Current neural networks for predictions of molecular properties use quantum chemistry only as a source of training data. This paper explores models that use quantum chemistry as an integral part of the prediction process. This is done by implementing selfconsistent-charge Density-Functional-Tight-Binding (DFTB) theory as a layer for use in deep learning models. The DFTB layer takes, as input, Hamiltonian matrix elements generated from earlier layers and produces, as output, electronic properties from self-consistent field solutions of the corresponding DFTB Hamiltonian. Backpropagation enables efficient training of the model to target electronic properties. Two types of input to the DFTB layer are explored, splines and feed-forward neural networks. Because overfitting can cause models trained on smaller molecules to perform poorly on larger molecules, regularizations are applied that penalize non-monotonic behavior and deviation of the Hamiltonian matrix elements from those of the published DFTB model used to initialize the model. The approach is evaluated on 15,700 hydrocarbons by comparing the root mean square error in energy and dipole moment, on test molecules with 8 heavy atoms, to the error from the initial DFTB model. When trained on molecules with up to 7 heavy atoms, the spline model reduces the test error in energy by 60% and in dipole moments by 42%. The neural network model performs somewhat better, with error reductions of 67% and 59% respectively. Training on molecules with up to 4 heavy atoms reduces performance, with both the spline and neural net models reducing the test error in energy by about 53% and in dipole by about 25%. arXiv:1808.04526v2 [physics.chem-ph]
The introduction of electron donor and acceptor groups at strategic locations on a fluorogenic cyanine dye allows fine-tuning of the absorption and emission spectra while preserving the ability of the dye to bind to biomolecular hosts such as double-stranded DNA and a single-chain antibody fragment originally selected for binding to the parent unsubstituted dye, thiazole orange (TO). The observed spectral shifts are consistent with calculated HOMO-LUMO energy gaps and reflect electron density localization on the quinoline half of TO in the LUMO. A dye bearing donating methoxy and withdrawing trifluoromethyl groups on the benzothiazole and quinoline rings, respectively, shifts the absorption spectrum to sufficiently longer wavelengths to allow excitation at green wavelengths as opposed to the parent dye, which is optimally excited in the blue.
The fluorescence of the SKC-513 ((E)-N-(9-(4-(1,4,7,10,13-pentaoxa-16-azacyclooctadecan-16-yl)phenyl)-6-(butyl(3-sulfopropyl)amino)-3H-xanthen-3-ylidene)-N-(3-sulfopropyl)butan-1-aminium)
dye is shown experimentally to have high sensitivity to binding of
the K+ ion. Computations are used to explore the potential
origins of this sensitivity and to make some suggestions regarding
structural improvements. In the absence of K+, excitation
is to two nearly degenerate states, a neutral (N) excited state with
a high oscillator strength, and a charge-transfer (CT) state with
a lower oscillator strength. Binding of K+ destabilizes
the CT state, raising its energy far above the N state. The increase
in fluorescence quantum yield upon binding of K+ is attributed
to the increased energy of the CT state suppressing a nonradiative
pathway mediated by the CT state. The near degeneracy of the N and
CT excited states can be understood by considering SKC-513 as a reduced
symmetry version of a parent molecule with 3-fold symmetry. Computations
show that acceptor–donor substituents can be used to alter
the relative energies of the N and CT state, whereas a methylene spacer
between the heterocycle and phenylene groups can be used to increase
the coupling between these states. These modifications provide synthetic
handles with which to optimize the dye for K+ detection.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.