Antioxidant proteins are involved importantly in many aspects of cellular life activities. They protect the cell and DNA from oxidative substances (such as peroxide, nitric oxide, oxygen-free radicals, etc.) which are known as reactive oxygen species (ROS). Free radical generation and antioxidant defenses are opposing factors in the human body and the balance between them is necessary to maintain a healthy body. An unhealthy routine or the degeneration of age can break the balance, leading to more ROS than antioxidants, causing damage to health. In general, the antioxidant mechanism is the combination of antioxidant molecules and ROS in a one-electron reaction. Creating computational models to promptly identify antioxidant candidates is essential in supporting antioxidant detection experiments in the laboratory. In this study, we proposed a machine learning-based model for this prediction purpose from a benchmark set of sequencing data. The experiments were conducted by using 10-fold cross-validation on the training process and validated by three different independent datasets. Different machine learning and deep learning algorithms have been evaluated on an optimal set of sequence features. Among them, Random Forest has been identified as the best model to identify antioxidant proteins with the highest performance. Our optimal model achieved high accuracy of 84.6%, as well as a balance in sensitivity (81.5%) and specificity (85.1%) for antioxidant protein identification on the training dataset. The performance results from different independent datasets also showed the significance in our model compared to previously published works on antioxidant protein identification.

The requesting of detailed information on new drugs including drug-drug interactions or targets is often unavailable and resource-intensive in assessing adverse drug events. To shorten the common evaluation process of drug-drug interactions, we present a machine learning framework-HAINI to predict DDI types for histamine antagonist drugs using simplified molecular-input line-entry systems (SMILES) combined with interaction features based on CYP450 group as inputs. The data used in our research consisted of approved drugs of histamine antagonists that are connected to 26,344 DDI pairs from the DrugBank database. Various classification algorithms such as Naive Bayes, Decision Tree, Random Forest, Logistic Regression, and XGBoost were used with 5-fold cross-validation to approach a large-scale DDIs prediction among histamine antagonist drugs. The prediction performance shows that our model outperformed previously published works on DDI prediction with the best precision of 0.788, a recall of 0.921, and an F1-score of 0.838 among 19 given DDIs types. An important finding of the study is that our prediction is based solely on the SMILES and CYP450 and thus can be applied at the early stage of drug development.

Decellularization has emerged as a potential solution for tracheal replacement. As a fully decellularized graft failed to achieve its purposes, the de-epithelialization partial decellularization protocol appeared to be a promising approach for fabricating scaffolds with preserved mechanical properties and few immune rejection responses after transplantation. Nevertheless, a lack of appropriate concurrent epithelialization treatment can lead to luminal stenosis of the transplant and impede its eventual success. To improve re-epithelialization, autologous nasal epithelial cell sheets generated by our cell sheet engineering platform were utilized in this study under an in vivo rabbit model. The newly created cell sheets have an intact and transplantable appearance, with their specific characteristics of airway epithelial origin being highly expressed upon histological and immunohistochemical analysis. Subsequently, those cell sheets were incorporated with a partially decellularized tracheal graft for autograft transplantation under tracheal partial resection models. The preliminary results two months post operation demonstrated that the transplanted patches appeared to be wholly integrated into the host trachea with adequate healing of the luminal surface, which was confirmed via endoscopic and histologic evaluations. The satisfactory result of this hybrid scaffold protocol could serve as a potential solution for tracheal reconstructions in the future.

In this study, we developed a new procedure for the rapid partial decellularization of the harvested trachea. Partial decellularization was performed using a combination of detergent and sonication to completely remove the epithelial layers outside of the cartilage ring. The post-decellularized tracheal segments were assessed with vital staining, which showed that the core cartilage cells remarkably remained intact while the cells outside of the cartilage were no longer viable. The ability of the decellularized tracheal segments to evade immune rejection was evaluated through heterotopic implantation of the segments into the chest muscle of rabbits without any immunosuppressive therapy, which demonstrated no evidence of severe rejection or tissue necrosis under H&E staining, as well as the mechanical stability under stress-pressure testing. Finally, orthotopic transplantation of partially decellularized trachea with no immunosuppression treatment resulted in 2 months of survival in two rabbits and one long-term survival (2 years) in one rabbit. Through evaluations of posttransplantation histology and endoscopy, we confirmed that our partial decellularization method could be a potential method of producing low-immunogenic cartilage scaffolds with viable, functional core cartilage cells that can achieve long-term survival after in vivo transplantation.