Machine learning identifies signatures of macrophage reactivity and tolerance that predict disease outcomes.

BACKGROUND: Single-cell transcriptomic studies have greatly improved organ-specific insights into macrophage polarization states are essential for the initiation and resolution of inflammation in all tissues; however, such insights are yet to translate into therapies that can predictably alter macrophage fate. METHOD: Using machine learning algorithms on human macrophages, here we reveal the continuum of polarization states that is shared across diverse contexts. A path, comprised of 338 genes accurately identified both physiologic and pathologic spectra of "reactivity" and "tolerance", and remained relevant across tissues, organs, species, and immune cells (>12,500 diverse datasets). FINDINGS: This 338-gene signature identified macrophage polarization states at single-cell resolution, in physiology and across diverse human diseases, and in murine pre-clinical disease models. The signature consistently outperformed conventional signatures in the degree of transcriptome-proteome overlap, and in detecting disease states; it also prognosticated outcomes across diverse acute and chronic diseases, e.g., sepsis, liver fibrosis, aging, and cancers. Crowd-sourced genetic and pharmacologic studies confirmed that model-rationalized interventions trigger predictable macrophage fates. INTERPRETATION: These findings provide a formal and universally relevant definition of macrophage states and a predictive framework (http://hegemon.ucsd.edu/SMaRT) for the scientific community to develop macrophage-targeted precision diagnostics and therapeutics. FUNDING: This work was supported by the National Institutes for Health (NIH) grant R01-AI155696 (to P.G, D.S and S.D). Other sources of support include: R01-GM138385 (to D.S), R01-AI141630 (to P.G), R01-DK107585 (to S.D), and UG3TR003355 (to D.S, S.D, and P.G). D.S was also supported by two Padres Pedal the Cause awards (Padres Pedal the Cause/RADY #PTC2017 and San Diego NCI Cancer Centers Council (C3) #PTC2017). S.S, G.D.K, and D.D were supported through The American Association of Immunologists (AAI) Intersect Fellowship Program for Computational Scientists and Immunologists. We also acknowledge support from the Padres Pedal the Cause #PTC2021 and the Torey Coast Foundation, La Jolla (P.G and D.S). D.S, P.G, and S.D were also supported by the Leona M. and Harry B. Helmsley Charitable Trust.

Transcriptional profiling of lung macrophages identifies a predictive signature for inflammatory lung disease in preterm infants.

Lung macrophages mature after birth, placing newborn infants, particularly those born preterm, within a unique window of susceptibility to disease. We hypothesized that in preterm infants, lung macrophage immaturity contributes to the development of bronchopulmonary dysplasia (BPD), the most common serious complication of prematurity. By measuring changes in lung macrophage gene expression in preterm patients at risk of BPD, we show here that patients eventually developing BPD had higher inflammatory mediator expression even on the first day of life. Surprisingly, the ex vivo response to LPS was similar across all samples. Our analysis did however uncover macrophage signature genes whose expression increased in the first week of life specifically in patients resilient to disease. We propose that these changes describe the dynamics of human lung macrophage differentiation. Our study therefore provides new mechanistic insight into both neonatal lung disease and human developmental immunology.

Computational Approach to Identifying Universal Macrophage Biomarkers.

Macrophages engulf and digest microbes, cellular debris, and various disease-associated cells throughout the body. Understanding the dynamics of macrophage gene expression is crucial for studying human diseases. As both bulk RNAseq and single cell RNAseq datasets become more numerous and complex, identifying a universal and reliable marker of macrophage cell becomes paramount. Traditional approaches have relied upon tissue specific expression patterns. To identify universal biomarkers of macrophage, we used a previously published computational approach called BECC (Boolean Equivalent Correlated Clusters) that was originally used to identify conserved cell cycle genes. We performed BECC analysis using the known macrophage marker CD14 as a seed gene. The main idea behind BECC is that it uses massive database of public gene expression dataset to establish robust co-expression patterns identified using a combination of correlation, linear regression and Boolean equivalences. Our analysis identified and validated FCER1G and TYROBP as novel universal biomarkers for macrophages in human and mouse tissues.