Predicting emergence of crystals from amorphous precursors with deep learning potentials.

Crystallization of amorphous precursors into metastable crystals plays a fundamental role in the formation of new matter, from geological to biological processes in nature to the synthesis and development of new materials in the laboratory. Reliably predicting the outcome of such a process would enable new research directions in these areas, but has remained beyond the reach of molecular modeling or ab initio methods. Here we show that candidates for the crystallization products of amorphous precursors can be predicted in many inorganic systems by sampling the local structural motifs at the atomistic level using universal deep learning interatomic potentials.

A principal odor map unifies diverse tasks in olfactory perception.

Mapping molecular structure to odor perception is a key challenge in olfaction. We used graph neural networks to generate a principal odor map (POM) that preserves perceptual relationships and enables odor quality prediction for previously uncharacterized odorants. The model was as reliable as a human in describing odor quality: On a prospective validation set of 400 out-of-sample odorants, the model-generated odor profile more closely matched the trained panel mean than did the median panelist.

Metabolic activity organizes olfactory representations.

Hearing and vision sensory systems are tuned to the natural statistics of acoustic and electromagnetic energy on earth and are evolved to be sensitive in ethologically relevant ranges. But what are the natural statistics of , and how do olfactory systems exploit them? Dissecting an accurate machine learning model (Lee et al., 2022) for human odor perception, we find a computable representation for odor at the molecular level that can predict the odor-evoked receptor, neural, and behavioral responses of nearly all terrestrial organisms studied in olfactory neuroscience.

Rapid Prediction of Electron-Ionization Mass Spectrometry Using Neural Networks.

When confronted with a substance of unknown identity, researchers often perform mass spectrometry on the sample and compare the observed spectrum to a library of previously collected spectra to identify the molecule. While popular, this approach will fail to identify molecules that are not in the existing library. In response, we propose to improve the library's coverage by augmenting it with synthetic spectra that are predicted from candidate molecules using machine learning.

Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules.

We report a method to convert discrete representations of molecules to and from a multidimensional continuous representation. This model allows us to generate new molecules for efficient exploration and optimization through open-ended spaces of chemical compounds. A deep neural network was trained on hundreds of thousands of existing chemical structures to construct three coupled functions: an encoder, a decoder, and a predictor.

Neural Networks for the Prediction of Organic Chemistry Reactions.

Reaction prediction remains one of the major challenges for organic chemistry and is a prerequisite for efficient synthetic planning. It is desirable to develop algorithms that, like humans, "learn" from being exposed to examples of the application of the rules of organic chemistry. We explore the use of neural networks for predicting reaction types, using a new reaction fingerprinting method.

Phosphorylated S6 kinase and S6 ribosomal protein are diagnostic markers of antibody-mediated rejection in heart allografts.

Background: Anti-MHC Class I alloantibodies have been implicated in the processes of acute and chronic rejection. These antibodies (Ab) bind to endothelial cells (EC) and transduce signals leading to the activation of cell survival and proliferation pathways, including Src, FAK and mTOR, as well as downstream targets ERK, S6 kinase (S6K) and S6 ribosomal protein (S6RP). We tested the hypothesis that phosphorylation of S6K, S6RP and ERK in capillary endothelium may serve as an adjunct diagnostic tool for antibody-mediated rejection (AMR) in heart allografts.

QM/MM model of the mouse olfactory receptor MOR244-3 validated by site-directed mutagenesis experiments.

Understanding structure/function relationships of olfactory receptors is challenging due to the lack of x-ray structural models. Here, we introduce a QM/MM model of the mouse olfactory receptor MOR244-3, responsive to organosulfur odorants such as (methylthio)methanethiol. The binding site consists of a copper ion bound to the heteroatoms of amino-acid residues H105, C109, and N202.

The active site of melanopsin: the biological clock photoreceptor.

The nonvisual ocular photoreceptor melanopsin, found in the neurons of vertebrate inner retina, absorbs blue light and triggers the "biological clock" of mammals by activating the suprachiasmatic nuclei (a small region of the brain that regulates the circadian rhythms of neuronal and hormonal activities over 24 h cycles). The structure of melanopsin, however, has yet to be established. Here, we propose for the first time a structural model of the active site of mouse melanopsin.

Printing colour at the optical diffraction limit.

The highest possible resolution for printed colour images is determined by the diffraction limit of visible light. To achieve this limit, individual colour elements (or pixels) with a pitch of 250 nm are required, translating into printed images at a resolution of ∼100,000 dots per inch (d.p.