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. By applying simple, interpretable, theoretically rooted transformations, the POM outperformed chemoinformatic models on several other odor prediction tasks, indicating that the POM successfully encoded a generalized map of structure-odor relationships. This approach broadly enables odor prediction and paves the way toward digitizing odors.

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 odors, 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. Using this olfactory representation (principal odor map [POM]), we find that odorous compounds with similar POM representations are more likely to co-occur within a substance and be metabolically closely related; metabolic reaction sequences (Caspi et al., 2014) also follow smooth paths in POM despite large jumps in molecular structure. Just as the brain's visual representations have evolved around the natural statistics of light and shapes, the natural statistics of metabolism appear to shape the brain's representation of the olfactory world.

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. We contribute a lightweight neural network model that quickly predicts mass spectra for small molecules, averaging 5 ms per molecule with a recall-at-10 accuracy of 91.8%. Achieving high-accuracy predictions requires a novel neural network architecture that is designed to capture typical fragmentation patterns from electron ionization. We analyze the effects of our modeling innovations on library matching performance and compare our models to prior machine-learning-based work on spectrum prediction.

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. The encoder converts the discrete representation of a molecule into a real-valued continuous vector, and the decoder converts these continuous vectors back to discrete molecular representations. The predictor estimates chemical properties from the latent continuous vector representation of the molecule. Continuous representations of molecules allow us to automatically generate novel chemical structures by performing simple operations in the latent space, such as decoding random vectors, perturbing known chemical structures, or interpolating between molecules. Continuous representations also allow the use of powerful gradient-based optimization to efficiently guide the search for optimized functional compounds. We demonstrate our method in the domain of drug-like molecules and also in a set of molecules with fewer that nine heavy atoms.

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. We combine this predictor with SMARTS transformations to build a system which, given a set of reagents and reactants, predicts the likely products. We test this method on problems from a popular organic chemistry textbook.

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 model is consistent with site-directed mutagenesis experiments and biochemical measurements of the receptor activation, and thus provides a valuable framework for further studies of the sense of smell at the molecular level.

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. The homology model is based on the crystal structure of squid rhodopsin (λ(max) = 490 nm) and shows a maximal absorbance (λ(max) = 447 nm) consistent with the observed absorption of the photoreceptor. The 43 nm spectral shift is due to an increased bond-length alternation of the protonated Schiff base of 11-cis-retinal chromophore, induced by N87Q mutation and water-mediated H-bonding interactions with the Schiff base linkage. These findings, analogous to spectral changes observed in the G89Q bovine rhodopsin mutant, suggest that single site mutations can convert photopigments into visual light sensors or nonvisual sensory photoreceptors.

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.i.). However, methods for dispensing multiple colourants or fabricating structural colour through plasmonic structures have insufficient resolution and limited scalability. Here, we present a non-colourant method that achieves bright-field colour prints with resolutions up to the optical diffraction limit. Colour information is encoded in the dimensional parameters of metal nanostructures, so that tuning their plasmon resonance determines the colours of the individual pixels. Our colour-mapping strategy produces images with both sharp colour changes and fine tonal variations, is amenable to large-volume colour printing via nanoimprint lithography, and could be useful in making microimages for security, steganography, nanoscale optical filters and high-density spectrally encoded optical data storage.