Neoantigens, arising from somatic mutations, have the potential to induce immune responses against tumor cells. As natural neoantigens that drive immune responses are uncommon, some methods to optimize neoantigens have been devised, leading to "heteroclitic" neoantigens capable of triggering cross-immunization. Existing methods, however, concentrate exclusively on the affinity of neoantigens for human leukocyte antigen (HLA), while neglecting the enhancement of their immunogenicity. Here, we developed a machine learning-based method, Naso, which integrates simulated annealing search and multi-objective training to optimize the immunogenicity of neoantigens. We also designed a search space optimization strategy to improve search efficiency. Experimental evaluation demonstrated that Naso outperforms existing methods in enhancing the immunogenicity of neoantigens. Specifically, Naso can transform nonimmunoreactive neoantigens into immunoreactive ones with no more than three mutation amino acids. Moreover, Naso can obtain competitive results in other immunological features, such as binding affinity and presentation. Consequently, Naso-optimized neoantigens can elicit an immune response and facilitate cross-immunization, thereby promoting the development of heteroclitic neoantigen-based vaccines. The source code of Naso is available at https://github.com/lyotvincent/Naso.

MOTIVATION: Fine-grained cellular characterization provides critical insights into biological processes, including tissue development, disease progression, and treatment responses. The spatial organization of cells and the interactions among distinct cell types play a pivotal role in shaping the tumor micro-environment, driving heterogeneity, and influencing patient prognosis. While computational pathology can uncover morphological structures from tissue images, conventional methods are often restricted to identifying coarse-grained and limited cell types. In contrast, spatial transcriptomics-based approaches hold promise for pinpointing fine-grained transcriptional cell types using histology data. However, these methods tend to overlook key molecular signatures inherent in gene expression data. RESULTS: To this end, we propose a cross-modal unified representation learning framework (CUCA) for identifying fine-grained cell types from histology images. CUCA is trained on paired morphology-molecule spatial transcriptomics data, enabling it to infer fine-grained cell types solely from pathology images. Our model aims to harness the cross-modal embedding alignment paradigm to harmonize the embedding spaces of morphological and molecular modalities, bridging the gap between image patterns and molecular expression signatures. Extensive results across three datasets show that CUCA captures molecule-enhanced cross-modal representations and improves the prediction of fine-grained transcriptional cell abundances. Downstream analyses of cellular spatial architectures and intercellular co-localization reveal that CUCA provides insights into tumor biology, offering potential advancements in cancer research. AVAILABILITY AND IMPLEMENTATION: The source code of CUCA is available in Zenodo: 10.5281/zenodo.15087256.

Understanding the three-dimensional (3D) architecture of chromatin is pivotal for unraveling gene regulation and cellular processes. Currently, a wealth of data on chromatin interactions, such as ChIA-PET sequencing data, is increasingly accessible. However, challenges persist in comparative analyses of these chromatin interactions. Specifically, accurately identifying differential chromatin interactions (DCIs) remains challenging, yet it is crucial for studying gene expression differences during cellular differentiation. Additionally, assessing the inter-sample reproducibility at the sample level, which is a fundamental indicator of the reliability and consistency of replicate experiments, still lacks a computational method. In this work, we present AREDCI, a novel approach integrating data preprocessing, normalization, reproducibility assessment, and DCI identification. By leveraging multiple normalization techniques and developing a self-similarity-based reproducibility algorithm, AREDCI offers a robust evaluation of sample consistency. Additionally, AREDCI designs algorithms based on Kernel Density Estimation (KDE) and local contextual information to enhance the accuracy and reliability of DCI identification. Experimental evaluations demonstrate that AREDCI outperforms existing methods in both reproducibility assessment and DCI identification. Through experiments on simulated and real-world datasets, AREDCI exhibits commendable precision and recall, showcasing its effectiveness in analyzing chromatin interaction data. Notably, AREDCI successfully identifies significant DCIs during mouse cell differentiation, aligning with known biological processes and molecular functions.

