AA Comparison of Dynamic Modeling Approaches for Epileptic EEG Detection and Classification.

Electroencephalogram (EEG) has been intensively used as a diagnosis tool for epilepsy. The traditional diagnostic procedure relies on a recording of EEG from several days up to a few weeks, and the recordings are visually inspected by trained medical professionals. This procedure is time consuming with a high misdiagnosis rate. In recent years, computer-aided techniques have been proposed to automate the epilepsy diagnosis by using machine learning methods to analyze EEG data. Considering the time-varying nature of EEG, the goal of this work is to characterize dynamic changes of EEG patterns for the detection and classification of epilepsy. Four different dynamic Bayesian modeling methods were evaluated using multi-subject epileptic EEG data. Experimental results show that an accuracy of 98.0% can be achieved by one of the four methods. The same method also provides an overall accuracy of 87.7% for the classification of seven different seizure types.

Macrocyclic Compounds from Ansamycin Antibiotic Class as Inhibitors of PD1-PDL1 Protein-Protein Interaction.

The ability of tumors to escape from immune destruction is attributed to the protein-protein interaction between programmed cell death protein 1 (PD1) and programmed cell death ligand 1 (PDL1) proteins expressed by immune T cells and cancer cells, respectively. Therefore, pharmacological inhibition of the PD1-PDL1 interaction presents an important therapeutic target against a variety of tumors expressing PDL1 on their cell surface. Recently, five antibodies have been approved and several are in clinical trials against the PD1-PDL1 protein-protein interaction target. In contrast, there are very few reports of small-molecule inhibitors of PD1-PDL1 interaction, and most of them have relatively modest or weak inhibition activities, emphasizing the difficulty in designing small-molecule inhibitors against this challenging target. Therefore, we focused our attention on macrocycles that are known to exhibit target activity comparable to large macromolecules despite having molecular weights closer to small, drug-like molecules. In this context, our present study led to the identification of several macrocyclic compounds from the ansamycin antibiotics class to be inhibitors of PD1-PDL1 interaction. Importantly, one of these macrocyclic antibiotics, Rifabutin, showed an IC50 value of ca. 25 µM. This is remarkable considering it has a relatively low molecular weight and still is capable of inhibiting PD1-PDL1 protein-protein interaction whose binding interface spans over ca. 1970 Å2. Thus, these macrocycles may serve as guiding points for discovery and optimization of more potent, selective small-molecule inhibitors of PD1-PDL1 interaction, one of the most promising therapeutic targets against cancer.

Improving brain-computer interface classification using adaptive common spatial patterns.

Common Spatial Patterns (CSP) is a widely used spatial filtering technique for electroencephalography (EEG)-based brain-computer interface (BCI). It is a two-class supervised technique that needs subject-specific training data. Due to EEG nonstationarity, EEG signal may exhibit significant intra- and inter-subject variation. As a result, spatial filters learned from a subject may not perform well for data acquired from the same subject at a different time or from other subjects performing the same task. Studies have been performed to improve CSP's performance by adding regularization terms into the training. Most of them require target subjects' training data with known class labels. In this work, an adaptive CSP (ACSP) method is proposed to analyze single trial EEG data from single and multiple subjects. The method does not estimate target data's class labels during the adaptive learning and updates spatial filters for both classes simultaneously. The proposed method was evaluated based on a comparison study with the classic CSP and several CSP-based adaptive methods using motor imagery EEG data from BCI competitions. Experimental results indicate that the proposed method can improve the classification performance as compared to the other methods. For circumstances where true class labels of target data are not instantly available, it was examined if adding classified target data to training data would improve the ACSP learning. Experimental results show that it would be better to exclude them from the training data. The proposed ACSP method can be performed in real-time and is potentially applicable to various EEG-based BCI applications.