Cell-cell communication network-based interpretable machine learning predicts cancer patient response to immune checkpoint inhibitors

Exploring the Emerging Association Between Immune Checkpoint Inhibitors and Thrombosis

Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment, but their association with thrombosis presents significant clinical challenges. Patients with cancer already exhibit elevated risks for venous thromboembolism and arterial thrombosis, with treatment modalities like chemotherapy further exacerbating this risk. Emerging evidence suggests that ICIs contribute to thrombotic events through multifactorial mechanisms, including immune dysregulation, T cell activation, endothelial dysfunction, elevated tissue factor expression, and impaired fibrinolysis. Additional risk factors such as obesity, smoking, prior thrombotic events, and combination ICI therapy further increase thrombosis susceptibility. The literature reports varying incidence rates of ICI-associated thrombosis, with some studies indicating comparable risks to chemotherapy, while others highlight higher rates, particularly during the initial treatment phase. Management aligns with standard protocols for cancer-associated thrombosis, using low-molecular-weight heparin or direct oral anticoagulants, though optimal treatment duration and the role of prophylactic anticoagulation require further investigation. This review provides a comprehensive overview of the mechanisms, incidence rates, and clinical management strategies of ICI-associated thrombosis, emphasizing the importance of proactive risk assessment to optimize patient outcomes.

Emerging artificial intelligence-driven precision therapies in tumor drug resistance: recent advances, opportunities, and challenges

Drug resistance is one of the main reasons for cancer treatment failure, leading to a rapid recurrence/disease progression of the cancer. Recently, artificial intelligence (AI) has empowered physicians to use its powerful data processing and pattern recognition capabilities to extract and mine valuable drug resistance information from large amounts of clinical or omics data, to study drug resistance mechanisms, to evaluate and predict drug resistance, and to develop innovative therapeutic strategies to reduce drug resistance. In this review, we proposed a feasible workflow for incorporating AI into tumor drug resistance research, highlighted current AI-driven tumor drug resistance applications, and discussed the opportunities and challenges encountered in the process. Based on a comprehensive literature analysis, we systematically summarized the role of AI in tumor drug resistance research, including drug development, resistance mechanism elucidation, drug sensitivity prediction, combination therapy optimization, resistance phenotype identification, and clinical biomarker discovery. With the continuous advancement of AI technology and rigorous validation of clinical data, AI models are expected to fuel the development of precision oncology by improving efficacy, guiding therapeutic decisions, and optimizing patient prognosis. In summary, by leveraging clinical and omics data, AI models are expected to pioneer new therapy strategies to mitigate tumor drug resistance, improve efficacy and patient survival, and provide novel perspectives and tools for oncology treatment.

AI-driven multi-omics integration for multi-scale predictive modeling of genotype-environment-phenotype relationships

Despite the wealth of single-cell multi-omics data, it remains challenging to predict the consequences of novel genetic and chemical perturbations in the human body. It requires knowledge of molecular interactions at all biological levels, encompassing disease models and humans. Current machine learning methods primarily establish statistical correlations between genotypes and phenotypes but struggle to identify physiologically significant causal factors, limiting their predictive power. Key challenges in predictive modeling include scarcity of labeled data, generalization across different domains, and disentangling causation from correlation. In light of recent advances in multi-omics data integration, we propose a new artificial intelligence (AI)-powered biology-inspired multi-scale modeling framework to tackle these issues. This framework will integrate multi-omics data across biological levels, organism hierarchies, and species to predict genotype-environment-phenotype relationships under various conditions. AI models inspired by biology may identify novel molecular targets, biomarkers, pharmaceutical agents, and personalized medicines for presently unmet medical needs.

Rapid prediction of acute thrombosis via nanoengineered immunosensors with unsupervised clustering for multiple circulating biomarkers

The recent SARS-CoV-2 pandemic underscores the need for rapid and accurate prediction of clinical thrombotic events. Here, we developed nanoengineered multichannel immunosensors for rapid detection of circulating biomarkers associated with thrombosis, including C-reactive protein (CRP), calprotectin, soluble platelet selectin (sP-selectin), and D-dimer. We fabricated the immunosensors using fiber laser engraving of carbon nanotubes and CO2 laser cutting of microfluidic channels, along with the electrochemical deposition of gold nanoparticles to conjugate with biomarker-specific aptamers and antibody. Using unsupervised clustering based on four biomarker concentrations, we predicted thrombotic events in 49 of 53 patients. The four-biomarker combination yielded an area under the receiver operating characteristic curve (AUC) of 0.95, demonstrating high sensitivity and specificity for acute thrombosis prediction compared to the AUC values for individual biomarkers: CRP (0.773), calprotectin (0.711), sP-selectin (0.683), and D-dimer (0.739). Thus, a nanoengineered multichannel platform with unsupervised clustering provides accurate and efficient methods for predicting thrombosis, guiding personalized medicine.

Mapping intratumoral myeloid-T cell interactomes at single-cell resolution reveals targets for overcoming checkpoint inhibitor resistance

Effective cancer immunotherapies restore anti-tumor immunity by rewiring cell-cell communication. Treatment-induced changes in communication can be inferred from single-cell RNA-sequencing (scRNA-seq) data, but current methods do not effectively manage heterogeneity within cell types. Here we developed a computational approach to efficiently analyze scRNA-seq-derived, single-cell-resolved cell-cell interactomes, which we applied to determine how agonistic CD40 (CD40ag) alters immune cell crosstalk alone, across tumor models, and in combination with immune checkpoint blockade (ICB). Our analyses suggested that CD40ag improves responses to ICB by targeting both immuno-stimulatory and immunosuppressive macrophage subsets communicating with T cells, and we experimentally validated a spatial basis for these subsets with immunofluorescence and spatial transcriptomics. Moreover, treatment with CD40ag and ICB established coordinated myeloid-T cell interaction hubs that are critical for reestablishing antitumor immunity. Our work advances the biological significance of hypotheses generated from scRNA-seq-derived cell-cell interactomes and supports the clinical translation of myeloid-targeted therapies for ICB-resistant tumors.

Applications of spatial transcriptomics and artificial intelligence to develop integrated management of pancreatic cancer

Cancer is a complex disease intrinsically associated with cellular processes and gene expression. With the development of techniques such as single-cell sequencing and sequential fluorescence in situ hybridization (seqFISH), it was possible to map the location of cells based on their gene expression with more precision. Moreover, in recent years, many tools have been developed to analyze these extensive datasets by integrating machine learning and artificial intelligence in a comprehensive manner. Since these tools analyze sequencing data, they offer the chance to analyze any tissue regardless of its origin. By applying this to cancer settings, spatial transcriptomic analysis based on artificial intelligence may help us understand cell-cell communications within the tumor microenvironment. Another advantage of this analysis is the identification of new biomarkers and therapeutic targets. The integration of such analysis with other omics data and with routine exams such as magnetic resonance imaging can help physicians with the earlier diagnosis of tumors as well as establish a more personalized treatment for pancreatic cancer patients. In this review, we give an overview description of pancreatic cancer, describe how spatial transcriptomics and artificial intelligence have been used to study pancreatic cancer and provide examples of how integrating these tools may help physicians manage pancreatic cancer in a more personalized approach.