SME-MFP: A novel spatiotemporal neural network with multiangle initialization embedding toward multifunctional peptides prediction.

As a promising alternative to conventional antibiotic drugs in the biomedical field, functional peptide has been widely used in disease treatment owing to its low toxicity, high absorption rate, and biological activity. Recently, several machine learning methods have been developed for functional peptide prediction. However, the main research heavily relies on statistical features and few consider multifunctional peptide identification. So, we propose SME-MFP, a novel predictor in the imbalanced multi-label functional peptide datasets. First, we employ physicochemical and evolutionary information to represent the peptide sequence's initialization features from multiple perspectives. Second, the features are fused and then put into spatial feature extractors, where the residual connection and multiscale convolutional neural network extract more discriminative features of different lengths' peptide sequences. Besides, we also design AFT-based temporal feature extractors to fully capture the global interactions of the sequences. Finally, devising a new loss to replace the traditional cross entropy loss to settle the class imbalance problems. The results show that our framework not only enhances the model's ability to capture sequence features effectively, but also accuracy improves by 3.89% over existing methods on public peptide datasets.

Shading treatment during late stage of seed development promotes subsequent seed germination and seedlings establishment in sunflower.

During the sunflower seed production process, the role of artificial shading treatment (ST) in seed development and subsequent seed germination remains largely unknown. In the present study, sunflower mother plants were artificially shaded during 1-34 (full period-ST, FST), 1-22 (early period-ST, EST), and 22-34 (late period-ST, LST) days after pollination (DAP), to examine the effects of parental shading on subsequent seed germination. Both FST and EST significantly reduced the photosynthetic efficiency of sunflower, manifested as decreased seed dry weight and unfavorable seed germination. On the contrary, LST remarkably increased seed dry weight and promoted subsequent seed germination and seedling establishment. LST enhanced the activities of several key enzymes involved in triglyceride anabolism and corresponding-genes expression, which in turn increased the total fatty acid contents and altered the fatty acid composition. During early germination, the key enzyme activities involved in triglyceride disintegration and corresponding-gene expressions in LST seeds were apparently higher than those in seeds without the shading treatment (WST). Consistently, LST seeds had significant higher contents of ATP and soluble sugar. Moreover, enzyme activities related to abscisic acid (ABA) biosynthesis and corresponding gene expressions decreased within LST seeds, whereas the enzyme activities and corresponding gene expressions associated with gibberellin (GA) biosynthesis were increased. These results were also evidenced by the reduced ABA content but elevated GA level within LST seeds, giving rise to higher GA/ABA ratio. Our findings suggested that LST could promote sunflower seed development and subsequent seed germination as well as seedling establishment through modulating the dynamic metabolism of triglycerides, fatty acid and GA/ABA balance.

Hybrid framework for membrane protein type prediction based on the PSSM.

Membrane proteins are considered the major source of drug targets and are indispensable for drug design and disease prevention. However, traditional biomechanical experiments are costly and time-consuming; thus, many computational methods for predicting membrane protein types are gaining popularity. The position-specific scoring matrix (PSSM) method is an excellent method for describing the evolutionary information of protein sequences. In this study, we propose an improved capsule neural network (ICNN) model based on a capsule neural network to acquire sufficient relevant information from the PSSM. Furthermore, accounting for the complementarity between traditional machine learning and deep learning, we propose a hybrid framework that combines both approaches to predict protein types. This framework trains 41 baseline models based on the PSSM. The optimal subset features, selected after traversal, are fused using a two-level decision-level feature fusion approach. Subsequently, comparisons are made using three combined strategies within an ensemble learning framework. The experimental results demonstrate that solely relying on PSSM input, the proposed method not only surpasses the optimal methods by 1.52 % , 2.26 % and 2.67 % on Dataset1, Dataset2, and Datasets3, respectively, but also exhibits superior generalizability. Furthermore, the code and dataset can be free download at https://github.com/ruanxiaoli/membrane-protein-types .

Efficient Fabrication of Quartz Glass Using Laser Coaxial Powder-Fed Additive Manufacturing Approach.

