Aaron J. Masino

Clinical phenotype-based gene prioritization: an initial study using semantic similarity and the human phenotype ontology

BackgroundExome sequencing is a promising method for diagnosing patients with a complex phenotype. However, variant interpretation relative to patient phenotype can be challenging in some scenarios, particularly clinical assessment of rare complex phenotypes. Each patient’s sequence reveals many possibly damaging variants that must be individually assessed to establish clear association with patient phenotype. To assist interpretation, we implemented an algorithm that ranks a given set of genes relative to patient phenotype. The algorithm orders genes by the semantic similarity computed between phenotypic descriptors associated with each gene and those describing the patient. Phenotypic descriptor terms are taken from the Human Phenotype Ontology (HPO) and semantic similarity is derived from each term’s information content.ResultsModel validation was performed via simulation and with clinical data. We simulated 33 Mendelian diseases with 100 patients per disease. We modeled clinical conditions by adding noise and imprecision, i.e. phenotypic terms unrelated to the disease and terms less specific than the actual disease terms. We ranked the causative gene against all 2488 HPO annotated genes. The median causative gene rank was 1 for the optimal and noise cases, 12 for the imprecision case, and 60 for the imprecision with noise case. Additionally, we examined a clinical cohort of subjects with hearing impairment. The disease gene median rank was 22. However, when also considering the patient’s exome data and filtering non-exomic and common variants, the median rank improved to 3.ConclusionsSemantic similarity can rank a causative gene highly within a gene list relative to patient phenotype characteristics, provided that imprecision is mitigated. The clinical case results suggest that phenotype rank combined with variant analysis provides significant improvement over the individual approaches. We expect that this combined prioritization approach may increase accuracy and decrease effort for clinical genetic diagnosis.

Deep learning for pharmacovigilance: recurrent neural network architectures for labeling adverse drug reactions in Twitter posts

Objective Social media is an important pharmacovigilance data source for adverse drug reaction (ADR) identification. Human review of social media data is infeasible due to data quantity, thus natural language processing techniques are necessary. Social media includes informal vocabulary and irregular grammar, which challenge natural language processing methods. Our objective is to develop a scalable, deep-learning approach that exceeds state-of-the-art ADR detection performance in social media. Materials and Methods We developed a recurrent neural network (RNN) model that labels words in an input sequence with ADR membership tags. The only input features are word-embedding vectors, which can be formed through task-independent pretraining or during ADR detection training. Results Our best-performing RNN model used pretrained word embeddings created from a large, non-domain-specific Twitter dataset. It achieved an approximate match F-measure of 0.755 for ADR identification on the dataset, compared to 0.631 for a baseline lexicon system and 0.65 for the state-of-the-art conditional random field model. Feature analysis indicated that semantic information in pretrained word embeddings boosted sensitivity and, combined with contextual awareness captured in the RNN, precision. Discussion Our model required no task-specific feature engineering, suggesting generalizability to additional sequence-labeling tasks. Learning curve analysis showed that our model reached optimal performance with fewer training examples than the other models. Conclusion ADR detection performance in social media is significantly improved by using a contextually aware model and word embeddings formed from large, unlabeled datasets. The approach reduces manual data-labeling requirements and is scalable to large social media datasets.

Crowd control

Annotating unstructured texts in Electronic Health Records data is usually a necessary step for conducting machine learning research on such datasets. Manual annotation by domain experts provides data of the best quality, but has become increasingly impractical given the rapid increase in the volume of EHR data. In this article, we examine the effectiveness of crowdsourcing with unscreened online workers as an alternative for transforming unstructured texts in EHRs into annotated data that are directly usable in supervised learning models. We find the crowdsourced annotation data to be just as effective as expert data in training a sentence classification model to detect the mentioning of abnormal ear anatomy in radiology reports of audiology. Furthermore, we have discovered that enabling workers to self-report a confidence level associated with each annotation can help researchers pinpoint less-accurate annotations requiring expert scrutiny. Our findings suggest that even crowd workers without specific domain knowledge can contribute effectively to the task of annotating unstructured EHR datasets.

The biorepository portal toolkit: an honest brokered, modular service oriented software tool set for biospecimen-driven translational research

BackgroundHigh throughput molecular sequencing and increased biospecimen variety have introduced significant informatics challenges for research biorepository infrastructures. We applied a modular system integration approach to develop an operational biorepository management system. This method enables aggregation of the clinical, specimen and genomic data collected for biorepository resources.MethodsWe introduce an electronic Honest Broker (eHB) and Biorepository Portal (BRP) open source project that, in tandem, allow for data integration while protecting patient privacy. This modular approach allows data and specimens to be associated with a biorepository subject at any time point asynchronously. This lowers the bar to develop new research projects based on scientific merit without institutional review for a proposal.ResultsBy facilitating the automated de-identification of specimen and associated clinical and genomic data we create a future proofed specimen set that can withstand new workflows and be connected to new associated information over time. Thus facilitating collaborative advanced genomic and tissue research.ConclusionsAs of Janurary of 2016 there are 23 unique protocols/patient cohorts being managed in the Biorepository Portal (BRP). There are over 4000 unique subject records in the electronic honest broker (eHB), over 30,000 specimens accessioned and 8 institutions participating in various biobanking activities using this tool kit. We specifically set out to build rich annotation of biospecimens with longitudinal clinical data; BRP/REDCap integration for multi-institutional repositories; EMR integration; further annotated specimens with genomic data specific to a domain; build application hooks for experiments at the specimen level integrated with analytic software; while protecting privacy per the Office of Civil Rights (OCR) and HIPAA.

Effectively Crowdsourcing Radiology Report Annotations

Crowdsourcing platforms are a popular choice for researchers to gather text annotations quickly at scale. We investigate whether crowdsourced annotations are useful when the labeling task requires medical domain knowledge. Comparing a sentence classification model trained with expert-annotated sentences to the same model trained on crowd-labeled sentences, we find the crowdsourced training data to be just as effective as the manually produced dataset. We can improve the accuracy of the crowd-fueled model without collecting further labels by filtering out worker labels applied with low confidence.