4385310178 creator A5017440090 @default.
- W4385310178 creator A5038396319 @default.
- W4385310178 date "2023-07-26" @default.
- W4385310178 modified "2023-09-30" @default.
- W4385310178 title "Molecular Descriptors Property Prediction Using Transformer-Based Approach" @default.
- W4385310178 cites W1560202902 @default.
- W4385310178 cites W1965313623 @default.
- W4385310178 cites W1973698523 @default.
- W4385310178 cites W1975147762 @default.
- W4385310178 cites W2046653925 @default.
- W4385310178 cites W2063060349 @default.
- W4385310178 cites W2087563523 @default.
- W4385310178 cites W2138906088 @default.
- W4385310178 cites W2157331557 @default.
- W4385310178 cites W2317467438 @default.
- W4385310178 cites W2405035126 @default.
- W4385310178 cites W2467309505 @default.
- W4385310178 cites W2578240541 @default.
- W4385310178 cites W2582187633 @default.
- W4385310178 cites W2594183968 @default.
- W4385310178 cites W2614053601 @default.
- W4385310178 cites W2742753960 @default.
- W4385310178 cites W2749279690 @default.
- W4385310178 cites W2789816271 @default.
- W4385310178 cites W2885592687 @default.
- W4385310178 cites W2888164077 @default.
- W4385310178 cites W2894559996 @default.
- W4385310178 cites W2899070097 @default.
- W4385310178 cites W2966357564 @default.
- W4385310178 cites W2971227267 @default.
- W4385310178 cites W2973114758 @default.
- W4385310178 cites W2979826702 @default.
- W4385310178 cites W3000139398 @default.
- W4385310178 cites W3008194656 @default.
- W4385310178 cites W3010813949 @default.
- W4385310178 cites W3023353883 @default.
- W4385310178 cites W3032781902 @default.
- W4385310178 cites W3036931110 @default.
- W4385310178 cites W3105259638 @default.
- W4385310178 cites W3127596955 @default.
- W4385310178 cites W3128029990 @default.
- W4385310178 cites W3187251571 @default.
- W4385310178 cites W3215781140 @default.
- W4385310178 cites W4210592951 @default.
- W4385310178 cites W4249179470 @default.
- W4385310178 cites W4306179830 @default.
- W4385310178 cites W4313527186 @default.
- W4385310178 doi "https://doi.org/10.3390/ijms241511948" @default.
- W4385310178 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37569322" @default.
- W4385310178 hasPublicationYear "2023" @default.
- W4385310178 type Work @default.
- W4385310178 citedByCount "0" @default.
- W4385310178 crossrefType "journal-article" @default.
- W4385310178 hasAuthorship W4385310178A5017440090 @default.
- W4385310178 hasAuthorship W4385310178A5038396319 @default.
- W4385310178 hasBestOaLocation W43853101781 @default.
- W4385310178 hasConcept C105795698 @default.
- W4385310178 hasConcept C111472728 @default.
- W4385310178 hasConcept C119599485 @default.
- W4385310178 hasConcept C119857082 @default.
- W4385310178 hasConcept C127413603 @default.
- W4385310178 hasConcept C137293760 @default.
- W4385310178 hasConcept C138885662 @default.
- W4385310178 hasConcept C154945302 @default.
- W4385310178 hasConcept C165801399 @default.
- W4385310178 hasConcept C189950617 @default.
- W4385310178 hasConcept C201995342 @default.
- W4385310178 hasConcept C204321447 @default.
- W4385310178 hasConcept C2779135771 @default.
- W4385310178 hasConcept C2780451532 @default.
- W4385310178 hasConcept C33923547 @default.
- W4385310178 hasConcept C41008148 @default.
- W4385310178 hasConcept C51632099 @default.
- W4385310178 hasConcept C60644358 @default.
- W4385310178 hasConcept C66322947 @default.
- W4385310178 hasConcept C74187038 @default.
- W4385310178 hasConcept C83546350 @default.
- W4385310178 hasConcept C86803240 @default.
- W4385310178 hasConcept C99726746 @default.
- W4385310178 hasConceptScore W4385310178C105795698 @default.
- W4385310178 hasConceptScore W4385310178C111472728 @default.
- W4385310178 hasConceptScore W4385310178C119599485 @default.
- W4385310178 hasConceptScore W4385310178C119857082 @default.
- W4385310178 hasConceptScore W4385310178C127413603 @default.
- W4385310178 hasConceptScore W4385310178C137293760 @default.
- W4385310178 hasConceptScore W4385310178C138885662 @default.
- W4385310178 hasConceptScore W4385310178C154945302 @default.
- W4385310178 hasConceptScore W4385310178C165801399 @default.
- W4385310178 hasConceptScore W4385310178C189950617 @default.
- W4385310178 hasConceptScore W4385310178C201995342 @default.
- W4385310178 hasConceptScore W4385310178C204321447 @default.
- W4385310178 hasConceptScore W4385310178C2779135771 @default.
- W4385310178 hasConceptScore W4385310178C2780451532 @default.
- W4385310178 hasConceptScore W4385310178C33923547 @default.
- W4385310178 hasConceptScore W4385310178C41008148 @default.
- W4385310178 hasConceptScore W4385310178C51632099 @default.