Search

The computer-assisted inverse design of photonic computing, especially by leveraging artificial intelligence algorithms, offers great convenience to accelerate the speed of development and improve calculation accuracy. However, traditional thickness-based modulation methods are hindered by large volume and difficult fabrication process, making it hard to meet the data-driven requirements of flexible light modulation. Here, we propose a diffractive deep neural network (D2NN) framework based on a three-layer all-dielectric phased transmitarray as hidden layers, which can perform the classification of handwritten digits. By tailoring the radius of a silicon nanodisk of a meta-atom, the metasurface can realize the phase profile calculated by D2NN and maintain a relative high transmittance of 0.9 at a wavelength of 600 nm. The designed image classifier consists of three layers of phase-only metasurfaces, each of which contains 1024 units, mimicking a fully connected neural network through the diffraction of light fields. The classification task of handwriting digits from the ‘0’ to ‘5’ dataset is verified, with an accuracy of over 90% on the blind test dataset, as well as demonstrated by the full-wave simulation. Furthermore, the performance of the more complex animal image classification task is also validated by increasing the number of neurons to enhance the connectivity of the neural network. This study may provide a possible solution for practical applications such as biomedical detection, image processing, and machine vision based on all-optical computing.

Abstract Lipophilicity is a fundamental physical property that significantly affects various aspects of drug behavior, including solubility, permeability, metabolism, distribution, protein binding, and toxicity. Accurate prediction of lipophilicity, measured by the logD7.4 value (the distribution coefficient between n-octanol and buffer at physiological pH 7.4), is crucial for successful drug discovery and design. However, the limited availability of data for logD modeling poses a significant challenge to achieving satisfactory generalization capability. To address this challenge, we have developed a novel logD7.4 prediction model called RTlogD, which leverages knowledge from multiple sources. RTlogD combines pre-training on a chromatographic retention time (RT) dataset since the RT is influenced by lipophilicity. Additionally, microscopic pKa values are incorporated as atomic features, providing valuable insights into ionizable sites and ionization capacity. Furthermore, logP is integrated as an auxiliary task within a multitask learning framework. We conducted ablation studies and presented a detailed analysis, showcasing the effectiveness and interpretability of RT, pKa, and logP in the RTlogD model. Notably, our RTlogD model demonstrated superior performance compared to commonly used algorithms and prediction tools. These results underscore the potential of the RTlogD model to improve the accuracy and generalization of logD prediction in drug discovery and design. In summary, the RTlogD model addresses the challenge of limited data availability in logD modeling by leveraging knowledge from RT, microscopic pKa, and logP. Incorporating these factors enhances the predictive capabilities of our model, and it holds promise for real-world applications in drug discovery and design scenarios. Graphical Abstract

Abstract Three-dimensional (3D) conformations of a small molecule profoundly affect its binding to the target of interest, the resulting biological effects, and its disposition in living organisms, but it is challenging to accurately characterize the conformational ensemble experimentally. Here, we proposed an autoregressive torsion angle prediction model Tora3D for molecular 3D conformer generation. Rather than directly predicting the conformations in an end-to-end way, Tora3D predicts a set of torsion angles of rotatable bonds by an interpretable autoregressive method and reconstructs the 3D conformations from them, which keeps structural validity during reconstruction. Another advancement of our method over other conformational generation methods is the ability to use energy to guide the conformation generation. In addition, we propose a new message-passing mechanism that applies the Transformer to the graph to solve the difficulty of remote message passing. Tora3D shows superior performance to prior computational models in the trade-off between accuracy and efficiency, and ensures conformational validity, accuracy, and diversity in an interpretable way. Overall, Tora3D can be used for the quick generation of diverse molecular conformations and 3D-based molecular representation, contributing to a wide range of downstream drug design tasks. Graphical Abstract

