Multimodal Emotion Recognition in Conversation (MERC) aims to infer the emotion of each utterance in a dialogue by integrating textual, acoustic, and visual cues. Existing graph-based approaches can model inter-utterance interactions. However, they often struggle to capture implicit contextual dependencies and to perform history-conditioned reasoning. As conversations become longer, implicitly constructed links may introduce redundancy and noise, which can be further amplified during message passing. Moreover, a discrepancy between training and inference is commonly observed: models are trained with ground-truth emotion histories as conditioning signals, while at test time they must rely on previously predicted histories. This exposure bias can cause distribution shift and lead to error accumulation. To mitigate these issues, we propose SIC-SEH (Sparse Implicit Connectivity Graphs with Scheduled Emotion History Sampling), a robustness-oriented framework that jointly improves graph structure and training strategy. Specifically, we build a sparse implicit connectivity graph to constrain the scale and quality of implicit links, allowing the model to focus on salient historical cues while suppressing noisy propagation. In addition, we adopt scheduled sampling over emotion histories, progressively increasing the proportion of predicted histories used during training to enhance stability at inference. Experiments on benchmark datasets such as IEMOCAP and MELD demonstrate consistent improvements.

Medical image segmentation plays a vital role in clinical diagnosis, yet it remains a challenging task due to the high cost of pixel-level annotations and the persistent difficulty in balancing long-range dependency modeling with computational efficiency. Although convolutional neural networks (CNNs) and vision transformers (ViTs) have significantly advanced the field, they are hindered by inherent limitations: CNNs suffer from restricted receptive fields, while ViTs impose substantial computational burdens, limiting their deployment in resource-constrained environments. To overcome these challenges, we propose TG-MUNet—a lightweight, semi-supervised segmentation framework that, for the first time, integrates text-guided cross-modal learning with Mamba, a state space model offering linear complexity in sequence modeling. Our architecture incorporates three novel components: Text-Guided Spatial Sequence Mamba Blocks (TG-SSMB), which employ fine-grained textual semantics to modulate spatial features via FiLM-based conditioning; Text-Guided Vision Mamba Blocks (TG-VMB), which leverage global text embeddings to gate high-level representations at the encoder–decoder bottleneck; and a Text-Guided Mamba Bridge (TG-MB), designed to fuse multi-scale convolutional and Mamba-based features across different depths, enabling rich semantic interaction and robust feature refinement. Extensive experiments on multiple medical image segmentation benchmarks under limited annotation settings demonstrate that TG-MUNet consistently outperforms state-of-the-art methods.

Spatial transcriptomics (ST) enables the joint profiling of gene expression and spatial localization, offering new insights into tissue microenvironments and biological processes. However, accurate spatial domain identification remains challenging due to the difficulty of effectively integrating multimodal data. To address this, we propose stDSGCL, a multi-view graph convolutional framework that models both spatial and transcriptomic information. stDSGCL constructs multiple spatial graphs from different distance metrics and embeds gene expression data into view-specific representations. These are refined via self-supervised contrastive learning and fused adaptively using an attention mechanism to enhance robustness and discriminative power. Experiments on 10x Visium datasets show that stDSGCL outperforms existing methods in clustering accuracy and spatial resolution, and generalizes well across platforms. The source code is available at: https://github.com/yumengg123/stDSGCL

