Understanding Clinical Trial Reports: Extracting Medical Entities and Their Relations.

The best evidence concerning comparative treatment effectiveness comes from clinical trials, the results of which are reported in unstructured articles. Medical experts must manually extract information from articles to inform decision-making, which is time-consuming and expensive. Here we consider the end-to-end task of both (a) extracting treatments and outcomes from full-text articles describing clinical trials (entity identification) and, (b) inferring the reported results for the former with respect to the latter (relation extraction). We introduce new data for this task, and evaluate models that have recently achieved state-of-the-art results on similar tasks in Natural Language Processing. We then propose a new method motivated by how trial results are typically presented that outperforms these purely data-driven baselines. Finally, we run a fielded evaluation of the model with a non-profit seeking to identify existing drugs that might be re-purposed for cancer, showing the potential utility of end-to-end evidence extraction systems.

Ambient temperature hydrophosphination of internal, unactivated alkynes and allenyl phosphineoxides with phosphine borane complexes.

Phosphine boranes have been found to hydrophosphinate internal, unactivated alkynes at room temperature under basic conditions without the need for catalysts or radical initiators. The use of air-sensitive secondary phosphines is avoided in this facile process. Broad scope in both the phosphine borane and alkyne partners leads to excellent diversity in the phosphine products. Asymmetric hydrogenation of these species then provides one of the shortest possible routes to chiral monodentate phosphines. Hydrophosphination of allenyl phosphine oxides under similar conditions followed by hydrogenation of the exomethylene moiety yields a wide variety of bis-phosphine derivatives.