Fei Wang

Paxlovid (nirmatrelvir/ritonavir) has been approved for use in patients who are at high risk for severe acute COVID-19 illness. Evidence regarding whether acute use of Paxlovid protects against Post-Acute Sequelae of SARS-CoV-2 infection (PASC), or Long COVID, is mixed in high-risk patients and lacking in low-risk patients. With a target trial emulation framework, we evaluated the association of Paxlovid treatment within 5 days of SARS-CoV-2 infection with incident Long COVID and hospitalization or death from any cause in the post-acute period (30–180 days after infection) using electronic health records from the Patient-Centered Clinical Research Networks (PCORnet) RECOVER repository. The study population included 497,499 SARS-CoV-2 positive patients between March 1, 2022, to February 28, 2023. For those who had at least 1 risk factor for severe COVID-19 illness, 159,659 were treated with at least one dose of Paxlovid within 5 days since infection and 272,048 were not treated with Paxlovid or other COVID-19 treatments during the acute infection period. Compared with the non-treated group, Paxlovid treatment was associated with reduced risk of Long COVID with a Hazard Ratio (HR) of 0.88 (95% CI, 0.87 to 0.89) and absolute risk reduction of 2.99 events per 100 persons (95% CI, 2.65 to 3.32). For those without documented risk factors, the associations (HR, 1.03, 95% CI 0.95 to 1.11; risk increase 0.80 events per 100 persons, 95% CI -0.84 to 2.45) were inconclusive. High-risk, nonhospitalized adult patients with COVID-19 who were treated with Paxlovid within 5 days of SARS-CoV-2 infection had a lower risk of Long COVID and all-cause hospitalization or death in the post-acute period. However, Long COVID risk reduction with Paxlovid was not observed in low-risk patients.

Medical evidence synthesis increasingly requires published studies, real-world clinical data and structured biomedical knowledge, yet most automated systems remain centered on literature retrieval and summarization. Here we present MES, a multi-agent framework for source-grounded medical evidence synthesis. MES coordinates six specialized agents to decompose clinical questions, retrieve literature and trial evidence, generate question-specific RWE by constructing and analyzing real-world cohorts, query biomedical knowledge graphs, integrate quantitative findings and screen generated claims against their cited evidence. The framework uses evidence-based medicine taxonomies to clarify underspecified questions, adapts evidence use when sources are absent or discordant and reports unresolved gaps rather than forcing consensus. MES also provides claim-level provenance tracking and cross-agent consistency checking, allowing final reports to distinguish trial evidence, real-world associations and knowledge-graph support. We evaluated MES in two clinical use cases and across 144 clinical queries spanning six evidence-based medicine categories. MES generated structured reports that preserved source traceability, identified cross-source disagreement and communicated uncertainty across diverse clinical question types. MES provides an auditable framework for organizing, testing and contextualizing heterogeneous clinical evidence while keeping the evidentiary basis of each conclusion explicit.

Recent advances in large-scale single-cell atlases and large language models (LLMs) have enabled the emergence of single-cell foundation models (scFMs)-pretrained models that aim to learn transferable representations of cellular states across tissues, conditions, and molecular modalities. These models hold promise for moving single-cell analysis beyond task-specific pipelines towards unified, generalizable and predictive frameworks, yet their biological fidelity, generalization and scaling capacity, as well as utility for perturbation modeling remain challenging. In this review, we summarize recent progress in scFMs across key design dimensions, including data representation, model architecture and learning objective, and examine how these frameworks are being applied to biological discovery. We further critically assess current challenges and opportunities from multimodal pretraining atlas, emerging pretraining paradigms, downstream applications, and real-world barriers. This review provides a structured guide for both computational scientists and experimental biologists seeking to understand, develop, and apply foundation models for single-cell research.