With the development of mass spectrometry technologies and bioinformatics analysis algorithms, disease research-driven human proteome project (HPP) is advancing rapidly. Protein biomarkers play critical roles in clinical applications and the biomarker discovery strategies and methods have become one of research hotspots. Feature selection and machine learning methods have good effects on solving the "dimensionality" and "sparsity" problems of proteomics data, which have been widely used in the discovery of protein biomarkers. Here, we systematically review the strategy of protein biomarker discovery and the frequently-used machine learning methods. Also, the review illustrates the prospects and limitations of deep learning in this field. It is aimed at providing a valuable reference for corresponding researchers.
Algorithms ; Biomarkers ; Humans ; Machine Learning ; Mass Spectrometry ; Proteomics

Tumor-specific gene mutations might generate suitable neoepitopes for cancer immunotherapy that are highly immunogenic and absent in normal tissues. The high heterogeneity of the tumor genome poses a big challenge for precision cancer immunotherapy. Mutations characteristic of each tumor can help to distinguish it from other tumors. Based on these mutations' characteristic, it is possible to develop immunotherapeutic strategies for specific tumors. In this study, a tumor neoantigen prediction scheme was proposed, in which both the intracellular antigen presentation process and the ability to bind with extracellular MHC molecule were taken into consideration. The overall design is meritorious and may help reduce the cost for validation experiments compared with conventional methods. This strategy was tested with several cancer genome datasets in the TCGA database, and a number of potential tumor neoantigens were predicted for each dataset. These predicted neoantigens showed tumor type specificity and were found in 20% to 70% of cancer patients. This scheme might prove useful clinically in future.
Antigens, Neoplasm ; Computational Biology ; Genome, Human ; Humans ; Immunotherapy ; Mutation ; Neoplasms

Objective To compare the dosimetric characteristics of non-coplanar and coplanar field technology in static intensity-modulated radiotherapy of gastric cancer patients, so as to provide a reference for clinical radiotherapy plan selection. Methods Thirty-six patients with gastric cancer were selected to receive intensity-modulated radiotherapy in Huanggang Central Hospital, which was designed plan A and B. Group A used 7-field coplanar technology, while Group B used 7-field non-coplanar technology. We compared the differences of the optimized monitor unit, the dosimetry of organs at risk and target areas between group A and group B. Results Both group A and B could meet the requirements of doctors. The homogeneity index (0.14 ± 0.02), the conformity index (0.98 ± 0.01), D_min (4315.21 ± 16.74) cGy、D_mean (4679.28 ± 28.39) cGy and D_max(4952.30 ± 33.26) cGy of target areas in group B were better than those of group A. Moreover, the monitor unit of group B was much lower than that of group A, and the difference was statistically significant (P < 0.05). The D_max, D_mean, V₁₅, V₂₀ and V₃₀ of the left and right kidneys in group B were lower than those of group A. The D_max (3408.57 ± 46.03) cGy, D_mean (1250.32 ± 14.27) cGy and V₂₀ (44.91% ± 6.67%) of spinal cord and the D_max (3408.57 ± 46.03) cGy, D_mean (1720.55 ± 17.42) cGy, V₂₀ (25.31% ± 7.78%) and V₃₀ (18.52% ± 1.56%) of small intestine were also lower than those of group A. The differences were statistically significant (P < 0.05). Conclusion The non-coplanar field radiation plan has more advantages in terms of target dose distribution and protection of organs so that it can be more considerably used in the process of planning and design.