Synthetic lethal (SL) pairs are pairs of genes whose simultaneous loss-of-function results in cell death, while a damaging mutation of either gene alone does not affect the cell’s survival. This makes SL pairs attractive targets for precision cancer therapies, as targeting the unimpaired gene of the SL pair can selectively kill cancer cells that already harbor the impaired gene. Limited by the difficulty of finding true SL pairs, especially on specific cell types, current computational approaches provide only limited insights because of overlooking the crucial aspects of cellular context dependency and mechanistic understanding of SL pairs. As a result, the identification of SL targets still relies on expensive, time-consuming experimental approaches. In this work, we applied cell-line specific multi-omics data to a specially designed deep learning model to predict cell-line specific SL pairs. Through incorporating multiple types of cell-specific omics data with a self-attention module, we represent gene relationships as graphs. Our approach achieves the prediction of SL pairs in a cell-specific manner and demonstrates the potential to facilitate the discovery of cell-specific SL targets for cancer therapeutics, providing a tool to unearth mechanisms underlying the origin of SL in cancer biology. The code and data of our approach can be found at https://github.com/promethiume/SLwise

Parity-time (PT) symmetric photonic systems have attracted much attention due to their intriguing properties and asymmetric behaviors. In this paper, we propose a plasmonic nanoantenna with PT-symmetric potential for unidirectional scattering functionality. The studied plasmonic nanoantenna is comprised of three metallic layers separated by two dielectric layers. Such kind of system, with the same coefficient κ of loss and gain in each of the two dielectric layers, holds the characteristic of PT symmetry. We show that the unidirectional scattering is obtained for the passive structure (i.e., κ = 0), and the switching between forward and backward directionality can be achieved with a single structure by changing the excitation wavelength, when the induced electric dipole (ED) and magnetic dipole (MD) modes satisfy the first or second Kerker conditions, respectively. In addition, we find that the forward-to-backward ratio spectra can be strongly affected by the non-Hermiticity parameter κ. In particular, it is possible to reverse the radiation direction at the same wavelength in a wide spectra band by adjusting κ. Moreover, putting the nanoantennas in an array of transverse configuration can efficiently narrow the main lobe angular beam width to be

In this paper, we propose a hybrid metallo-dielectric core-shell nanorod for the Kerker-type effect at two different frequencies. The effect arises from the interference of the scattering waves of the nanorod, which are generated by the magnetic dipole moment (MD) of the high-index hollow particle and the electric dipole moment (ED) induced in both metallic and dielectric particles. Interestingly, we find that such kind of unidirectional radiation properties, (i.e., zero back scattering occurring at dual frequencies) can be sustained with a single nanorod, which usually being equivalent to a local electric dipole source. The effect of substrate is also considered to investigate the typical experimental realization for the dual-frequency unidirectionalities of the nanoantenna. Furthermore, the unidirectionality can be further improved by the design of one-dimensional array of the hybrid nanoantenna. Our results could provide an additional degree of freedom for light scattering manipulation, and widen the versatile applications in nanoantennas, optical sensor, light emitters, as well as photovoltaic devices.

Recently, the study of analog optical computing raised renewed interest due to its natural advantages of parallel, high speed and low energy consumption over conventional digital counterpart, particularly in applications of big data and high-throughput image processing. The emergence of metamaterials or metasurfaces in the last decades offered unprecedented opportunities to arbitrarily manipulate the light waves within subwavelength scale. Metamaterials and metasurfaces with freely controlled optical properties have accelerated the progress of wave-based analog computing and are emerging as a practical, easy-integration platform for optical analog computing. In this review, the recent progress of metamaterial-based spatial analog optical computing is briefly reviewed. We first survey the implementation of classical mathematical operations followed by two fundamental approaches (metasurface approach and Green’s function approach). Then, we discuss recent developments based on different physical mechanisms and the classical optical simulating of quantum algorithms are investigated, which may lead to a new way for high-efficiency signal processing by exploiting quantum behaviors. The challenges and future opportunities in the booming research field are discussed.