MOTIVATION: Bioactive peptides exhibit immense potential in pharmaceutical and food science domains, with antioxidant peptides (AOPs) garnering significant attention for their roles in scavenging free radicals. However, traditional discovery methods are inefficient and costly. This study introduces RLAnOxPeptide, an integrated computational framework that merges machine learning and reinforcement learning for the efficient prediction and de novo design of AOPs. RESULTS: The framework initially establishes a high-precision predictor, RLP-T5Pred, based on the ProtT5 model via a 'protein-to-peptide' knowledge transfer strategy. By employing label smoothing and logit penalty regularization, it achieves state-of-the-art accuracy (AUC-ROC: 0.9692) and robust calibration. The second component is the generator, RLP-T5Gen, which is trained in an iterative 'Yin-Yang' loop combining supervised learning (to maintain sequence syntax) and reinforcement learning (to drive innovation). Guided by RLP-T5Pred serving as a fixed evaluator and a multi-objective reward function, the generator efficiently designs novel AOPs with high predicted activity. We experimentally validated the framework by synthesizing 17 designed peptides. Most candidates demonstrated potent radical scavenging abilities in chemical assays (DPPH and ABTS), leading to the selection of the top five candidates for cellular validation. In a t-BHP-induced HepG2 cell model, peptides Pep4, Pep5, Pep10, and Pep11 exhibited significant protective effects against oxidative damage. Consequently, the RLAnOxPeptide framework provides a powerful, experimentally verified paradigm for accelerating the discovery of novel antioxidant peptides. AVAILABILITY: The datasets generated and/or analysed during the current study, along with model outputs and representative peptide sequences, have been deposited in a public repository. The RLAnOxPeptide framework source code is available at GitHub: https://github.com/changshh/RLAnOxPeptide. An archival snapshot of the code used to perform the experiments described in this manuscript has been deposited in Zenodo with the DOI: 10.5281/zenodo.20078425. An interactive online demonstration is also available via Hugging Face Spaces: https://huggingface.co/spaces/chshan/RLAnOxPeptide.

With advancements in technologies like autonomous driving and digital twins, alongside the pursuit of an intelligent future, modern mobile communication systems face unprecedented demands, driving the evolution of sixth-generation (6G) networks. Traditional architectures based on Shannon’s information theory are nearing their limits, necessitating novel paradigms to deliver higher-quality service. Semantic communication has emerged as a cornerstone of 6G, leveraging abstract semantic features to reduce data transmission volume. This paper proposes a semantic information extraction method using convolutional neural networks (CNNs) and employs a generative adversarial network (GAN) at the receiver for semantic reconstruction. Experimental results confirm its superior efficiency in image compression and reconstruction, supporting the practical application of semantic communication.

As wireless networks evolve, Vehicle-to-Everything (V2X) communications, including vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), and vehicle-to-pedestrian (V2P), have gradually become more sophisticated, enabling information exchange between vehicles and their surrounding environment, thereby enhancing road safety and traffic efficiency. However, ensuring service quality when vehicles are moving at high speeds remains a significant challenge that cannot be overlooked.Due to the rapid changes in channels caused by the high mobility of vehicles, this paper models resource allocation as a multi-agent deep reinforcement learning problem. It analyzes multiple V2V links and V2I links and proposes a resource allocation algorithm that considers V2V communication efficiency based on the Deep Deterministic Policy Gradient (DDPG).Each agent interacts with the V2X network environment to obtain a common reward function and aggregates actions from other agents for training the critic network collectively. By designing the reward function, a balance between communication efficiency and power control can be achieved, thereby effectively increasing the transmission rate of V2V links.

Aberrant alternative splicing, prevalent in cancer, impacts various cancer hallmarks involving proliferation, angiogenesis, and invasion. Splicing disruption often results from somatic point mutations rewiring functional pathways to support cancer cell survival. We introduce iSoMAs (iSoform expression and somatic Mutation Association), an efficient computational pipeline leveraging principal component analysis technique, to explore how somatic mutations influence transcriptome-wide gene expression at the isoform level. Applying iSoMAs to 33 cancer types comprising 9,738 tumor samples in The Cancer Genome Atlas, we identified 908 somatically mutated genes significantly associated with altered isoform expression across three or more cancer types. Mutations linked to differential isoform expression occurred through both cis- and trans-acting mechanisms, involving well-known oncogenes/suppressor genes, RNA binding protein and splicing factor genes. With wet-lab experiments, we verified direct association between TP53 mutations and differential isoform expression in cell cycle genes. Additional iSoMAs genes have been validated in the literature with independent cohorts and/or methods. Despite the complexity of cancer, iSoMAs attains computational efficiency via dimension reduction strategy and reveals critical associations between regulatory factors and transcriptional landscapes.

