MFLOGP, a new method for determining a single component octanol–water partition coefficients (
In this work, we aim to accurately predict the number of hospitalizations during the COVID19 pandemic by developing a spatiotemporal prediction model. We propose HOIST, an Ising dynamicsbased deep learning model for spatiotemporal COVID19 hospitalization prediction. By drawing the analogy between locations and lattice sites in statistical mechanics, we use the Ising dynamics to guide the model to extract and utilize spatial relationships across locations and model the complex influence of granular information from realworld clinical evidence. By leveraging rich linked databases, including insurance claims, census information, and hospital resource usage data across the U.S., we evaluate the HOIST model on the largescale spatiotemporal COVID19 hospitalization prediction task for 2299 counties in the U.S. In the 4week hospitalization prediction task, HOIST achieves 368.7 mean absolute error, 0.6
 NSFPAR ID:
 10416645
 Publisher / Repository:
 Nature Publishing Group
 Date Published:
 Journal Name:
 Nature Communications
 Volume:
 14
 Issue:
 1
 ISSN:
 20411723
 Format(s):
 Medium: X
 Sponsoring Org:
 National Science Foundation
More Like this

Abstract ) is presented which uses molecular formula as the only input. Octanol–water partition coefficients are useful in many applications, ranging from environmental fate and drug delivery. Currently, partition coefficients are either experimentally measured or predicted as a function of structural fragments, topological descriptors, or thermodynamic properties known or calculated from precise molecular structures. The MFLOGP method presented here differs from classical methods as it does not require any structural information and uses molecular formula as the sole model input. MFLOGP is therefore useful for situations in which the structure is unknown or where the use of a low dimensional, easily automatable, and computationally inexpensive calculations is required. MFLOGP is a random forest algorithm that is trained and tested on 15,377 data points, using 10 features derived from the molecular formula to make$$LogP$$ $\mathrm{LogP}$ predictions. Using an independent validation set of 2713 data points, MFLOGP was found to have an average$$LogP$$ $\mathrm{LogP}$ = 0.77 ± 0.007,$$RMSE$$ $\mathrm{RMSE}$ = 0.52 ± 0.003, and$$MAE$$ $\mathrm{MAE}$ = 0.83 ± 0.003. This performance fell within the spectrum of performances reported in the published literature for conventional higher dimensional models ($${R}^{2}$$ ${R}^{2}$ = 0.42–1.54,$$RMSE$$ $\mathrm{RMSE}$ = 0.09–1.07, and$$MAE$$ $\mathrm{MAE}$ = 0.32–0.95). Compared with existing models, MFLOGP requires a maximum of ten features and no structural information, thereby providing a practical and yet predictive tool. The development of MFLOGP provides the groundwork for development of more physical prediction models leveraging big data analytical methods or complex multicomponent mixtures.$${R}^{2}$$ ${R}^{2}$Graphical Abstract 
Abstract Developing prediction models for emerging infectious diseases from relatively small numbers of cases is a critical need for improving pandemic preparedness. Using COVID19 as an exemplar, we propose a transfer learning methodology for developing predictive models from multimodal electronic healthcare records by leveraging information from more prevalent diseases with shared clinical characteristics. Our novel hierarchical, multimodal model (
) integrates baseline risk factors from the natural language processing of clinical notes at admission, timeseries measurements of biomarkers obtained from laboratory tests, and discrete diagnostic, procedure and drug codes. We demonstrate the alignment of$${\textsc {TransMED}}$$ $TRANS\mathrm{MED}$ ’s predictions with wellestablished clinical knowledge about COVID19 through univariate and multivariate risk factor driven subcohort analysis.$${\textsc {TransMED}}$$ $TRANS\mathrm{MED}$ ’s superior performance over stateoftheart methods shows that leveraging patient data across modalities and transferring prior knowledge from similar disorders is critical for accurate prediction of patient outcomes, and this approach may serve as an important tool in the early response to future pandemics.$${\textsc {TransMED}}$$ $TRANS\mathrm{MED}$ 