Multimodal data, integrating complementary cues from speech and text, has demonstrated superior potential over unimodal approaches in speech emotion recognition (SER) by enriching feature representations and improving model robustness. While acoustic features capture paralinguistic emotions (e.g., pitch, prosody), textual transcripts provide lexical and contextual insights into a speaker's emotional state. Although unimodal methods using either speech or text can achieve reasonable performance, they often fail to address inherent ambiguities, such as sarcasm or masked emotions, where cross-modal interactions are critical. Existing multimodal SER frameworks frequently overlook inter-modal dynamics or rely on simplistic fusion strategies, limiting their ability to model nuanced emotion-related dependencies. To bridge these gaps, we propose a Multilayer Interaction Module with Contrastive Learning (MIMCL). Specifically, we first utilize the Data2Vec and RoBERTa to encode raw speech signals and their corresponding transcripts into high-dimensional feature spaces. We then design a multilayer interaction fusion model to align token-level representations between audio and text. To preserve information integrity, we integrate original features extracted by pre-trained encoders into the fusion process, mitigating information loss during modality integration. Finally, a label-based contrastive learning task is added to enforce the model by pulling same-label samples and separating different-label ones across modalities. Experimental results demonstrate that the proposed method achieves state-of-the-art performance on the IEMOCAP and MELD datasets.

As a high mortality disease, cancer seriously affects people's life and well-being. Reliance on pathologists to assess disease progression from pathological images is inaccurate and burdensome. Computer aided diagnosis (CAD) system can effectively assist diagnosis and make more credible decisions. However, a large number of labeled medical images that contribute to improve the accuracy of machine learning algorithm, especially for deep learning in CAD, are difficult to collect. Therefore, in this work, an improved few-shot learning method is proposed for medical image recognition. In addition, to make full use of the limited feature information in one or more samples, a feature fusion strategy is involved in our model. On the dataset of BreakHis and skin lesions, the experimental results show that our model achieved the classification accuracy of 91.22% and 71.20% respectively when only 10 labeled samples are given, which is superior to other state-of-the-art methods.

Protein-ligand binding can play an important role in many fields. It is of great importance to accurately predict the binding affinity between molecules by computational methods. Most computational binding affinity methods require molecular structures. However, there are still a large number of protein molecules with known amino acid sequences whose structures have not yet been solved. To address this issue, this paper proposes a sequence-based convolution and ligand graph network, called SGNet, to fuse the molecular graph information and the amino acid sequence information. This method integrates Conjoint Triad (CT) encoding of amino acid sequence and one-dimensional convolutional neural network module to extract protein molecules, develops graph attention network to extract molecular features of ligand, and then fuses the two feature sets to predict the binding affinity between molecules from the fully connected layer. As a result, SGNet achieves good prediction performance on both KIKD andIC50data sets, with prediction error RMSEs of 1.287 and 1.58, and correlation Pearson Rs of 0.687 and 0.592, respectively. Comparative experimental results under the same conditions showed that SGNet outperformed Kdeep and GraphDTA in predicting binding affinities between protein-ligand molecules.

The computational methods of protein-protein interaction sites prediction can effectively avoid the shortcomings of high cost and time in traditional experimental approaches. However, the serious class imbalance between interface and non-interface residues on the protein sequences limits the prediction performance of these methods. This work therefore proposed a new strategy, NearMiss-based under-sampling for unbalancing datasets and Random Forest classification (NM-RF), to predict protein interaction sites. Herein, the residues on protein sequences were represented by the PSSM-derived features, hydropathy index (HI) and relative solvent accessibility (RSA). In order to resolve the class imbalance problem, an under-sampling method based on NearMiss algorithm is adopted to remove some non-interface residues, and then the random forest algorithm is used to perform binary classification on the balanced feature datasets. Experiments show that the accuracy of NM-RF model reaches 87.6% and 84.3% on Dtestset72 and PDBtestset164 respectively, which demonstrate the effectiveness of the proposed NM-RF method in differentiating the interface or non-interface residues.

