Scents play a central role in nature, as olfactory interactions are the language of life. In a new research project of the UvA Molecular and Materials Design Technology hub, scientists will use machine learning to predict what types of olfactory molecules interact with insect olfactory receptors. This information is important to develop safe-by-design molecules that do not interfere with insect olfaction. Scents play a central role in the lives of living beings, from locating food and mates to sensing and avoiding danger. Insects use many different types of scents, such as sex, trail, alarm and aggregation pheromones, as well as plant odors to locate their host plants.

A new model for chemosensory reception is presented. The mathematical formulation of the reaction kinetics is transformed into an artificial neural network (ANN). The resulting feed-forward network provides a powerful means for parameter fitting by applying learning algorithms. The weights of the network corresponding to chemical parameters can be trained by presen(cid:173) ting experimental data. We demonstrate the simulation capabilities of the model with experimental data from honey bee chemosensory neurons.

Protein interactions are important in a broad range of biological processes. Traditionally, computational methods have been developed to automatically predict protein interface from hand-crafted features. Recent approaches employ deep neural networks and predict the interaction of each amino acid pair independently. However, these methods do not incorporate the important sequential information from amino acid chains and the high-order pairwise interactions. Intuitively, the prediction of an amino acid pair should depend on both their features and the information of other amino acid pairs. In this work, we propose to formulate the protein interface prediction as a 2D dense prediction problem. In addition, we propose a novel deep model to incorporate the sequential information and high-order pairwise interactions to perform interface predictions. We represent proteins as graphs and employ graph neural networks to learn node features. Then we propose the sequential modeling method to incorporate the sequential information and reorder the feature matrix. Next, we incorporate high-order pairwise interactions to generate a 3D tensor containing different pairwise interactions. Finally, we employ convolutional neural networks to perform 2D dense predictions. Experimental results on multiple benchmarks demonstrate that our proposed method can consistently improve the protein interface prediction performance.

Foregoing a good night's sleep may wreck the brain's ability to make new memories. A new study from Johns Hopkins University School of Medicine demonstrated that a key purpose of sleep is to recalibrate the brain cells responsible for learning and memory, solidifying lessons learned for when the sleeper is awake. Using a mouse model, the researchers discovered several important molecules that govern the recalibration process, as well as evidence that sleep deprivation, sleep disorders and sleeping pills can interfere with the process. Graham Diering, Ph.D., the postdoctoral fellow who led the study, explained that the results from the mouse study can be used to make determinations about the human brain. "Our findings solidly advance the idea that the mouse and presumably the human brain can only store so much information before it needs to recalibrate," he said in a statement.

A new model for chemosensory reception is presented.

A new model for chemosensory reception is presented.

A new model for chemosensory reception is presented.