Cortical bone allografts suffer from high rates of failure due to poor integration with host tissue, leading to non-union, fracture, and infection following secondary procedures. Here, we report a method for modifying the surfaces of cortical bone with coatings that have biological functions that may help overcome these challenges. These chitosan-heparin coatings promote mesenchymal stem cell attachment and have significant antibacterial activity against both S. aureus and E. coli. Furthermore, their chemistry is similar to coatings we have reported on previously, which effectively stabilize and deliver heparin-binding growth factors. These coatings have potential as synthetic periosteum for improving bone allograft outcomes.

The identification of drug-drug interactions (DDIs) is important for patient safety; yet, compared to other pharmacovigilance work, a limited amount of research has been conducted in this space. Recent work has successfully applied a method of deriving distributed vector representations from structured biomedical knowledge, known as Embedding of Semantic Predications (ESP), to the problem of predicting individual drug side effects. In the current paper we extend this work by applying ESP to the problem of predicting polypharmacy side-effects for particular drug combinations, building on a recent reconceptualization of this problem as a network of drug nodes connected by side effect edges. We evaluate ESP embeddings derived from the resulting graph on a side-effect prediction task against a previously reported graph convolutional neural network approach, using the same data and evaluation methods. We demonstrate that ESP models perform better, while being faster to train, more re-usable, and significantly simpler.

Our methods can assist the pharmacovigilance process using information from the biomedical literature. Unsupervised pretraining generates a rich relationship-based representational foundation for machine learning techniques to classify drugs in the context of a putative side effect, given known examples.