Functional near-infrared spectroscopy (fNIRS) is a promising neuroimaging technology. The fNIRS classification problem has always been the focus of the brain-computer interface (BCI). Inspired by the success of Transformer based on self-attention mechanism in the fields of natural language processing and computer vision, we propose an fNIRS classification network based on Transformer, named fNIRS-T. We explore the spatial-level and channel-level representation of fNIRS signals to improve data utilization and network representation capacity. Besides, a preprocessing module, which consists of one-dimensional average pooling and layer normalization, is designed to replace filtering and baseline correction of data preprocessing. It makes fNIRS-T an end-to-end network, called fNIRS-PreT. Compared with traditional machine learning classifiers, convolutional neural network (CNN), and long short-term memory (LSTM), the proposed models obtain the best accuracy on three open-access datasets. Specifically, in the most extensive ternary classification task (30 subjects) that includes three types of overt movements, fNIRS-T, CNN, and LSTM obtain 75.49%, 72.89%, and 61.94% on test sets, respectively. Compared to traditional classifiers, fNIRS-T is at least 27.41% higher than statistical features and 6.79% higher than well-designed features. In the individual subject experiment of the ternary classification task, fNIRS-T achieves an average subject accuracy of 78.22% and surpasses CNN and LSTM by a large margin of +4.75% and +11.33%. fNIRS-PreT using raw data also achieves competitive performance to fNIRS-T. Therefore, the proposed models improve the performance of fNIRS-based BCI significantly.

Biological targets are most commonly proteins such as enzymes, ion channels, and receptors. They are anything within a living organism to bind with some other entities (like an endogenous ligand or a drug), resulting in change in their behaviors or functions. Exploring potential drug-target interactions (DTIs) are crucial for drug discovery and effective drug development. Computational methods were widely applied in drug-target interactions, since experimental methods are extremely time-consuming and resource-intensive. In this paper, we proposed a novel deep learning-based prediction system, with a new negative instance generation, to identify DTIs. As a result, our method achieved an accuracy of 0.9800 on our created dataset. Another dataset derived from DrugBank was used to further assess the generalization of the model, which yielded a good performance with accuracy of 0.8814 and AUC value of 0.9527 on the dataset. The outcome of our experimental results indicated that the proposed method, involving the credible negative generation, can be employed to discriminate the interactions between drugs and targets. Website: http://www.dlearningapp.com/web/DrugCNN.htm.

Protein-protein interactions play essential roles in various biological progresses. Identifying protein interaction sites can facilitate researchers to understand life activities and therefore will be helpful for drug design. However, the number of experimental determined protein interaction sites is far less than that of protein sites in protein-protein interaction or protein complexes. Therefore, the negative and positive samples are usually imbalanced, which is common but bring result bias on the prediction of protein interaction sites by computational approaches. In this work, we presented three imbalance data processing strategies to reconstruct the original dataset, and then extracted protein features from the evolutionary conservation of amino acids to build a predictor for identification of protein interaction sites. On a dataset with 10,430 surface residues but only 2,299 interface residues, the imbalance dataset processing strategies can obviously reduce the prediction bias, and therefore improve the prediction performance of protein interaction sites. The experimental results show that our prediction models can achieve a better prediction performance, such as a prediction accuracy of 0.758, or a high F-measure of 0.737, which demonstrated the effectiveness of our method.

Pathogenicity-related studies are of great importance in understanding the pathogenesis of complex diseases and improving the level of clinical medicine. This work proposed a bioinformatics scheme to analyze cancer-related gene mutations, and try to figure out potential genes associated with diseases from the protein domain-domain interaction network. Herein, five measures of the principle of centrality lethality had been adopted to implement potential correlation analysis, and prioritize the significance of genes. This method was further applied to KEGG pathway analysis by taking the malignant melanoma as an example. The experimental results show that 25 domains can be found, and 18 of them have high potential to be pathogenically important related to malignant melanoma. Finally, a web-based tool, named Human Cancer Related Domain Interaction Network Analyzer, is developed for potential pathogenic genes prioritization for 26 types of human cancers, and the analysis results can be visualized and downloaded online.

