RESUMEN
Here we present a novel machine-learning approach to predict protein aggregation propensity (PAP) which is a key factor in the formation of amyloid fibrils based on logistic regression (LR). Amyloid fibrils are associated with various neurodegenerative diseases (ND) such as Alzheimer's disease (AD) and Parkinson's disease (PD), which are caused by oxidative stress and impaired protein homeostasis. Accordingly, the paper uses a dataset of hexapeptides with known aggregation tendencies and eight physiochemical features to train and test the LR model. Also, it evaluates the performance of the LR model using F-measure and Matthews correlation coefficient (MCC) as metrics and compares it with other existing methods. Moreover, it investigates the effect of combining sequence and feature information in the prediction. In conclusion, the LR model with sequence and feature information achieves high F-measure (0.841) and MCC (0.6692), outperforming other methods and demonstrating its efficiency and reliability for PAP prediction. In addition, the overall performance of the concluded method was higher than the other known servers, for instance, Aggrescan, Metamyl, Foldamyloid, and PASTA 2.0. The LR model can be accessed at: https://github.com/KatherineEshari/Protein-aggregation-prediction.
Asunto(s)
Amiloide , Agregado de Proteínas , Modelos Logísticos , Reproducibilidad de los Resultados , Aprendizaje AutomáticoRESUMEN
In this study, the chitin of adult Mediterranean flour moth (Ephestia kuheniella) (Cht) was extracted and then converted to chitosan by deacetylation process to achieve the chitosan derived from E. kuheniella (Chsfm). The new chitosan-based scaffold was produced using the polyvinyl alcohol (PVA) co-electrospinning technique. The degree of deacetylation was obtained using the distillation-titration and Fourier transform infrared spectroscopy. The surface morphology and crystallinity index of Chsfm were observed using scanning electron microscopy and X-ray diffraction analysis, respectively, and compared with the commercial chitosan (Chsc). Thermogravimetric analysis was used to estimate two chitosans' water content and thermal stability. The average molecular mass analysis was performed using viscometry. Moreover, the minimum inhibitory concentration and DPPH assay were used to study the antimicrobial activity and antioxidant potential of the Chsfm, respectively. Accordingly, Chsfm was smoother with fewer pores and flakes than Chsc, and its crystallinity index was higher than Chsc. The water content and thermal stability were lower and similar for Chsfm compared to Chsc. The average molecular mass of Chsfm was ~ 5.8 kDa, making it classified as low molecular weight chitosan. The antimicrobial activity of Chsfm against a representative Gram-negative bacteria; E. coli resulted to be the same as Chsc. However, less effective than Chsc against a representative Gram-positive bacteria is S. aureus. The Chsfm/PVA ratio scaffold was optimized at 30:70 to fabricate a uniform nanofiber scaffold.