Cancer is one of the most dangerous diseases in the world, killing millions of people every year. Drugs composed of anticancer peptides have been used to treat cancer with low side effects in recent years. Therefore, identifying anticancer peptides has become a focus of research. In this study, an improved anticancer peptide predictor named ACP-GBDT, based on gradient boosting decision tree (GBDT) and sequence information, is proposed. To encode the peptide sequences included in the anticancer peptide dataset, ACP-GBDT uses a merged-feature composed of AAIndex and SVMProt-188D. A GBDT is adopted to train the prediction model in ACP-GBDT. Independent testing and ten-fold cross-validation show that ACP-GBDT can effectively distinguish anticancer peptides from non-anticancer ones. The comparison results of the benchmark dataset show that ACP-GBDT is simpler and more effective than other existing anticancer peptide prediction methods.

Genes, the nucleotide sequences that encode a polypeptide chain or functional RNA, are the basic genetic unit controlling biological traits. They are the guarantee of the basic structures and functions in organisms, and they store information related to biological factors and processes such as blood type, gestation, growth, and apoptosis. The environment and genetics jointly affect important physiological processes such as reproduction, cell division, and protein synthesis. Genes are related to a wide range of phenomena including growth, decline, illness, aging, and death. During the evolution of organisms, there is a class of genes that exist in a conserved form in multiple species. These genes are often located on the dominant strand of DNA and tend to have higher expression levels. The protein encoded by it usually either performs very important functions or is responsible for maintaining and repairing these essential functions. Such genes are called persistent genes. Among them, the irreplaceable part of the body’s life activities is the essential gene. For example, when starch is the only source of energy, the genes related to starch digestion are essential genes. Without them, the organism will die because it cannot obtain enough energy to maintain basic functions. The function of the proteins encoded by these genes is thought to be fundamental to life. Nowadays, DNA can be extracted from blood, saliva, or tissue cells for genetic testing, and detailed genetic information can be obtained using the most advanced scientific instruments and technologies. The information gained from genetic testing is useful to assess the potential risks of disease, and to help determine the prognosis and development of diseases. Such information is also useful for developing personalized medication and providing targeted health guidance to improve the quality of life. Therefore, it is of great theoretical and practical significance to identify important and essential genes. In this paper, the research status of essential genes and the essential genome database of bacteria are reviewed, the computational prediction method of essential genes based on communication coding theory is expounded, and the significance and practical application value of essential genes are discussed.

Range query is the hot topic of the privacy-preserving data publishing. To preserve privacy, the large range query means more accumulate noise will be injected into the input data. This study presents a research on differential privacy for range query via Haar wavelet transform and Gaussian mechanism. First, the noise injected into the input data via Laplace mechanism is analyzed, and we conclude that it is difficult to judge the level of privacy protection based on the Haar wavelet transform and Laplace mechanism for range query because the sum of independent random Laplace variables is not a variable of a Laplace distribution. Second, the method of injecting noise into Haar wavelet coefficients via Gaussian mechanism is proposed in this study. Finally, the maximum variance for any range query under the framework of Haar wavelet transform and Gaussian mechanism is given. The analysis shows that using Haar wavelet transform and Gaussian mechanism, we can preserve the differential privacy for each input data and any range query, and the variance of noise is far less than that just using the Gaussian mechanism. In an experimental study on the dataset age extracted from IPUM’s census data of the United States, we confirm that the proposed mechanism has much smaller maximum variance of noises than the Gaussian mechanism for range-count queries.

Various bacterial pathogens can deliver their secreted effectors to host cells via type IV secretion system (T4SS) and cause host diseases. Since T4SS secreted effectors (T4SEs) play important roles in the interaction between pathogens and host, identifying T4SEs is crucial to understanding of the pathogenic mechanism of T4SS. We established an effective predictor called SMOPredT4SE to identify T4SEs from protein sequences. SMOPredT4SE employed combination features of series correlation pseudo amino acid composition and position-specific scoring matrix to present protein sequences, and employed support vector machines (SVM) training with sequential minimal optimization (SMO) arithmetic to train the prediction model (To distinguish it from the traditional SVM, we will abbreviate it as SMO later). In the 5-fold cross-validation test, SMOPredT4SE’s overall accuracy was 95.6%. Experiments on comparison with other feature, classifiers, and existing methods are conducted. Experimental results show the effectiveness of SMOPredT4SE in predicting T4SEs.

The major histocompatibility complex (MHC) comprises a set of genes located on chromosome 6 in humans and chromosome 17 in mice. It is instrumental in autoimmune diseases, the success of organ transplants, and antigen presentation in tumor immunotherapy. Therefore, accurately identifying MHC is essential for understanding its role in immunology. In this study, we proposed a machine learning-based model for predicting MHC, called ESM-MHC. Firstly, the ESM protein language model was employed to characterize protein sequences, resulting in the generation of 1280-dimensional features. Secondly, principal component analysis (PCA) was employed to analyze these features and select the features that showed notably different distributions between positive and negative samples as the final feature set. Finally, Multi-Layer Perceptron (MLP) was trained on the final feature set to obtain the identification model. The model achieved an accuracy of 95.97% and 96% in the 10-fold cross-validation and test set, respectively, outperforming existing methods in terms of performance.