XFXin Feng

Xin Feng

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Xin Feng has a total of 69 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Elastic Ranking-Driven Time Series Feature Optimization for Aeroengine Remaining Useful Life Prediction

    byĀ Ruihao Xin, Sudan Bai, Jiankang Fan, Cong Gao, Xin Feng

    This paper proposes a hierarchical recurrent neural network framework that leverages a context-gated mechanism and the elastic sorting of time series indicators, addressing the strong dynamic coupling characteristics of aeroengine operational time series data. This framework addresses the coupling of multi-physical field signals and the interleaved cross-scale degradation characteristics of engine time series data. The framework achieves high-precision predictions of residual service life under complex operating conditions by deeply integrating multi-modal feature engineering with hierarchical time series modeling. An elastic ranking algorithm for time series indexes is designed to adaptively fuse multiple sensors’ time domains, frequency domains, and nonlinear characteristics, thereby constructing a dynamic feature space sensitive to load conditions. This approach addresses the limitations of traditional fixed feature combinations in characterizing variable load conditions. Additionally, a multi-scale stack dilation convolution module is introduced to exponentially enlarge the receptive field, allowing for the capture of long-range dependencies in weakly degraded signals. A bidirectional time–frequency converter decomposes the signal into low-frequency trend components and high-frequency anomaly components, enabling coupling characterization through cross-scale feature interactive gating. Furthermore, context-gated cyclic units based on hierarchical cyclic networks are constructed to hierarchically integrate multi-modal features while dynamically adjusting time-dependent weights, thereby enhancing the model’s causal reasoning ability for long sequence degradation patterns. In four typical experiments conducted on the C-MAPSS dataset, the ERCG-HRNN demonstrates significant improvements in RMSE and Score compared to existing methods.

  • GSCI: a Generative and Sparse Compressed Sensing Imputation framework for scRNA-seq dropout recovery

    byĀ Yan Tian, Meng Li, Bo Han, Jun Zhang, Tao You, Ruihao Xin, Xin Feng

    Single-cell RNA-sequencing data are inherently sparse and high-dimensional, with dropout events introducing a large number of missing values that hinder downstream analyses. To address the dual challenges of data imputation and dimensionality reduction, we propose an integrated recovery framework that combines probabilistic modeling with sparse optimization. The proposed method captures latent distribution patterns underlying gene expression, enabling the reconstruction of nonlinear dependencies among genes. Furthermore, sparsity constraints and heuristic search strategies are employed to enhance recovery accuracy, particularly in regions with low expression, while maintaining global expression consistency. We evaluate the framework on in-domain breast-cancer cohorts, on mask-augmented datasets with prescribed masking ratios and known references, and on 5 heterogeneous external datasets spanning distinct protocols and scales; across these settings, the method outperforms representative baselines in reconstruction error, structural fidelity, and recovery of biologically critical genes. These results highlight the effectiveness of jointly modeling distributional structure and sparsity for the reliable restoration of single-cell expression data.

  • Uncovering hidden biomarkers in systemic lupus erythematosus through mqTrans analysis

    byĀ Tao You, Meng Li, Bo Han, Jun Zhang, Ruihao Xin, Xin Feng

  • Open Access

    Definer: A computational method for accurate identification of RNA pseudouridine sites based on deep learning