Taste peptides have emerged as promising natural flavoring agents attributed to their unique organoleptic properties, high safety profile, and potential health benefits. However, the de novo identification of taste peptides derived from animal, plant, or microbial sources remains a time-consuming and resource-intensive process, significantly impeding their widespread application in the food industry. In this work, we present TastePepAI, a comprehensive artificial intelligence framework for customized taste peptide design and safety assessment. As the key element of this framework, a loss-supervised adaptive variational autoencoder (LA-VAE) is implemented to efficiently optimize the latent representation of sequences during training and facilitate the generation of target peptides with desired taste profiles. Notably, our model incorporates a novel taste-avoidance mechanism, allowing for selective flavor exclusion. Subsequently, our in-house developed toxicity prediction algorithm (SpepToxPred) is integrated in the framework to undergo rigorous safety evaluation of generated peptides. Using this integrated platform, we successfully identified 73 peptides exhibiting sweet, salty, and umami, significantly expanding the current repertoire of taste peptides. This work demonstrates the potential of TastePepAI in accelerating taste peptide discovery for food applications and provides a versatile framework adaptable to broader peptide engineering challenges.

China had conducted some of the most stringent public health measures to control the spread of successive SARS-CoV-2 variants. However, the effectiveness of these measures and their impacts on the associated disease burden have rarely been quantitatively assessed at the national level. To address this gap, we developed a stochastic age-stratified metapopulation model that incorporates testing, contact tracing and isolation, based on 419 million travel movements among 366 Chinese cities. The study period for this model began from September 2022. The COVID-19 disease burden was evaluated, considering 8 types of underlying health conditions in the Chinese population. We identified the marginal effects between the testing speed and reduction in the epidemic duration. The findings suggest that assuming a vaccine coverage of 89%, the Omicron-like wave could be suppressed by 3-day interval population-level testing (PLT), while it would become endemic with 4-day interval PLT, and without testing, it would result in an epidemic. PLT conducted every 3 days would not only eliminate infections but also keep hospital bed occupancy at less than 29.46% (95% CI, 22.73-38.68%) of capacity for respiratory illness and ICU bed occupancy at less than 58.94% (95% CI, 45.70-76.90%) during an outbreak. Furthermore, the underlying health conditions would lead to an extra 2.35 (95% CI, 1.89-2.92) million hospital admissions and 0.16 (95% CI, 0.13-0.2) million ICU admissions. Our study provides insights into health preparedness to balance the disease burden and sustainability for a country with a population of billions.

“Electronic system design” is an important course closely related to electronic design competition. A wide range of knowledge modules are involved in the class, but some modules are not studied by students. Due to the constraints of classroom time, they need to preview independently before class under the guidance of teachers. We design a recommendation system based on improved collaborative filtering algorithm, so that students can learn by themselves according to the learning resources pushed by teachers. To increase the accuracy of collaborative filtering algorithm, the user's attribute similarity is combined with the traditional collaborative filtering recommendation algorithm to improve the cold start problem and data sparsity of the algorithm. Then we build an experimental teaching platform of "Electronic System Design" curriculum to achieve automatic recommendation of experimental learning resources under teachers’ guidance.

