Prediction of protein secondary structure using feature selection and analysis approach

The Development of Machine Learning Methods in discriminating Secretory Proteins of Malaria Parasite

Malaria caused by Plasmodium falciparum is one of the major infectious diseases in the world. It is essential to exploit an effective method to predict secretory proteins of malaria parasites to develop effective cures and treatment. Biochemical assays can provide details for accurate identification of the secretory proteins, but these methods are expensive and time-consuming. In this paper, we summarized the machine learning-based identification algorithms and compared the construction strategies between different computational methods. Also, we discussed the use of machine learning to improve the ability of algorithms to identify proteins secreted by malaria parasites.

Bio-detoxification of Jatropha curcas L. cake by a soil-borne Mucor circinelloides strain using a zebrafish survival model and solid-state fermentation

AIMS

The aims of the study were to (i) improve the evaluation criteria of detoxifying Jatropha curcas L. cake (JCC), (ii) isolate and characterize a JCC tolerant strain, (iii) explore its JCC detoxifying potential.

METHODS AND RESULTS

The zebrafish was employed as a survival model to screen the strains capable of detoxifying JCC. A strain identified as Mucor circinelloides SCYA25, which is highly capable of degrading all toxic components, was isolated from soil. Different solid-state fermentation parameters were optimized by response surface methodology. The optimal values for inoculation amount, moisture content, temperature, and time were found to be 18% (1·8 × 10⁶ spores g^-1 cake), 66%, 26, and 36 days, respectively, to achieve maximum detoxification of the JCC (92%). Under optimal fermentation conditions, the protein content of JCC was increased, while the concentrations of ether extract, crude fiber, toxins, and anti-nutritional substances were all degraded considerably (P < 0·05). Scanning electron microscopy and Fourier transform infrared spectrometer analysis revealed that the fermentation process could disrupt the surface structure and improve the ratio of α-helix to β-folding in the JCC protein, which may improve the digestibility when the detoxified JCC is used as a feedstuff.

CONCLUSIONS

Our results indicate that M. circinelloides SCYA25 is able to detoxify JCC and improve its nutritional profile, which is beneficial to the safe utilization of JCC as a protein feedstuff.

SIGNIFICANCE AND IMPACT OF THE STUDY

The newly identified M. circinelloides SCYA25 detoxified JCC in a safe manner to provide a potential alternative to soybean meal for the feed industry. These results also provide a new perspective and method for the toxicity evaluation and utilization of JCC and similar toxic agricultural by-products.

Canis familiaris allergen Can f 7: Expression, purification and analysis of B cell epitopes in Chinese children with dog allergies

Dogs are a major source of indoor allergens. However, the prevalence of dog allergies in China remains unclear, especially in children. In the present study, Can f 7, a canine allergen belonging to the Niemann pick type C2 protein family, was selected to study its sensitization rate in Chinese children with dog allergies. The Can f 7 gene was subcloned into a pET‑28a vector and expressed in Escherichia coli BL21 (DE3) cells. Recombinant Can f 7 was purified by nickel affinity chromatography, identified by SDS‑PAGE electrophoresis, and had its allergenicity assessed by western blot, ELISA and basophil activation tests. Through a series of bioinformatical approaches, B‑cell epitopes, secondary structures, and 3 dimensional (3D) homology modeling of Can f 7 were predicted. The activity of the B cell epitopes was verified by ELISA. The recombinant Can f 7 showed a distinct band with a molecular weight of 14 kDa. Six of 20 sera from dog‑allergic children reacted positively to the Can f 7. Can f 7 induced an ~4.0‑fold increase in cluster of differentiation 63 and C‑C motif chemokine receptor R3 expression in basophils sensitized with the serum of dog‑allergic children compared with those of non‑allergic controls. The secondary structure analysis showed that Can f 7 contains 6 β‑sheets. Five B cell epitopes of Can f 7 were predicted, and two of these were confirmed by ELISA. These results indicate that Can f 7 is an important canine allergen in Chinese children and provide novel data for further research concerning the use of Can f 7 in the diagnosis and treatment of Chinese children with canine allergy symptoms.

Improving Prediction of Self-interacting Proteins Using Stacked Sparse Auto-Encoder with PSSM profiles

Self-interacting proteins (SIPs) play a significant role in the execution of most important molecular processes in cells, such as signal transduction, gene expression regulation, immune response and enzyme activation. Although the traditional experimental methods can be used to generate SIPs data, it is very expensive and time-consuming based only on biological technique. Therefore, it is important and urgent to develop an efficient computational method for SIPs detection. In this study, we present a novel SIPs identification method based on machine learning technology by combing the Zernike Moments (ZMs) descriptor on Position Specific Scoring Matrix (PSSM) with Probabilistic Classification Vector Machines (PCVM) and Stacked Sparse Auto-Encoder (SSAE). More specifically, an efficient feature extraction technique called ZMs is firstly utilized to generate feature vectors on Position Specific Scoring Matrix (PSSM); Then, Deep neural network is employed for reducing the feature dimensions and noise; Finally, the Probabilistic Classification Vector Machine is used to execute the classification. The prediction performance of the proposed method is evaluated on S.erevisiae and Human SIPs datasets via cross-validation. The experimental results indicate that the proposed method can achieve good accuracies of 92.55% and 97.47%, respectively. To further evaluate the advantage of our scheme for SIPs prediction, we also compared the PCVM classifier with the Support Vector Machine (SVM) and other existing techniques on the same data sets. Comparison results reveal that the proposed strategy is outperforms other methods and could be a used tool for identifying SIPs.

Structure-based design for binding peptides in anti-cancer therapy

The conventional anticancer therapeutics usually lack cancer specificity, leading to damage of normal tissues that patients find hard to tolerate. Ideally, anticancer therapeutics carrying payloads of drugs equipped with cancer targeting peptides can act like "guided missiles" with the capacity of targeted delivery toward many types of cancers. Peptides are amenable for conjugation to nano drugs for functionalization, thereby improving drug delivery and cellular uptake in cancer-targeting therapies. Peptide drugs are often more difficult to design through molecular docking and in silico analysis than small molecules, because peptide structures are more flexible, possess intricate molecular conformations, and undergo complex interactions. In this review, the development and application of strategies for structure-based design of cancer-targeting peptides against GRP78 are discussed. This Review also covers topics related to peptide pharmacokinetics and targeting delivery, including molecular docking studies, features that provide advantages for in vivo use, and properties that influence the cancer-targeting ability. Some advanced technologies and special peptides that can overcome the pharmacokinetic challenges have also been included.

Identify Beta-Hairpin Motifs with Quadratic Discriminant Algorithm Based on the Chemical Shifts

Successful prediction of the beta-hairpin motif will be helpful for understanding the of the fold recognition. Some algorithms have been proposed for the prediction of beta-hairpin motifs. However, the parameters used by these methods were primarily based on the amino acid sequences. Here, we proposed a novel model for predicting beta-hairpin structure based on the chemical shift. Firstly, we analyzed the statistical distribution of chemical shifts of six nuclei in not beta-hairpin and beta-hairpin motifs. Secondly, we used these chemical shifts as features combined with three algorithms to predict beta-hairpin structure. Finally, we achieved the best prediction, namely sensitivity of 92%, the specificity of 94% with 0.85 of Mathew’s correlation coefficient using quadratic discriminant analysis algorithm, which is clearly superior to the same method for the prediction of beta-hairpin structure from 20 amino acid compositions in the three-fold cross-validation. Our finding showed that the chemical shift is an effective parameter for beta-hairpin prediction, suggesting the quadratic discriminant analysis is a powerful algorithm for the prediction of beta-hairpin.