Comparison of deep learning models with simple method to assess the problem of antimicrobial peptides prediction.

Antibiotic-resistant strains are an emerging threat to public health. The usage of antimicrobial peptides (AMPs) is one of the promising approaches to solve this problem. For the development of new AMPs, it is necessary to have reliable prediction methods. Recently, deep learning approaches have been used to predict AMP. In this paper, we want to compare simple and complex methods for these purposes. We used the BERT transformer to create sequence embeddings and the multilayer perceptron (MLP) and light attention (LA) approaches for classification. One of them reached about 80 % accuracy and specificity in benchmark testing, which is on par with the best available methods. For comparison, we proposed a simple method using only the amino acid composition of proteins or peptides. This method has shown good results, at the level of the best methods. We have prepared a special server for predicting the ability of AMPs by amino acid composition: http://bioproteom.protres.ru/antimicrob/.

[Improvement of diagnostics and tactics of treatment of patients of elderly and senile age with acute obturational pulpositional obstacle of tumor genesis.]

The results of providing care to 346 elderly and senile patients with acute obstructive intestinal obstruction of tumor Genesis were analyzed. In the diagnosis of acute intestinal obstruction, along with traditional diagnostic methods, the dynamics of intra-abdominal pressure and hemodynamic parameters in the visceral arteries of the abdominal aorta were evaluated. Based on the study, it was shown that acute obstructive intestinal obstruction is accompanied by an increase in intra-abdominal pressure and a reduction in blood flow in the visceral arteries of the abdominal aorta. Moreover, the greater the degree of intestinal obstruction, the more pronounced these changes are. The use of these studies made it possible to improve the diagnosis of acute intestinal obstruction of tumor Genesis. In addition, the assessment of these indicators in the dynamics indicated the effectiveness of conservative measures and gave reason to establish more timely indications for performing surgery. A comprehensive approach to timely diagnosis of acute intestinal obstruction of tumor origin allowed us to identify a group of patients who can perform surgical interventions using endovideosurgical technologies. The use of minimally invasive technologies in the treatment of colon cancer complicated by acute intestinal obstruction has reduced the number of postoperative complications and the level of postoperative mortality.

Amyloid Properties of Titin.

This review considers data on structural and functional features of titin, on the role of this protein in determination of mechanical properties of sarcomeres, and on specific features of regulation of the stiffness and elasticity of its molecules, amyloid aggregation of this protein in vitro, and possibilities of formation of intramolecular amyloid structure in vivo. Molecular mechanisms are described of protection of titin against aggregation in muscle cells. Based on the data analysis, it is supposed that titin and the formed by it elastic filaments have features of amyloid.

Search for the most stable folds of protein chains: III. Improvement in fold recognition by averaging over homologous sequences and 3D structures.

Three-dimensional (3D) protein fold recognition by query sequence can be improved using information of fold recognition yielded by the sequences homologous to the query one. This idea is now used more and more widely. Our paper presents its consequent development. We suggest incorporating information both on the sequences homologous to the query protein sequence and the 3D structures homologous to the target (already deciphered) protein folds. We show that both these tricks, and especially their combination reduces errors in fold recognition by the threading method. Proteins 2000;40:494-501.