Abstract Extending computational harmonic analysis tools from the classical setting of regular lattices to the more general setting of graphs and networks is very important, and much research has been done recently. The generalized Haar–Walsh transform (GHWT) developed by Irion and Saito (2014) is a multiscale transform for signals on graphs, which is a generalization of the classical Haar and Walsh–Hadamard transforms. We propose the
extended generalized Haar–Walsh transform (eGHWT), which is a generalization of the adapted time–frequency tilings of Thiele and Villemoes (1996). The eGHWT examines not only the efficiency of graphdomain partitions but also that of “sequencydomain” partitionssimultaneously . Consequently, the eGHWT and its associated bestbasis selection algorithm for graph signals significantly improve the performance of the previous GHWT with the similar computational cost, , where$$O(N \log N)$$ $O(NlogN)$N is the number of nodes of an input graph. While the GHWT bestbasis algorithm seeks the most suitable orthonormal basis for a given task among more than possible orthonormal bases in$$(1.5)^N$$ ${\left(1.5\right)}^{N}$ , the eGHWT bestbasis algorithm can find a better one by searching through more than$$\mathbb {R}^N$$ ${R}^{N}$ possible orthonormal bases in$$0.618\cdot (1.84)^N$$ $0.618\xb7{\left(1.84\right)}^{N}$ . This article describes the details of the eGHWT bestbasis algorithm and demonstrates its superiority using several examples including genuine graph signals as well as conventional digital images viewed as graph signals. Furthermore, we also show how the eGHWT can be extended to 2D signals and matrixform data by viewing them as a tensor product of graphs generated from their columns and rows and demonstrate its effectiveness on applications such as image approximation.$$\mathbb {R}^N$$ ${R}^{N}$ 
Abstract We prove multipoint correlation bounds in
for arbitrary$$\mathbb {Z}^d$$ ${Z}^{d}$ with symmetrized distances, answering open questions proposed by Sims–Warzel (Commun Math Phys 347(3):903–931, 2016) and Aza–Bru–Siqueira Pedra (Commun Math Phys 360(2):715–726, 2018). As applications, we prove multipoint correlation bounds for the Ising model on$$d\ge 1$$ $d\ge 1$ , and multipoint dynamical localization in expectation for uniformly localized disordered systems, which provides the first examples of this conjectured phenomenon by Bravyi–König (Commun Math Phys 316(3):641–692, 2012) .$$\mathbb {Z}^d$$ ${Z}^{d}$ 
Abstract We present the first unquenched latticeQCD calculation of the form factors for the decay
at nonzero recoil. Our analysis includes 15 MILC ensembles with$$B\rightarrow D^*\ell \nu $$ $B\to {D}^{\ast}\ell \nu $ flavors of asqtad sea quarks, with a strange quark mass close to its physical mass. The lattice spacings range from$$N_f=2+1$$ ${N}_{f}=2+1$ fm down to 0.045 fm, while the ratio between the light and the strangequark masses ranges from 0.05 to 0.4. The valence$$a\approx 0.15$$ $a\approx 0.15$b andc quarks are treated using the Wilsonclover action with the Fermilab interpretation, whereas the light sector employs asqtad staggered fermions. We extrapolate our results to the physical point in the continuum limit using rooted staggered heavylight meson chiral perturbation theory. Then we apply a modelindependent parametrization to extend the form factors to the full kinematic range. With this parametrization we perform a joint latticeQCD/experiment fit using several experimental datasets to determine the CKM matrix element . We obtain$$V_{cb}$$ ${V}_{\mathrm{cb}}$ . The first error is theoretical, the second comes from experiment and the last one includes electromagnetic and electroweak uncertainties, with an overall$$\left V_{cb}\right = (38.40 \pm 0.68_{\text {th}} \pm 0.34_{\text {exp}} \pm 0.18_{\text {EM}})\times 10^{3}$$ $\left({V}_{\mathrm{cb}}\right)=(38.40\pm 0.{68}_{\text{th}}\pm 0.{34}_{\text{exp}}\pm 0.{18}_{\text{EM}})\times {10}^{3}$ , which illustrates the tensions between the experimental data sets, and between theory and experiment. This result is in agreement with previous exclusive determinations, but the tension with the inclusive determination remains. Finally, we integrate the differential decay rate obtained solely from lattice data to predict$$\chi ^2\text {/dof} = 126/84$$ ${\chi}^{2}\text{/dof}=126/84$ , which confirms the current tension between theory and experiment.$$R(D^*) = 0.265 \pm 0.013$$ $R\left({D}^{\ast}\right)=0.265\pm 0.013$