A novel method for atomization energy prediction based on natural-parameter network

Atomization energy(AE)is an important indicator for measuring material stability and reactivity,which refers to the energy change when a polyatomic molecule decomposes into its constituent atoms.Predicting AE based on the structural information of molecules has been a focus of researchers,but existing methods have limitations such as being time-consuming or requiring complex preprocessing and large amounts of training data.Deep learning(DL),a new branch of machine learning(ML),has shown promise in learning internal rules and hierarchical representations of sample data,making it a potential solution for AE prediction.To address this problem,we propose a natural-parameter network(NPN)approach for AE prediction.This method establishes a clearer statistical interpretation of the relationship between the network’s output and the given data.We use the Coulomb matrix(CM)method to represent each compound as a structural information matrix.Furthermore,we also designed an end-to-end predictive model.Experimental results demonstrate that our method achieves excellent performance on the QM7 and BC2P datasets,and the mean absolute error(MAE)obtained on the QM7 test set ranges from 0.2 kcal/mol to 3 kcal/mol.The optimal result of our method is approximately an order of magnitude higher than the accuracy of 3 kcal/mol in published works.Additionally,our approach significantly accelerates the prediction time.Overall,this study presents a promising approach to accelerate the process of predicting structures using DL,and provides a valuable contribution to the field of chemical energy prediction.

Investigating the Immunogenic Cell Death‑Dependent Subtypes and Prognostic Signature of Triple‑Negative Breast Cancer

Recently,immunotherapy has emerged as a promising and efective method for treating triple-negative breast cancer(TNBC).However,challenges still persist.Immunogenic cell death(ICD)is considered a prospective treatment and potential combinational treatment strategy as it induces an anti-tumor immune response by presenting the antigenic epitopes of dead cells.Nevertheless,the ICD process in TNBC and its impact on disease progression and the response to immunotherapy are not well understood.In this study,we observed dysregulation of the ICD process and verifed the altered expression of prognostic ICD genes in TNBC through quantitative real-time polymerase chain reaction(qRT-PCR)analysis.To investigate the potential role of the ICD process in TNBC progression,we determined the ICD-dependent subtypes,and two were identifed.Analysis of their distinct tumor immune microenvironment(TIME)and cancer hallmark features revealed that Cluster 1 and 2 corresponded to the immune“cold”and“hot”phenotypes,respectively.In addition,we constructed the prognostic signature ICD score of TNBC patients and demonstrated its clinical independence and generalizability.The ICD score could also serve as a potential biomarker for immune checkpoint blockade and may aid in the identifcation of targeted efective agents for individualized clinical strategies.

Autonomous navigation method and technology implementation of high-precision solar spectral velocity measurement

The velocity information of spacecraft can be directly obtained by the autonomous navigation method based on astronomical spectral velocity measurement. It provides complete direct velocity measurement information for the traditional navigation methods represented by astronomical angle measurement and astronomical ranging, which is of great significance for spacecraft high precision autonomous navigation. This paper comprehensively introduces the principle and navigation method of astronomical spectral velocity measurement, as well as the technical realization of the solar atomic frequency discriminator for autonomous navigation(SAFDAN) based on atomic frequency discrimination velocity measurement. The new SAFDAN is the first instrument to measure the Doppler velocity of spacecraft relative to the Sun. Carried by the CHASE mission, the in-orbit experiment of the SAFDAN is realized, and the in-orbit velocity measurement accuracy reaches 1.93 m/s, which effectively verifies the feasibility of the astronomical spectral velocity measurement method and technology.