MOTIVATION: Human epidermal growth factor receptor 2 (HER2) status identification enables physicians to assess the prognosis risk and determine the treatment schedule for patients. In clinical practice, pathological slides serve as the gold standard, offering morphological information on cellular structure and tumoral regions. Computational analysis of pathological images has the potential to discover morphological patterns associated with HER2 molecular targets and achieve precise status prediction. However, pathological images are typically equipped with high-resolution attributes, and HER2 expression in breast cancer (BC) images often manifests the intratumoral heterogeneity. RESULTS: We present a phenotype-informed weakly supervised multiple instance learning architecture (PhiHER2) for the prediction of the HER2 status from pathological images of BC. Specifically, a hierarchical prototype clustering module is designed to identify representative phenotypes across whole slide images. These phenotype embeddings are then integrated into a cross-attention module, enhancing feature interaction and aggregation on instances. This yields a phenotype-based feature space that leverages the intratumoral morphological heterogeneity for HER2 status prediction. Extensive results demonstrate that PhiHER2 captures a better WSI-level representation by the typical phenotype guidance and significantly outperforms existing methods on real-world datasets. Additionally, interpretability analyses of both phenotypes and WSIs provide explicit insights into the heterogeneity of morphological patterns associated with molecular HER2 status. AVAILABILITY AND IMPLEMENTATION: Our model is available at https://github.com/lyotvincent/PhiHER2.

Inductive link prediction for knowledge graph aims at predicting missing links between unseen entities, those not shown in training stage. Most previous works learn entity-specific embeddings of entities, which cannot handle unseen entities. Recent several methods utilize enclosing subgraph to obtain inductive ability. However, all these works only consider the enclosing part of subgraph without complete neighboring relations, which leads to the issue that partial neighboring relations are neglected, and sparse subgraphs are hard to be handled. To address that, we propose Subgraph Neighboring Relations Infomax, SNRI, which sufficiently exploits complete neighboring relations from two aspects: neighboring relational feature for node feature and neighboring relational path for sparse subgraph. To further model neighboring relations in a global way, we innovatively apply mutual information (MI) maximization for knowledge graph. Experiments show that SNRI outperforms existing state-of-art methods by a large margin on inductive link prediction task, and verify the effectiveness of exploring complete neighboring relations in a global way to characterize node features and reason on sparse subgraphs.

High-power magnetically coupled resonant (MCR) bidirectional wireless power transfer (BWPT) within long distance can be potentially used in various applications. However, the coupling between transmission coils will drastically decrease with the rise of distance to diameter (d-D) ratio, and voltage/current stresses on resonant components tend to increase apparently, which further deteriorate the system efficiency and stability. In this paper, the relationship between the coupling coefficient and the d-D ratio in high-power BWPT systems is analyzed by mathematics methods. The correlations of transferred power and system efficiency with d-D ratio are presented consequently. The scheme of coils magnetic concentration and double-layer coils in parallel is adopted to improve the system performance. The theoretical analysis is demonstrated by the experimental results of a 2kW prototype, and the system efficiency is improved from 70.7% to 77.47% under the d-D ratio of 1 (300mm-300mm).

Nowadays, the magnetically coupled resonant (MCR) wireless power transfer (WPT) system are mostly the single-source or single-load systems that operate at “one to one” mode. With the increasing number of electrical equipment and types of input sources, the “one to one” mode cannot meet the application requirements. Therefore, the "one-to-many" and "many-to-many" WPT become increasingly important. In this paper, a three-port MCR wireless energy router (Wi E-Router) architecture with dual sources and dual loads is investigated in detail, which allows power transfer among dual sources and dual loads wirelessly. The equivalent circuit model of the system is built to analyze its transfer characteristics. Moreover, an effective power management strategy for a variety of input power cases is proposed. Finally, the theoretical analysis is validated by the experimental results from a 600 W prototype.

Nowadays, bidirectional wireless power transfer (BWPT) technology has caused increasingly concern, but its application is greatly limited when the number of sources and loads increases. In this paper, the concept of multi-port wireless energy router (Wi E-Router) is proposed to realize energy transfer wirelessly among multiple sources and loads for the multi-source and multi-load wireless power transfer (WPT) applications. Specifically, a three-port magnetically coupling resonant (MCR) Wi E-Router with LCC hybrid compensation network is investigated in detail. The equivalent circuit model of the three-port Wi E-Router is built and the power transfer characteristics are analyzed. Based on the circuit model, the relationships between the power magnitude as well as flowing direction and the shifted phase among or inside multiple ports are revealed. Moreover, a zero-power-flow control scheme is put forward for the case when one port quits from the system. By regulating the outer shifted phase, the power transfer among other ports can still be realized when the idling port achieves zero power flow. Finally, the validity of the above theoretical analysis is verified by experiments.