FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313595673> ?p ?o ?g. }

• W4313595673 abstract "The past few years have witnessed significant advances in developing machine learning methods for molecular energetics predictions, including calculated electronic energies with high-level quantum mechanical methods and experimental properties, such as solvation free energy and logP. Typically, task-specific machine learning models are developed for distinct prediction tasks. In this work, we present a multitask deep ensemble model, sPhysNet-MT-ens5, which can simultaneously and accurately predict electronic energies of molecules in gas, water, and octanol phases, as well as transfer free energies at both calculated and experimental levels. On the calculated data set Frag20-solv-678k, which is developed in this work and contains 678,916 molecular conformations, up to 20 heavy atoms, and their properties calculated at B3LYP/6-31G* level of theory with continuum solvent models, sPhysNet-MT-ens5 predicts density functional theory (DFT)-level electronic energies directly from force field-optimized geometry within chemical accuracy. On the experimental data sets, sPhysNet-MT-ens5 achieves state-of-the-art performances, which predict both experimental hydration free energy with a RMSE of 0.620 kcal/mol on the FreeSolv data set and experimental logP with a RMSE of 0.393 on the PHYSPROP data set. Furthermore, sPhysNet-MT-ens5 also provides a reasonable estimation of model uncertainty which shows correlations with prediction error. Finally, by analyzing the atomic contributions of its predictions, we find that the developed deep learning model is aware of the chemical environment of each atom by assigning reasonable atomic contributions consistent with our chemical knowledge." @default.
• W4313595673 created "2023-01-06" @default.
• W4313595673 creator A5061354710 @default.
• W4313595673 creator A5063629758 @default.
• W4313595673 creator A5079817016 @default.
• W4313595673 date "2023-01-06" @default.
• W4313595673 modified "2023-09-29" @default.
• W4313595673 title "Multitask Deep Ensemble Prediction of Molecular Energetics in Solution: From Quantum Mechanics to Experimental Properties" @default.
• W4313595673 cites W1531674615 @default.
• W4313595673 cites W1757990252 @default.
• W4313595673 cites W1974272773 @default.
• W4313595673 cites W1975997599 @default.
• W4313595673 cites W1998260904 @default.
• W4313595673 cites W2008505552 @default.
• W4313595673 cites W2011215428 @default.
• W4313595673 cites W2027482274 @default.
• W4313595673 cites W2029413789 @default.
• W4313595673 cites W2043932978 @default.
• W4313595673 cites W2055526416 @default.
• W4313595673 cites W2057069496 @default.
• W4313595673 cites W2058370262 @default.
• W4313595673 cites W2068950612 @default.
• W4313595673 cites W2080635178 @default.
• W4313595673 cites W2083415705 @default.
• W4313595673 cites W2104489082 @default.
• W4313595673 cites W2114704115 @default.
• W4313595673 cites W2121853844 @default.
• W4313595673 cites W2162235098 @default.
• W4313595673 cites W2165698076 @default.
• W4313595673 cites W2176516200 @default.
• W4313595673 cites W2244785476 @default.
• W4313595673 cites W2290847742 @default.
• W4313595673 cites W2319902168 @default.
• W4313595673 cites W2477754403 @default.
• W4313595673 cites W2527189750 @default.
• W4313595673 cites W2541404351 @default.
• W4313595673 cites W2594183968 @default.
• W4313595673 cites W2726184500 @default.
• W4313595673 cites W2778051509 @default.
• W4313595673 cites W2793396277 @default.
• W4313595673 cites W2801991413 @default.
• W4313595673 cites W2899070097 @default.
• W4313595673 cites W2901003004 @default.
• W4313595673 cites W2911789160 @default.
• W4313595673 cites W2911997094 @default.
• W4313595673 cites W2923693308 @default.
• W4313595673 cites W2947121332 @default.
• W4313595673 cites W2952736849 @default.
• W4313595673 cites W2954961100 @default.
• W4313595673 cites W2962876364 @default.
• W4313595673 cites W2963613699 @default.
• W4313595673 cites W2964007201 @default.
• W4313595673 cites W2966357564 @default.
• W4313595673 cites W2968734407 @default.
• W4313595673 cites W2983997668 @default.
• W4313595673 cites W3002565078 @default.
• W4313595673 cites W3013487850 @default.
• W4313595673 cites W3014339631 @default.
• W4313595673 cites W3021503072 @default.
• W4313595673 cites W3035559885 @default.
• W4313595673 cites W3036441178 @default.
• W4313595673 cites W3044724994 @default.
• W4313595673 cites W3097145107 @default.
• W4313595673 cites W3101643101 @default.
• W4313595673 cites W3102449990 @default.
• W4313595673 cites W3103092523 @default.
• W4313595673 cites W3116202926 @default.
• W4313595673 cites W3117876228 @default.
• W4313595673 cites W3119655479 @default.
• W4313595673 cites W3132956480 @default.
• W4313595673 cites W3134184520 @default.
• W4313595673 cites W3166272013 @default.
• W4313595673 cites W3167275903 @default.
• W4313595673 cites W3170966572 @default.
• W4313595673 cites W3171375210 @default.
• W4313595673 cites W3185227028 @default.
• W4313595673 cites W3185456481 @default.
• W4313595673 cites W3189651386 @default.
• W4313595673 cites W3192643845 @default.
• W4313595673 cites W4200226776 @default.
• W4313595673 cites W4224058524 @default.
• W4313595673 doi "https://doi.org/10.1021/acs.jctc.2c01024" @default.
• W4313595673 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36607141" @default.
• W4313595673 hasPublicationYear "2023" @default.
• W4313595673 type Work @default.
• W4313595673 citedByCount "0" @default.
• W4313595673 crossrefType "journal-article" @default.
• W4313595673 hasAuthorship W4313595673A5061354710 @default.
• W4313595673 hasAuthorship W4313595673A5063629758 @default.
• W4313595673 hasAuthorship W4313595673A5079817016 @default.
• W4313595673 hasConcept C105795698 @default.
• W4313595673 hasConcept C10803110 @default.
• W4313595673 hasConcept C121332964 @default.
• W4313595673 hasConcept C121864883 @default.
• W4313595673 hasConcept C139945424 @default.
• W4313595673 hasConcept C147597530 @default.
• W4313595673 hasConcept C148093993 @default.
• W4313595673 hasConcept C149635348 @default.
• W4313595673 hasConcept C152365726 @default.
• W4313595673 hasConcept C154945302 @default.

• next