Mutations to the human kinome are known to play causal roles in cancer. The kinome regulates numerous cell processes including growth, proliferation, differentiation, and apoptosis. In addition to aberrant expression, aberrant alternative splicing of cancer-driver genes is receiving increased attention as it could lead to loss or gain of functional domains, altering a kinase's downstream impact. The present study quantifies changes in gene expression and isoform ratios in the kinome of metastatic melanoma cells relative to primary tumors. We contrast 538 total kinases and 3,040 known kinase isoforms between 103 primary tumor and 367 metastatic samples from The Cancer Genome Atlas (TCGA). We find strong evidence of differential expression (DE) at the gene level in 123 kinases (23%). Additionally, of the 468 kinases with alternative isoforms, 60 (13%) had significant difference in isoform ratios (DIR). Notably, DE and DIR have little correlation; for instance, although DE highlights enrichment in receptor tyrosine kinases (RTKs), DIR identifies altered splicing in non-receptor tyrosine kinases (nRTKs). Using exon junction mapping, we identify five examples of splicing events favored in metastatic samples. We demonstrate differential apoptosis and protein localization between SLK isoforms in metastatic melanoma. We cluster isoform expression data and identify subgroups that correlate with genomic subtypes and anatomic tumor locations. Notably, distinct DE and DIR patterns separate samples with BRAF hotspot mutations and (N/K/H)RAS hotspot mutations, the latter of which lacks effective kinase inhibitor treatments. DE in RAS mutants concentrates in CMGC kinases (a group including cell cycle and splicing regulators) rather than RTKs as in BRAF mutants. Furthermore, isoforms in the RAS kinase subgroup show enrichment for cancer-related processes such as angiogenesis and cell migration. Our results reveal a new approach to therapeutic target identification and demonstrate how different mutational subtypes may respond differently to treatments highlighting possible new driver events in cancer.

It has been increasingly accepted that microRNA (miRNA) can both activate and suppress gene expression, directly or indirectly, under particular circumstances. Yet, a systematic study on the switch in their interaction pattern between activation and suppression and between normal and cancer conditions based on multi-omics evidences is not available. We built miRactDB, a database for miRNA-gene interaction, at https://ccsm.uth.edu/miRactDB, to provide a versatile resource and platform for annotation and interpretation of miRNA-gene relations. We conducted a comprehensive investigation on miRNA-gene interactions and their biological implications across tissue types in both tumour and normal conditions, based on TCGA, CCLE and GTEx databases. We particularly explored the genetic and epigenetic mechanisms potentially contributing to the positive correlation, including identification of miRNA binding sites in the gene coding sequence (CDS) and promoter regions of partner genes. Integrative analysis based on this resource revealed that top-ranked genes derived from TCGA tumour and adjacent normal samples share an overwhelming part of biological processes, which are quite different than those from CCLE and GTEx. The most active miRNAs predicted to target CDS and promoter regions are largely overlapped. These findings corroborate that adjacent normal tissues might have undergone significant molecular transformations towards oncogenesis before phenotypic and histological change; and there probably exists a small yet critical set of miRNAs that profoundly influence various cancer hallmark processes. miRactDB provides a unique resource for the cancer and genomics communities to screen, prioritize and rationalize their candidates of miRNA-gene interactions, in both normal and cancer scenarios.

Adaptive mesh refinement based on octree data structures has enabled efficient simulations of complex physical phenomena. Existing meshing algorithms were proposed with the assumption that computer memory is volatile. Consequently, for failure recovery, in-core algorithms need to save memory states as snapshots with slow file I/O, while out-of-core algorithms store octants on disk for persistence. However, neither was designed to best exploit the unique characteristics of non-volatile byte-addressable memory (NVBM). We propose a novel data structure, the Distributed Persistent Merged octree (DPM-octree), for both meshing and in-memory storage of persistent octrees using NVBM. DPM-octree is a multi-version data structure that can recover from failures using an earlier persistent version stored in NVBM. In addition, we design a feature-directed sampling approach to help dynamically transform the DPM-octree layout for reducing NVBM-induced memory write latency. DPM-octree uses parity trees which are created using erasure coding and stored in NVBM to support low-latency in-memory octant recovery after data loss. DPM-octree has been successfully integrated with the Gerris software for simulation of fluid dynamics. Our experimental results with real-world scientific workloads show that DPM-octree scales up to 1.1 billion mesh elements with 1,000 processors on the Titan supercomputer.

Octree-based mesh adaptation has enabled simulations of complex physical phenomena. Existing meshing algorithms were proposed with the assumption that computer memory is volatile. Consequently, for failure recovery, the in-core algorithms need to save memory states as snapshots with slow file I/Os. The out-of-core algorithms store octants on disks for persistence. However, neither of them was designed to leverage unique characteristics of non-volatile byte-addressable memory (NVBM). In this paper, we propose a novel data structure Persistent Merged octree (PM-octree) for both meshing and in-memory storage of persistent octrees using NVBM. It is a multi-version data structure and can recover from failures using its earlier persistent version stored in NVBM. In addition, we design a feature-directed sampling approach to help dynamically transform the PM-octree layout for reducing NVBM-induced memory write latency. PM-octree has been successfully integrated with Gerris software for simulation of fluid dynamics. Our experimental results with real-world scientific workloads show that PM-octree scales up to 1.1 billion mesh elements with 1000 processors on the Titan supercomputer.

