Search

Automatic phenotype concept recognition from unstructured text remains a challenging task in biomedical text mining research. Previous works that address the task typically use dictionary-based matching methods, which can achieve high precision but suffer from lower recall. Recently, machine learning-based methods have been proposed to identify biomedical concepts, which can recognize more unseen concept synonyms by automatic feature learning. However, most methods require large corpora of manually annotated data for model training, which is difficult to obtain due to the high cost of human annotation. In this paper, we propose PhenoTagger, a hybrid method that combines both dictionary and machine learning-based methods to recognize Human Phenotype Ontology (HPO) concepts in unstructured biomedical text. We first use all concepts and synonyms in HPO to construct a dictionary, which is then used to automatically build a distantly supervised training dataset for machine learning. Next, a cutting-edge deep learning model is trained to classify each candidate phrase (n-gram from input sentence) into a corresponding concept label. Finally, the dictionary and machine learning-based prediction results are combined for improved performance. Our method is validated with two HPO corpora, and the results show that PhenoTagger compares favorably to previous methods. In addition, to demonstrate the generalizability of our method, we retrained PhenoTagger using the disease ontology MEDIC for disease concept recognition to investigate the effect of training on different ontologies. Experimental results on the NCBI disease corpus show that PhenoTagger without requiring manually annotated training data achieves competitive performance as compared with state-of-the-art supervised methods., Accepted by Bioinformatics

In biology and biomedicine, relating phenotypic outcomes with genetic variation and environmental factors remains a challenge: patient phenotypes may not match known diseases, candidate variants may be in genes that haven’t been characterized, research organisms may not recapitulate human or veterinary diseases, environmental factors affecting disease outcomes are unknown or undocumented, and many resources must be queried to find potentially significant phenotypic associations. The Monarch Initiative (https://monarchinitiative.org) integrates information on genes, variants, genotypes, phenotypes and diseases in a variety of species, and allows powerful ontology-based search. We develop many widely adopted ontologies that together enable sophisticated computational analysis, mechanistic discovery and diagnostics of Mendelian diseases. Our algorithms and tools are widely used to identify animal models of human disease through phenotypic similarity, for differential diagnostics and to facilitate translational research. Launched in 2015, Monarch has grown with regards to data (new organisms, more sources, better modeling); new API and standards; ontologies (new Mondo unified disease ontology, improvements to ontologies such as HPO and uPheno); user interface (a redesigned website); and community development. Monarch data, algorithms and tools are being used and extended by resources such as GA4GH and NCATS Translator, among others, to aid mechanistic discovery and diagnostics.

Background: Telephone delivery of genetic counseling is an alternative to in-person genetic counseling because it may extend the reach of genetic counseling. Previous reports have established the noninferiority of telephone counseling on short-term psychosocial and decision-making outcomes. Here we examine the long-term impact of telephone counseling (TC) vs inperson counseling (usual care [UC]). Methods: We recruited high-risk women for a noninferiority trial comparing TC with UC. Of 1057 potentially eligible women, 669 were randomly assigned to TC (n = 335) or UC (n = 334), and 512 completed the 12-month follow-up. Primary outcomes were patient-reported satisfaction with genetic testing decision, distress, and quality of life. Secondary outcomes were uptake of cancer risk management strategies. Results: TC was noninferior to UC on all primary outcomes. Satisfaction with decision (d = 0.13, lower bound of 97.5% confidence interval [CI] = -0.34) did not cross its one-point noninferiority limit, cancer-specific distress (d = -2.10, upper bound of 97.5% CI = -0.07) did not cross its four-point noninferiority limit, and genetic testing distress (d = -0.27, upper bound of 97.5% CI = 1.46), physical function (d = 0.44, lower bound of 97.5% CI = -0.91) and mental function (d = -0.04, lower bound of 97.5% CI = -1.44) did not cross their 2.5-point noninferiority limit. Bivariate analyses showed no differences in risk-reducing mastectomy or oophorectomy across groups; however, when combined, TC had significantly more risk-reducing surgeries than UC (17.8% vs 10.5%; chi(2) = 4.43, P = .04). Conclusions: Findings support telephone delivery of genetic counseling to extend the accessibility of this service without long-termadverse outcomes., This study was supported by grants (R01 CA108933 and P30 CA051008) from the National Cancer Institute and by the Jess and Mildred Fisher Center for Hereditary Cancer and Clinical Genomics Research.