In contrast to traditional dehazing methods, deep learning based single image dehazing (SID) algorithms have achieved better performances by creating a mapping function from haze to haze-free images. Usually, the images taken from the natural scenes have different haze levels, but deep SID algorithms only process the hazy images as one group. It makes the deep SID algorithms difficult to deal with the image set with some images having specific haze density. In this paper, a Discrete Haze Level Dehazing network (DHL-Dehaze), a very effective method to dehaze multiple different haze level images, is proposed. The proposed approach considers a single image dehazing problem as a multi-domain image-to-image translation, instead of grouping all hazy images into the same domain. DHL-Dehaze provides computational derivation to describe the role of different haze levels for image translation. To verify the proposed approach, we synthesize two largescale datasets with multiple haze level images based on the NYU-Depth and DIML/CVL datasets. The experiments show that DHL-Dehaze can obtain excellent quantitative and qualitative dehazing results, especially when the haze concentration is high.

The AKAZE algorithm is a typical image registration algorithm that has the advantage of high computational efficiency based on non‐linear diffusion. However, it is weaker than the scale‐invariant feature transformation (SIFT) algorithm in terms of robustness and stability. We propose a new and improved version of the AKAZE algorithm by using the SIFT descriptor based on sparse random projection (SRP). The proposed method not only retains the advantage of high efficiency of the AKAZE algorithm in feature detection but also has the stability of the SIFT descriptor. Moreover, the computational complexity due to the high dimension of the SIFT descriptor, which limits the speed of feature matching, is drastically reduced by the SRP strategy. Experiments on several benchmark image datasets demonstrate that the proposed algorithm can significantly improve the stability of the AKAZE algorithm, and the results suggest the better matching performance and robustness of the feature descriptor.

Research on quantitative structure-activity relationships (QSAR) provides an effective approach to determine new hits and promising lead compounds during drug discovery. In the past decades, various works have gained good performance for QSAR with the development of machine learning. The rise of deep learning, along with massive accessible chemical databases, made improvement on the QSAR performance. This article proposes a novel deep-learning-based method to implement QSAR prediction by the concatenation of end-to-end encoder-decoder model and convolutional neural network (CNN) architecture. The encoder-decoder model is mainly used to generate fixed-size latent features to represent chemical molecules; while these features are then input into CNN framework to train a robust and stable model and finally to predict active chemicals. Two models with different schemes are investigated to evaluate the validity of our proposed model on the same data sets. Experimental results showed that our proposed method outperforms other state-of-the-art methods in successful identification of chemical molecule whether it is active.

BACKGROUND: Accurate identification of potential interactions between drugs and protein targets is a critical step to accelerate drug discovery. Despite many relative experimental researches have been done in the past decades, detecting drug-target interactions (DTIs) remains to be extremely resource-intensive and time-consuming. Therefore, many computational approaches have been developed for predicting drug-target associations on a large scale. RESULTS: In this paper, we proposed an deep learning-based method to predict DTIs only using the information of drug structures and protein sequences. The final results showed that our method can achieve good performance with the accuracies up to 92.0%, 90.0%, 92.0% and 90.7% for the target families of enzymes, ion channels, GPCRs and nuclear receptors of our created dataset, respectively. Another dataset derived from DrugBank was used to further assess the generalization of the model, which yielded an accuracy of 0.9015 and an AUC value of 0.9557. CONCLUSION: It was elucidated that our model shows improved performance in comparison with other state-of-the-art computational methods on the common benchmark datasets. Experimental results demonstrated that our model successfully extracted more nuanced yet useful features, and therefore can be used as a practical tool to discover new drugs. AVAILABILITY: http://deeplearner.ahu.edu.cn/web/CnnDTI.htm.

