RESUMO
Background: Phenotypes identified during dysmorphology physical examinations are critical to genetic diagnosis and nearly universally documented as free-text in the electronic health record (EHR). Variation in how phenotypes are recorded in free-text makes large-scale computational analysis extremely challenging. Existing natural language processing (NLP) approaches to address phenotype extraction are trained largely on the biomedical literature or on case vignettes rather than actual EHR data. Methods: We implemented a tailored system at the Children's Hospital of Philadelpia that allows clinicians to document dysmorphology physical exam findings. From the underlying data, we manually annotated a corpus of 3136 organ system observations using the Human Phenotype Ontology (HPO). We provide this corpus publicly. We trained a transformer based NLP system to identify HPO terms from exam observations. The pipeline includes an extractor, which identifies tokens in the sentence expected to contain an HPO term, and a normalizer, which uses those tokens together with the original observation to determine the specific term mentioned. Findings: We find that our labeler and normalizer NLP pipeline, which we call PhenoID, achieves state-of-the-art performance for the dysmorphology physical exam phenotype extraction task. PhenoID's performance on the test set was 0.717, compared to the nearest baseline system (Pheno-Tagger) performance of 0.633. An analysis of our system's normalization errors shows possible imperfections in the HPO terminology itself but also reveals a lack of semantic understanding by our transformer models. Interpretation: Transformers-based NLP models are a promising approach to genetic phenotype extraction and, with recent development of larger pre-trained causal language models, may improve semantic understanding in the future. We believe our results also have direct applicability to more general extraction of medical signs and symptoms. Funding: US National Institutes of Health.
RESUMO
Previous data obtained in our laboratory suggested that there may be constitutive signaling through the myeloid differentiation primary response gene 88 (Myd88)-dependent signaling cascade in murine mammary carcinoma. Here, we extended these findings by showing that, in the absence of an added Toll-like receptor (TLR) agonist, the myddosome complex was preformed in 4T1 tumor cells, and that Myd88 influenced cytoplasmic extracellular signal-regulated kinase (Erk)1/Erk2 levels, nuclear levels of nuclear factor-kappaB (NFκB) and signal transducer and activator of transcription 5 (STAT5), tumor-derived chemokine (C-C motif) ligand 2 (CCL2) expression, and in vitro and in vivo tumor growth. In addition, RNA-sequencing revealed that Myd88-dependent signaling enhanced the expression of genes that could contribute to breast cancer progression and genes previously associated with poor outcome for patients with breast cancer, in addition to suppressing the expression of genes capable of inhibiting breast cancer progression. Yet, Myd88-dependent signaling in tumor cells also suppressed expression of genes that could contribute to tumor progression. Collectively, these data revealed a multifaceted role for Myd88-dependent signaling in murine mammary carcinoma.