This article investigates a laser-directed energy deposition additive manufacturing (AM) method, based on coaxial powder feeding, for preparing quartz glass. Through synergistic optimization of line deposition and plane deposition experiments, key parameters of laser coaxial powder feeding AM were identified. The corresponding mechanical properties, thermal properties, and microstructure of the bulk parts were analyzed. The maximum mechanical strength of the obtained quartz glass element reached 72.36 ± 5.98 MPa, which is ca. 95% that of quartz glass prepared by traditional methods. The thermal properties of the obtained quartz glass element were also close to those prepared by traditional methods. The present research indicates that one can use laser AM technology that is based on coaxial powder feeding to form quartz glass with high density and good thermodynamic properties. Such quartz glass has substantial potential in, for example, optics and biomedicine.

Rapid determination of total flavonoid content, xanthine oxidase inhibitory activities, and antioxidant activity in Prunus mume by near-infrared spectroscopy.

Evaluating the quality of herbal medicine based on the content and activity of its main components is highly beneficial. Developing an eco-friendly determination method has significant application potential. In this study, we propose a new method to simultaneously predict the total flavonoid content (TFC), xanthine oxidase inhibitory (XO) activity, and antioxidant activity (AA) of Prunus mume using near-infrared spectroscopy (NIR). Using the sodium nitrite-aluminum nitrate-sodium hydroxide colorimetric method, uric acid colorimetric method, and 2,2-diphenyl-1-picrylhydrazyl radical (DPPH) free radical scavenging activity as reference methods, we analyzed TFC, XO, and AA in 90 P. mume samples collected from different locations in China. The solid samples were subjected to NIR. By employing spectral preprocessing and optimizing spectral bands, we established a rapid prediction model for TFC, XO, and AA using partial least squares regression (PLS). To improve the model's performance and eliminate irrelevant variables, competitive adaptive reweighted sampling (CARS) was used to calculate the pretreated full spectrum. Evaluation model indicators included the root mean square error of cross-validation (RMSECV) and determination coefficient (R2) values. The TFC, XO, and AA model, combining optimal spectral preprocessing and spectral bands, had RMSECV values of 0.139, 0.117, and 0.121, with RCV2 values exceeding 0.92. The root mean square error of prediction (RMSEP) for the TFC, XO, and AA model on the prediction set was 0.301, 0.213, and 0.149, with determination coefficient (RP2) values of 0.915, 0.933, and 0.926. The results showed a strong correlation between NIR with TFC, XO, and AA in P. mume. Therefore, the established model was effective, suitable for the rapid quantification of TFC, XO, and AA. The prediction method is simple and rapid, and can be extended to the study of medicinal plant content and activity.

Bayesian diagnostic test evaluation and true prevalence estimation of malnutrition in gastric cancer patients.

BACKGROUND & AIMS: Malnutrition is prevalent among gastric cancer (GC) patients, necessitating early assessment of nutritional status to guide monitoring and interventions for improved outcomes. We aim to evaluate the accuracy and prognostic capability of three nutritional tools in GC patients, providing insights for clinical implementation. METHODS: The present study is an analysis of data from 1308 adult GC patients recruited in a multicenter from July 2013 to July 2018. Nutritional status was assessed using Nutritional Risk Screening 2002 (NRS-2002), Patient-Generated Subjective Global Assessment (PG-SGA) and Global Leadership Initiative on Malnutrition (GLIM) criteria. Bayesian latent class model (LCM) estimated the malnutrition prevalence of GC patients, sensitivity and specificity of nutritional tools. Cox regression model analyzed the relationship between nutritional status and overall survival (OS) in GC patients. RESULTS: Among 1308 GC patients, NRS-2002, PG-SGA, and GLIM identified 50.46%, 76.76%, and 68.81% as positive, respectively. Bayesian LCM analysis revealed that PG-SGA had the highest sensitivity (0.96) for malnutrition assessment, followed by GLIM criteria (0.78) and NRS-2002 (0.65). Malnutrition or being at risk of malnutrition were identified as independent prognostic factors for OS. Use any of these tools improved survival prediction in TNM staging system. CONCLUSION: PG-SGA is the most reliable tool for diagnosing malnutrition in GC patients, whereas NRS-2002 is suitable for nutritional screening in busy clinical practice. Given the lower sensitivity of NRS-2002, direct utilization of GLIM for nutritional assessment may be necessary. Each nutritional tool should be associated with a specific course of action, although further research is needed.