    byĀ Bo Han, Sudan Bai, Yang Liu, Jiezhang Wu, Xin Feng, Ruihao Xin

    Pseudouridine is an important modification site, which is widely present in a variety of non-coding RNAs and is involved in a variety of important biological processes. Studies have shown that pseudouridine is important in many biological functions such as gene expression, RNA structural stability, and various diseases. Therefore, accurate identification of pseudouridine sites can effectively explain the functional mechanism of this modification site. Due to the rapid increase of genomics data, traditional biological experimental methods to identify RNA modification sites can no longer meet the practical needs, and it is necessary to accurately identify pseudouridine sites from high-throughput RNA sequence data by computational methods. In this study, we propose a deep learning-based computational method, Definer, to accurately identify RNA pseudouridine loci in three species, Homo sapiens, Saccharomyces cerevisiae and Mus musculus. The method incorporates two sequence coding schemes, including NCP and One-hot, and then feeds the extracted RNA sequence features into a deep learning model constructed from CNN, GRU and Attention. The benchmark dataset contains data from three species, H. sapiens, S. cerevisiae and M. musculus, and the results using 10-fold cross-validation show that Definer significantly outperforms other existing methods. Meanwhile, the data sets of two species, H. sapiens and S. cerevisiae, were tested independently to further demonstrate the predictive ability of the model. In summary, our method, Definer, can accurately identify pseudouridine modification sites in RNA.


  • MRNDR: Multihead Attention-Based Recommendation Network for Drug Repurposing

    byĀ Xin Feng, Zhansen Ma, Cuinan Yu, Ruihao Xin

    As is well-known, the process of developing new drugs is extremely expensive, whereas drug repurposing represents a promising approach to augment the efficiency of new drug development. While this method can indeed spare us from expensive drug toxicity and safety experiments, it still demands a substantial amount of time to carry out precise efficacy experiments for specific diseases, thereby consuming a significant quantity of resources. Therefore, if we can prescreen potential other indications for selected drugs, it could result in substantial cost savings. In light of this, this paper introduces a drug repurposing recommendation model called MRNDR, which stands for Multi-head attention-based Recommendation Network for Drug Repurposing. This model serves as a prediction tool for drug-disease relationships, leveraging the multihead self-attention mechanism that demonstrates robust generalization capabilities. These capabilities stem not only from our extensive million-level training data set, BioRE (Biology Recommended Entity data), but also from the utilization of the WRDS (Weighted Representation Distance Score) algorithm proposed by us. The MRNDR model has achieved new state-of-the-art results on the GP-KG public data set, with an MRR (Mean Reciprocal Rank) score of 0.308 and a Hits@10 score of 0.628. This represents significant improvements of 4.7% (MRR) and 18.1% (Hits@10) over the current best-performing models. Additionally, to further validate the practical utility of the model, we examined results recommended by MRNDR that were not present in the training data set. Some of these recommendations have undergone clinical trials, as evidenced by their presence on ClinicalTrials.gov and the China Clinical Trials Center, indirectly confirming the applicability of MRNDR. The MRNDR model can predict the reusability of candidate drugs, reducing the need for manual expert assessments and enabling efficient drug repurposing.


  • Open Access

    Computational Characterization of Undifferentially Expressed Genes with Altered Transcription Regulation in Lung Cancer

    byĀ Ruihao Xin, Qian Cheng, Xiaohang Chi, Xin Feng, Hang Zhang, Yueying Wang, Meiyu Duan, Tunyang Xie, Xiaonan Song, Qiong Yu, et al.

    A transcriptome profiles the expression levels of genes in cells and has accumulated a huge amount of public data. Most of the existing biomarker-related studies investigated the differential expression of individual transcriptomic features under the assumption of inter-feature independence. Many transcriptomic features without differential expression were ignored from the biomarker lists. This study proposed a computational analysis protocol (mqTrans) to analyze transcriptomes from the view of high-dimensional inter-feature correlations. The mqTrans protocol trained a regression model to predict the expression of an mRNA feature from those of the transcription factors (TFs). The difference between the predicted and real expression of an mRNA feature in a query sample was defined as the mqTrans feature. The new mqTrans view facilitated the detection of thirteen transcriptomic features with differentially expressed mqTrans features, but without differential expression in the original transcriptomic values in three independent datasets of lung cancer. These features were called dark biomarkers because they would have been ignored in a conventional differential analysis. The detailed discussion of one dark biomarker, GBP5, and additional validation experiments suggested that the overlapping long non-coding RNAs might have contributed to this interesting phenomenon. In summary, this study aimed to find undifferentially expressed genes with significantly changed mqTrans values in lung cancer. These genes were usually ignored in most biomarker detection studies of undifferential expression. However, their differentially expressed mqTrans values in three independent datasets suggested their strong associations with lung cancer.


