Comparative analysis of key phagocytic genes in humans and mice using machine learning integrated with single-cell RNA sequencing

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Not quantified - qualitative gene expression differences reported

• Primary Outcome: Species-specific identification of phagocytosis-associated genes: Tlr2 in mice and CLEC7A in humans

• Nnt Or Sensitivity: XGBoost model selected as best-performing among five machine learning approaches

• Confidence Interval: Not reported

Clinical Application

Requires specialized single-cell sequencing facilities and bioinformatics expertise; not immediately applicable to routine clinical practice Relevant to Australian stroke units and neurocritical care; may inform future TGA submissions for microglial-targeted therapeutics; aligns with NHMRC precision medicine initiatives Patients with intracerebral hemorrhage, particularly those being considered for microglial-targeted therapies

Abstract

Microglial phagocytosis is essential for neurological recovery after intracerebral hemorrhage (ICH). Using single-cell RNA sequencing, we compared microglial responses in murine and human ICH and identified striking species-specific temporal patterns. Murine microglia exhibited a sustained enhancement of phagocytic activity, whereas human microglia showed only a transient increase followed by a decline and persistent inflammation. To identify genes associated with phagocytic differences, we evaluated five machine learning models and selected XGBoost as the best-performing model. This analysis identified Tlr2 in mice and CLEC7A in humans as genes associated with microglial phagocytic status. Inferred transcription factor activity analysis further revealed stronger phagocytosis- and inflammation-associated transcriptional activity in murine phagocytic microglial subclusters, whereas human microglia were predominantly characterized by inflammation-associated transcription factors. Consistent with these results, Tlr2 expression was markedly increased at day 14 in single-cell data, and immunostaining confirmed its colocalization with IBA1+ microglia and upregulation at days 3 and 7 after ICH. Together, our findings demonstrate that integrating single-cell RNA sequencing with machine learning facilitates the identification of phagocytosis-associated genes and reveals both conserved and divergent patterns of microglial phagocytosis, providing new insights into species-specific responses to ICH.