No abstract

Platelet activation by the coagulation protease thrombin is central to arterial thrombosis, a major cause of morbidity and mortality. We recently isolated a complementary DNA encoding the platelet thrombin receptor. The extracellular amino-terminal extension of this seven transmembrane domain receptor contains the putative thrombin cleavage site LDPR/S which is critical for receptor activation. By replacing this cleavage site with the cleavage site for enterokinase, we have created a functional enterokinase receptor. This result demonstrates that all information necessary for receptor activation is provided by receptor proteolysis. Nanomolar enterokinase concentrations are required to activate this new receptor, in contrast to the picomolar thrombin concentrations that activate wild-type thrombin receptor. We identified a receptor domain critical for thrombin's remarkable potency at its receptor. This domain resembles the carboxyl tail of the leech anticoagulant hirudin and functions by binding to thrombin's anion-binding exosite. Our studies thus define a model for thrombin-receptor interaction. The utility of this model was demonstrated by the design of novel thrombin inhibitors based on receptor peptides.

Magnetic resonance imaging (MRI) protocoling can be time- and resource-intensive, and protocols can often be suboptimal dependent upon the expertise or preferences of the protocoling radiologist. Providing a best-practice recommendation for an MRI protocol has the potential to improve efficiency and decrease the likelihood of a suboptimal or erroneous study. The goal of this study was to develop and validate a machine learning-based natural language classifier that can automatically assign the use of intravenous contrast for musculoskeletal MRI protocols based upon the free-text clinical indication of the study, thereby improving efficiency of the protocoling radiologist and potentially decreasing errors. We utilized a deep learning-based natural language classification system from IBM Watson, a question-answering supercomputer that gained fame after challenging the best human players on Jeopardy! in 2011. We compared this solution to a series of traditional machine learning-based natural language processing techniques that utilize a term-document frequency matrix. Each classifier was trained with 1240 MRI protocols plus their respective clinical indications and validated with a test set of 280. Ground truth of contrast assignment was obtained from the clinical record. For evaluation of inter-reader agreement, a blinded second reader radiologist analyzed all cases and determined contrast assignment based on only the free-text clinical indication. In the test set, Watson demonstrated overall accuracy of 83.2% when compared to the original protocol. This was similar to the overall accuracy of 80.2% achieved by an ensemble of eight traditional machine learning algorithms based on a term-document matrix. When compared to the second reader's contrast assignment, Watson achieved 88.6% agreement. When evaluating only the subset of cases where the original protocol and second reader were concordant (n = 251), agreement climbed further to 90.0%. The classifier was relatively robust to spelling and grammatical errors, which were frequent. Implementation of this automated MR contrast determination system as a clinical decision support tool may save considerable time and effort of the radiologist while potentially decreasing error rates, and require no change in order entry or workflow.

Embryonal carcinoma and embryonic stem cells expressed a novel form of platelet-derived growth factor receptor mRNA which was -1,100 base pairs shorter than the 5.3-kilobase (kb) transcript expressed in fibroblasts and other cell types. The 4.2-kb stem cell transcript was initiated within the genomic region immediately upstream of exon 6 of the 5.3-kb transcript and therefore lacked the first five exons, which encode much of the extracellular domain of the receptor expressed in fibroblasts. In stem cells, the short form was predominant, although both forms were present at low levels. Following differentiation in vitro, expression levels of the long form increased dramatically. These findings suggest that during early embryogenesis, a stem cell-specific promoter is used in a stage-and cell type-specific manner to express a form of the platelet-derived growth factor receptor that lacks much of the extracellular domain and may function independently of ligand.