FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4214842232> ?p ?o ?g. }

• W4214842232 endingPage "2143" @default.
• W4214842232 startingPage "2132" @default.
• W4214842232 abstract "Deep learning methods provide a novel way to establish a correlation between two quantities. In this context, computer vision techniques such as three-dimensional (3D)-convolutional neural networks become a natural choice to associate a molecular property with its structure due to the inherent 3D nature of a molecule. However, traditional 3D input data structures are intrinsically sparse in nature, which tend to induce instabilities during the learning process, which in turn may lead to underfitted results. To address this deficiency, in this project, we propose to use quantum-chemically derived molecular topological features, namely, localized orbital locator and electron localization function, as molecular descriptors, which provide a relatively denser input representation in a 3D space. Such topological features provide a detailed picture of the atomic and electronic configuration and interatomic interactions in the molecule and hence are ideal for predicting properties that are highly dependent on the physical or electronic structure of the molecule. Herein, we demonstrate the efficacy of our proposed model by applying it to the task of predicting atomization energies for the QM9-G4MP2 data set, which contains ∼134k molecules. Furthermore, we incorporated the Δ-machine learning approach into our model, which enabled us to reach beyond benchmark accuracy levels (∼1.0 kJ mol-1). As a result, we consistently obtain impressive mean absolute errors of the order 0.1 kcal mol-1 (∼0.42 kJ mol-1) versus the G4(MP2) theory using relatively modest models, which could potentially be improved further in a systematic manner using additional compute resources." @default.
• W4214842232 created "2022-03-05" @default.
• W4214842232 creator A5011183754 @default.
• W4214842232 creator A5039602411 @default.
• W4214842232 date "2022-02-28" @default.
• W4214842232 modified "2023-10-02" @default.
• W4214842232 title "Three-Dimensional Convolutional Neural Networks Utilizing Molecular Topological Features for Accurate Atomization Energy Predictions" @default.
• W4214842232 cites W1966587798 @default.
• W4214842232 cites W1968210381 @default.
• W4214842232 cites W1971044734 @default.
• W4214842232 cites W1976495225 @default.
• W4214842232 cites W1977850702 @default.
• W4214842232 cites W1981661712 @default.
• W4214842232 cites W1982539988 @default.
• W4214842232 cites W2003850441 @default.
• W4214842232 cites W2005284090 @default.
• W4214842232 cites W2017488020 @default.
• W4214842232 cites W2030970551 @default.
• W4214842232 cites W2032495608 @default.
• W4214842232 cites W2034539597 @default.
• W4214842232 cites W2039827935 @default.
• W4214842232 cites W2053992562 @default.
• W4214842232 cites W2067675515 @default.
• W4214842232 cites W2075711588 @default.
• W4214842232 cites W2080635178 @default.
• W4214842232 cites W2087935756 @default.
• W4214842232 cites W2092930273 @default.
• W4214842232 cites W2093914988 @default.
• W4214842232 cites W2096443962 @default.
• W4214842232 cites W2114704115 @default.
• W4214842232 cites W2132525235 @default.
• W4214842232 cites W2144168070 @default.
• W4214842232 cites W2163562767 @default.
• W4214842232 cites W2194775991 @default.
• W4214842232 cites W2398056652 @default.
• W4214842232 cites W2541404351 @default.
• W4214842232 cites W2550260771 @default.
• W4214842232 cites W2556802233 @default.
• W4214842232 cites W2569680626 @default.
• W4214842232 cites W2576915720 @default.
• W4214842232 cites W2601564443 @default.
• W4214842232 cites W2606620387 @default.
• W4214842232 cites W2609436233 @default.
• W4214842232 cites W2617750324 @default.
• W4214842232 cites W2622401893 @default.
• W4214842232 cites W2625768267 @default.
• W4214842232 cites W2768213699 @default.
• W4214842232 cites W2768638516 @default.
• W4214842232 cites W2778051509 @default.
• W4214842232 cites W2781821160 @default.
• W4214842232 cites W2784213390 @default.
• W4214842232 cites W2789074794 @default.
• W4214842232 cites W2794434752 @default.
• W4214842232 cites W2891927397 @default.
• W4214842232 cites W2900957533 @default.
• W4214842232 cites W2914877211 @default.
• W4214842232 cites W2923693308 @default.
• W4214842232 cites W2951553337 @default.
• W4214842232 cites W2954088480 @default.
• W4214842232 cites W2955551200 @default.
• W4214842232 cites W2956850742 @default.
• W4214842232 cites W2957746479 @default.
• W4214842232 cites W2959176200 @default.
• W4214842232 cites W2963446712 @default.
• W4214842232 cites W2963527880 @default.
• W4214842232 cites W2970235642 @default.
• W4214842232 cites W2990174420 @default.
• W4214842232 cites W3003486042 @default.
• W4214842232 cites W3005364306 @default.
• W4214842232 cites W3005776600 @default.
• W4214842232 cites W3012511738 @default.
• W4214842232 cites W3021453944 @default.
• W4214842232 cites W3023962374 @default.
• W4214842232 cites W3024819430 @default.
• W4214842232 cites W3093036756 @default.
• W4214842232 cites W3101744125 @default.
• W4214842232 cites W3103736477 @default.
• W4214842232 cites W3104141662 @default.
• W4214842232 cites W3104705366 @default.
• W4214842232 cites W3120580474 @default.
• W4214842232 cites W3126954028 @default.
• W4214842232 cites W3128933281 @default.
• W4214842232 cites W3129238601 @default.
• W4214842232 cites W3159885451 @default.
• W4214842232 cites W3172760943 @default.
• W4214842232 cites W3216896057 @default.
• W4214842232 doi "https://doi.org/10.1021/acs.jctc.1c00504" @default.
• W4214842232 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35226496" @default.
• W4214842232 hasPublicationYear "2022" @default.
• W4214842232 type Work @default.
• W4214842232 citedByCount "3" @default.
• W4214842232 countsByYear W42148422322023 @default.
• W4214842232 crossrefType "journal-article" @default.
• W4214842232 hasAuthorship W4214842232A5011183754 @default.
• W4214842232 hasAuthorship W4214842232A5039602411 @default.
• W4214842232 hasConcept C111919701 @default.
• W4214842232 hasConcept C114614502 @default.
• W4214842232 hasConcept C13280743 @default.

• next