  • SDBA: Score Domain-Based Attention for DNA N4-Methylcytosine Site Prediction from Multiperspectives

    byĀ Ruihao Xin, Fan Zhang, Jiaxin Zheng, Yangyi Zhang, Cuinan Yu, Xin Feng

    In tasks related to DNA sequence classification, choosing the appropriate encoding methods is challenging. Some of the methods encode sequences based on prior knowledge that limits the ability of the model to obtain multiperspective information from the sequences. We introduced a new trainable ensemble method based on the attention mechanism SDBA, which stands for Score Domain-Based Attention. Unlike other methods, we fed the task-independent encoding results into the models and dynamically ensembled features from different perspectives using the SDBA mechanism. This approach allows the model to acquire and weight sequence features voluntarily. SDBA is conceptually general and empirically powerful. It has achieved new state-of-the-art results on the benchmark data sets associated with DNA N4-methylcytosine site prediction.


  • Open Access

    A Multi-Task-Based Deep Multi-Scale Information Fusion Method for Intelligent Diagnosis of Bearing Faults

    byĀ Ruihao Xin, Xin Feng, Tiantian Wang, Fengbo Miao, Cuinan Yu

    The use of deep learning for fault diagnosis is already a common approach. However, integrating discriminative information of fault types and scales into deep learning models for rich multitask fault feature diagnosis still deserves attention. In this study, a deep multitask-based multiscale feature fusion network model (MEAT) is proposed to address the limitations and poor adaptability of traditional convolutional neural network models for complex jobs. The model performed multidimensional feature extraction through convolution at different scales to obtain different levels of fault information, used a hierarchical attention mechanism to weight the fusion of features to achieve an accuracy of 99.95% for the total task of fault six classification, and considered two subtasks in fault classification to discriminate fault size and fault type through multi-task mapping decomposition. Of these, the highest accuracy of fault size classification reached 100%. In addition, Precision, ReCall, and Sacore F1 all reached the index of 1, which achieved the accurate diagnosis of bearing faults.


  • Seven non-Differentially Expressed ā€˜Dark Biomarkers’ Show Transcriptional Dysregulation in Chronic Lymphocytic Leukemia

    byĀ Ruihao Xin, Xin Feng, Hang Zhang, Yueying Wang, Meiyu Duan, Tunyang Xie, Lin Dong, Qiong Yu, Lan Huang, Fengfeng Zhou

    Aim: Transcriptional regulation is actively involved in the onset and progression of various diseases. This study used the feature-engineering approach model-based quantitative transcription regula...


  • Open Access

    Multiview Feature Fusion Attention Convolutional Recurrent Neural Networks for EEG‐Based Emotion Recognition

    byĀ Ruihao Xin, Fengbo Miao, Ping Cong, Fan Zhang, Yongxian Xin, Xin Feng

    Emotion recognition is essential for computers to understand human emotions. Traditional EEG emotion recognition methods have significant limitations. To improve the accuracy of EEG emotion recognition, we propose a multiview feature fusion attention convolutional recurrent neural network (multi‐aCRNN) model. Multi‐aCRNN combines CNN, GRU, and attention mechanisms to fuse features from multiple perspectives deeply. Specifically, multiscale CNN can unite elements in the frequency and spatial domains through the convolution of different scales. The role of the attention mechanism is to weigh the frequency domain and spatial domain information of different periods to find more valuable temporal perspectives. Finally, the implicit feature representation is learned from the time domain through the bidirectional GRU to achieve the profound fusion of features from multiple perspectives in the time domain, frequency domain, and spatial domain. At the same time, for the noise problem, we use label smoothing to reduce the influence of label noise to achieve a better emotion recognition classification effect. Finally, the model is validated on the EEG data of 32 subjects on a public dataset (DEAP) by fivefold cross‐validation. Multi‐aCRNN achieves an average classification accuracy of 96.43% and 96.30% in arousal and valence classification tasks, respectively. In conclusion, multi‐aCRNN can better integrate EEG features from different angles and provide better classification results for emotion recognition.