Spatial transcriptomics technologies are used to profile transcriptomes while preserving spatial information, which enables high-resolution characterization of transcriptional patterns and reconstruction of tissue architecture. Due to the existence of low-resolution spots in recent spatial transcriptomics technologies, uncovering cellular heterogeneity is crucial for disentangling the spatial patterns of cell types, and many related methods have been proposed. Here, we benchmark 18 existing methods resolving a cellular deconvolution task with 50 real-world and simulated datasets by evaluating the accuracy, robustness, and usability of the methods. We compare these methods comprehensively using different metrics, resolutions, spatial transcriptomics technologies, spot numbers, and gene numbers. In terms of performance, CARD, Cell2location, and Tangram are the best methods for conducting the cellular deconvolution task. To refine our comparative results, we provide decision-tree-style guidelines and recommendations for method selection and their additional features, which will help users easily choose the best method for fulfilling their concerns.

Modern machine learning models toward various tasks with omic data analysis give rise to threats of privacy leakage of patients involved in those datasets. Here, we proposed a secure and privacy-preserving machine learning method (PPML-Omics) by designing a decentralized differential private federated learning algorithm. We applied PPML-Omics to analyze data from three sequencing technologies and addressed the privacy concern in three major tasks of omic data under three representative deep learning models. We examined privacy breaches in depth through privacy attack experiments and demonstrated that PPML-Omics could protect patients’ privacy. In each of these applications, PPML-Omics was able to outperform methods of comparison under the same level of privacy guarantee, demonstrating the versatility of the method in simultaneously balancing the privacy-preserving capability and utility in omic data analysis. Furthermore, we gave the theoretical proof of the privacy-preserving capability of PPML-Omics, suggesting the first mathematically guaranteed method with robust and generalizable empirical performance in protecting patients’ privacy in omic data.

Unveiling the heterogeneity in the tissues is crucial to explore cell–cell interactions and cellular targets of human diseases. Spatial transcriptomics (ST) supplies spatial gene expression profile which has revolutionized our biological understanding, but variations in cell-type proportions of each spot with dozens of cells would confound downstream analysis. Therefore, deconvolution of ST has been an indispensable step and a technical challenge toward the higher-resolution panorama of tissues. Here, we propose a novel ST deconvolution method called SD² integrating spatial information of ST data and embracing an important characteristic, dropout, which is traditionally considered as an obstruction in single-cell RNA sequencing data (scRNA-seq) analysis. First, we extract the dropout-based genes as informative features from ST and scRNA-seq data by fitting a Michaelis–Menten function. After synthesizing pseudo-ST spots by randomly composing cells from scRNA-seq data, auto-encoder is applied to discover low-dimensional and non-linear representation of the real- and pseudo-ST spots. Next, we create a graph containing embedded profiles as nodes, and edges determined by transcriptional similarity and spatial relationship. Given the graph, a graph convolutional neural network is used to predict the cell-type compositions for real-ST spots. We benchmark the performance of SD² on the simulated seqFISH+ dataset with different resolutions and measurements which show superior performance compared with the state-of-the-art methods. SD² is further validated on three real-world datasets with different ST technologies and demonstrates the capability to localize cell-type composition accurately with quantitative evidence. Finally, ablation study is conducted to verify the contribution of different modules proposed in SD². The SD² is freely available in github (https://github.com/leihouyeung/SD2) and Zenodo (https://doi.org/10.5281/zenodo.7024684). Supplementary data are available at Bioinformatics online.

While the abilities of language models are thoroughly evaluated in areas like general domains and biomedicine, academic chemistry remains less explored. Chemical QA tools also play a crucial role in both education and research by effectively translating complex chemical information into an understandable format. Addressing this gap, we introduce ScholarChemQA, a large-scale QA dataset constructed from chemical papers. Specifically, the questions are from paper titles with a question mark, and the multi-choice answers are reasoned out based on the corresponding abstracts. This dataset reflects typical real-world challenges, including an imbalanced data distribution and a substantial amount of unlabeled data that can be potentially useful. Correspondingly, we introduce a ChemMatch model, specifically designed to effectively answer chemical questions by fully leveraging our collected data. Experiments show that Large Language Models (LLMs) still have significant room for improvement in the field of chemistry. Moreover, ChemMatch significantly outperforms recent similar-scale baselines: https://github.com/iriscxy/chemmatch.

Brain metastasis (BM) frequently occurs in advanced non-small cell lung cancer (NSCLC) and is associated with poor clinical prognosis. Due to the location of metastatic lesions, the surgical resection is limited and the chemotherapy is ineffective because of the existence of the blood brain barrier (BBB). Therefore, it is essential to enhance our understanding about the underlying mechanisms associated with brain metastasis in NSCLC. In the present study, we explored the RNA-Seq data of brain metastasis cells from the GEO database, and extracted RNA collected from primary NSCLC tumors as well as paired brain metastatic lesions followed by microRNA PCR array. Meanwhile, we improved the in vivo model and constructed a cancer stem cell-derived transplantation model of brain metastasis in mice. Our data indicated that the level of miR-596-3p is high in primary NSCLC tumors, but significantly downregulated in the brain metastatic lesion. The prediction target of microRNA suggested that miR-596-3p was considered to modulate two genes essential in the brain invasion process, YAP1 and IL-8 that restrain the invasion of cancer cells and permeability of BBB, respectively. Moreover, in vivo experiments suggested that our model mimics the clinical aspect of NSCLC and improves the success ratio of brain metastasis model. The results demonstrated that miR-596-3p significantly inhibited the capacity of NSCLC cells to metastasize to the brain. Furthermore, these finding elucidated that miR-596-3p exerts a critical role in brain metastasis of NSCLC by modulating the YAP1-IL8 network, and this miRNA axis may provide a potential therapeutic strategy for brain metastasis.

Macrocyclic peptides hold great promise as therapeutics targeting intracellular proteins. This stems from their remarkable ability to bind flat protein surfaces with high affinity and specificity while potentially traversing the cell membrane. Research has already explored their use in developing inhibitors for intracellular proteins, such as KRAS, a well-known driver in various cancers. However, computational approaches for de novo macrocyclic peptide design remain largely unexplored. Here, we introduce HELM-GPT, a novel method that combines the strength of the hierarchical editing language for macromolecules (HELM) representation and generative pre-trained transformer (GPT) for de novo macrocyclic peptide design. Through reinforcement learning (RL), our experiments demonstrate that HELM-GPT has the ability to generate valid macrocyclic peptides and optimize their properties. Furthermore, we introduce a contrastive preference loss during the RL process, further enhanced the optimization performance. Finally, to co-optimize peptide permeability and KRAS binding affinity, we propose a step-by-step optimization strategy, demonstrating its effectiveness in generating molecules fulfilling both criteria. In conclusion, the HELM-GPT method can be used to identify novel macrocyclic peptides to target intracellular proteins. The code and data of HELM-GPT are freely available on GitHub (https://github.com/charlesxu90/helm-gpt).