ABAndrew Bliss

Andrew Bliss

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Andrew Bliss has a total of 51 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Benchmarking large language models for cell-free RNA diagnostic biomarker discovery

    by Hunter A. Gaudio, Andrew Bliss, Conor J. Loy, Daniel Eweis-LaBolle, Anne E. Gardella, Iwijn De Vlaminck

    Large language models can synthesize biomedical knowledge, parse vast amounts of data, and generate code, positioning them as promising tools for biomarker discovery from high-throughput omics data. Here, we benchmark six models from OpenAI, Anthropic, and Google on plasma cell-free RNA datasets spanning three clinical cohorts: Kawasaki disease versus multisystem inflammatory syndrome in children, active tuberculosis versus symptomatic respiratory controls, and myalgic encephalomyelitis/chronic fatigue syndrome versus sedentary controls. We evaluate literature-guided nomination of diagnostic gene panels for downstream machine learning and autonomous construction of end-to-end classifiers from raw count matrices to held-out test predictions. Despite prompt adherence issues, model-nominated panels recapitulate canonical immune pathways and outperform random panels across cohorts, even matching differential gene expression baselines in the tuberculosis cohort. End-to-end automation proves feasible but is model- and task-dependent. One model approaches conventional performance for Kawasaki disease versus multisystem inflammatory syndrome in children, whereas performance decreases for tuberculosis and myalgic encephalomyelitis/chronic fatigue syndrome cohorts. These findings delineate current capabilities and limitations of large language models in diagnostics and open a path for their future use in biomarker discovery.

  • Open Access

    Minimal correlation but complementary diagnostic utility for plasma cell-free RNA and proteins

    by Andrew Bliss, Conor J. Loy, Jihoon Kim, Chisato Shimizu, Joan S. Lenz, Emma Belcher, Adriana H. Tremoulet, Jane C. Burns, Iwijn De Vlaminck

    Background Proteins and RNA circulate in plasma and can offer insights into human physiology. Yet, despite their clinical importance, direct comparisons between these analytes remain unexplored. Methods: Here, we measure and compare plasma cell-free RNA (cfRNA) and protein levels for 263 children diagnosed with inflammatory diseases, specifically either Kawasaki disease (KD) or Multisystem Inflammatory Syndrome in Children (MIS-C), by RNA sequencing (n = 108 KD and n = 47 MIS-C, mean age=4.2 years) and SomaScan proteomics (n = 70 KD and n = 101 MIS-C, mean age=6.8 years). Results Here we show that cell-free RNA and protein levels are largely uncorrelated across samples (feature-by-sample correlation coefficient 0.052; median feature-level correlation coefficient 0.009). Nonetheless, machine learning models based on either modality distinguish KD from MIS-C with similar high accuracy (median area under the curve greater than 0.93). Analysis of KD subtypes reveals distinct cell-free RNA and protein signatures, with one group showing molecular similarity to MIS-C. Conclusions These findings underscore the complementary nature of cell-free RNA and protein profiling and highlight the utility of integrating multiple plasma analytes to improve disease classification and deepen our understanding of complex inflammatory conditions.

  • Open Access

    Minimal Correlation but Complementary Diagnostic Utility for Plasma Cell-free RNA and Proteins

    by Andrew Bliss, Conor J. Loy, Jihoon Kim, Chisato Shimizu, Joan S. Lenz, Emma Belcher, Adriana H. Tremoulet, Jane C. Burns, Iwijn De Vlaminck

    Proteins and RNA circulate in plasma and can offer insights into human physiology. Yet, despite their clinical importance, direct comparisons between these analytes remain unexplored. Here, we measured and compared plasma cell-free RNA (cfRNA) and protein levels for 263 children diagnosed with inflammatory diseases by RNA-sequencing (n=155) and SomaScan proteomics (n=171). Remarkably, cfRNA and protein levels were largely uncorrelated across samples (feature-by-sample r=0.052; median feature-level r=0.009). Nonetheless, machine learning models based on either modality distinguished Kawasaki Disease (KD) from Multisystem Inflammatory Syndrome in Children (MIS-C) with similar high accuracy (median AUC > 0.93). Analysis of KD subtypes revealed distinct cfRNA and protein signatures, with one group showing molecular similarity to MIS-C. These findings underscore the complementary nature of cfRNA and protein profiling and highlight the utility of integrating multiple blood analytes to improve disease classification and deepen our understanding of complex inflammatory conditions.

  • Open Access

    Plasma cell-free RNA signatures of inflammatory syndromes in children

    by Conor J. Loy, Venice Servellita, Alicia Sotomayor-Gonzalez, Andrew Bliss, Joan S. Lenz, Emma Belcher, Will Suslovic, Jenny Nguyen, Meagan E. Williams, Miriam Oseguera, et al.

    Inflammatory syndromes, including those caused by infection, are a major cause of hospital admissions among children and are often misdiagnosed because of a lack of advanced molecular diagnostic tools. In this study, we explored the utility of circulating cell-free RNA (cfRNA) in plasma as an analyte for the differential diagnosis and characterization of pediatric inflammatory syndromes. We profiled cfRNA in 370 plasma samples from pediatric patients with a range of inflammatory conditions, including Kawasaki disease (KD), multisystem inflammatory syndrome in children (MIS-C), viral infections, and bacterial infections. We developed machine learning models based on these cfRNA profiles, which effectively differentiated KD from MIS-C—two conditions presenting with overlapping symptoms—with high performance [test area under the curve = 0.98]. We further extended this methodology into a multiclass machine learning framework that achieved 80% accuracy in distinguishing among KD, MIS-C, viral, and bacterial infections. We further demonstrated that cfRNA profiles can be used to quantify injury to specific tissues and organs, including the liver, heart, endothelium, nervous system, and the upper respiratory tract. Overall, this study identified cfRNA as a versatile analyte for the differential diagnosis and characterization of a wide range of pediatric inflammatory syndromes.