MOTIVATION: It becomes widely accepted that human cancer is a disease involving dynamic changes in the genome and that the missense mutations constitute the bulk of human genetic variations. A multitude of computational algorithms, especially the machine learning-based ones, has consequently been proposed to distinguish missense changes that contribute to the cancer progression ('driver' mutation) from those that do not ('passenger' mutation). However, the existing methods have multifaceted shortcomings, in the sense that they either adopt incomplete feature space or depend on protein structural databases which are usually far from integrated. RESULTS: In this article, we investigated multiple aspects of a missense mutation and identified a novel feature space that well distinguishes cancer-associated driver mutations from passenger ones. An index (DX score) was proposed to evaluate the discriminating capability of each feature, and a subset of these features which ranks top was selected to build the SVM classifier. Cross-validation showed that the classifier trained on our selected features significantly outperforms the existing ones both in precision and robustness. We applied our method to several datasets of missense mutations culled from published database and literature and obtained more reasonable results than previous studies. AVAILABILITY: The software is available online at http://www.methodisthealth.com/software and https://sites.google.com/site/drivermutationidentification/. CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: The epidermal growth factor receptor (EGFR) signaling pathway and angiogenesis in brain cancer act as an engine for tumor initiation, expansion and response to therapy. Since the existing literature does not have any models that investigate the impact of both angiogenesis and molecular signaling pathways on treatment, we propose a novel multi-scale, agent-based computational model that includes both angiogenesis and EGFR modules to study the response of brain cancer under tyrosine kinase inhibitors (TKIs) treatment. RESULTS: The novel angiogenesis module integrated into the agent-based tumor model is based on a set of reaction-diffusion equations that describe the spatio-temporal evolution of the distributions of micro-environmental factors such as glucose, oxygen, TGFα, VEGF and fibronectin. These molecular species regulate tumor growth during angiogenesis. Each tumor cell is equipped with an EGFR signaling pathway linked to a cell-cycle pathway to determine its phenotype. EGFR TKIs are delivered through the blood vessels of tumor microvasculature and the response to treatment is studied. CONCLUSIONS: Our simulations demonstrated that entire tumor growth profile is a collective behaviour of cells regulated by the EGFR signaling pathway and the cell cycle. We also found that angiogenesis has a dual effect under TKI treatment: on one hand, through neo-vasculature TKIs are delivered to decrease tumor invasion; on the other hand, the neo-vasculature can transport glucose and oxygen to tumor cells to maintain their metabolism, which results in an increase of cell survival rate in the late simulation stages.

BACKGROUND: RNA interference (RNAi) becomes an increasingly important and effective genetic tool to study the function of target genes by suppressing specific genes of interest. This system approach helps identify signaling pathways and cellular phase types by tracking intensity and/or morphological changes of cells. The traditional RNAi screening scheme, in which one siRNA is designed to knockdown one specific mRNA target, needs a large library of siRNAs and turns out to be time-consuming and expensive. RESULTS: In this paper, we propose a conceptual model, called compressed sensing RNAi (csRNAi), which employs a unique combination of group of small interfering RNAs (siRNAs) to knockdown a much larger size of genes. This strategy is based on the fact that one gene can be partially bound with several small interfering RNAs (siRNAs) and conversely, one siRNA can bind to a few genes with distinct binding affinity. This model constructs a multi-to-multi correspondence between siRNAs and their targets, with siRNAs much fewer than mRNA targets, compared with the conventional scheme. Mathematically this problem involves an underdetermined system of equations (linear or nonlinear), which is ill-posed in general. However, the recently developed compressed sensing (CS) theory can solve this problem. We present a mathematical model to describe the csRNAi system based on both CS theory and biological concerns. To build this model, we first search nucleotide motifs in a target gene set. Then we propose a machine learning based method to find the effective siRNAs with novel features, such as image features and speech features to describe an siRNA sequence. Numerical simulations show that we can reduce the siRNA library to one third of that in the conventional scheme. In addition, the features to describe siRNAs outperform the existing ones substantially. CONCLUSIONS: This csRNAi system is very promising in saving both time and cost for large-scale RNAi screening experiments which may benefit the biological research with respect to cellular processes and pathways.