BACKGROUND: In recent years, lncRNAs (long-non-coding RNAs) have been proved to be closely related to the occurrence and development of many serious diseases that are seriously harmful to human health. However, most of the lncRNA-disease associations have not been found yet due to high costs and time complexity of traditional bio-experiments. Hence, it is quite urgent and necessary to establish efficient and reasonable computational models to predict potential associations between lncRNAs and diseases. RESULTS: In this manuscript, a novel prediction model called TCSRWRLD is proposed to predict potential lncRNA-disease associations based on improved random walk with restart. In TCSRWRLD, a heterogeneous lncRNA-disease network is constructed first by combining the integrated similarity of lncRNAs and the integrated similarity of diseases. And then, for each lncRNA/disease node in the newly constructed heterogeneous lncRNA-disease network, it will establish a node set called TCS (Target Convergence Set) consisting of top 100 disease/lncRNA nodes with minimum average network distances to these disease/lncRNA nodes having known associations with itself. Finally, an improved random walk with restart is implemented on the heterogeneous lncRNA-disease network to infer potential lncRNA-disease associations. The major contribution of this manuscript lies in the introduction of the concept of TCS, based on which, the velocity of convergence of TCSRWRLD can be quicken effectively, since the walker can stop its random walk while the walking probability vectors obtained by it at the nodes in TCS instead of all nodes in the whole network have reached stable state. And Simulation results show that TCSRWRLD can achieve a reliable AUC of 0.8712 in the Leave-One-Out Cross Validation (LOOCV), which outperforms previous state-of-the-art results apparently. Moreover, case studies of lung cancer and leukemia demonstrate the satisfactory prediction performance of TCSRWRLD as well. CONCLUSIONS: Both comparative results and case studies have demonstrated that TCSRWRLD can achieve excellent performances in prediction of potential lncRNA-disease associations, which imply as well that TCSRWRLD may be a good addition to the research of bioinformatics in the future.

BACKGROUND: The recognition of protein interaction sites is of great significance in many biological processes, signaling pathways and drug designs. However, most sites on protein sequences cannot be defined as interface or non-interface sites because only a small part of protein interactions had been identified, which will cause the lack of prediction accuracy and generalization ability of predictors in protein interaction sites prediction. Therefore, it is necessary to effectively improve prediction performance of protein interaction sites using large amounts of unlabeled data together with small amounts of labeled data and background knowledge today. RESULTS: In this work, three semi-supervised support vector machine-based methods are proposed to improve the performance in the protein interaction sites prediction, in which the information of unlabeled protein sites can be involved. Herein, five features related with the evolutionary conservation of amino acids are extracted from HSSP database and Consurf Sever, i.e., residue spatial sequence spectrum, residue sequence information entropy and relative entropy, residue sequence conserved weight and residual Base evolution rate, to represent the residues within the protein sequence. Then three predictors are built for identifying the interface residues from protein surface using three types of semi-supervised support vector machine algorithms. CONCLUSION: The experimental results demonstrated that the semi-supervised approaches can effectively improve prediction performance of protein interaction sites when unlabeled information is involved into the predictors and one of them can achieve the best prediction performance, i.e., the accuracy of 70.7%, the sensitivity of 62.67% and the specificity of 78.72%, respectively. With comparison to the existing studies, the semi-supervised models show the improvement of the predication performance.

BACKGROUND: The occurrence of cotton pests and diseases has always been an important factor affecting the total cotton production. Cotton has a great dependence on environmental factors during its growth, especially climate change. In recent years, machine learning and especially deep learning methods have been widely used in many fields and have achieved good results. METHODS: First, this papaer used the common Aprioro algorithm to find the association rules between weather factors and the occurrence of cotton pests. Then, in this paper, the problem of predicting the occurrence of pests and diseases is formulated as time series prediction, and an LSTM-based method was developed to solve the problem. RESULTS: The association analysis reveals that moderate temperature, humid air, low wind spreed and rain fall in autumn and winter are more likely to occur cotton pests and diseases. The discovery was then used to predict the occurrence of pests and diseases. Experimental results showed that LSTM performs well on the prediction of occurrence of pests and diseases in cotton fields, and yields the Area Under the Curve (AUC) of 0.97. CONCLUSION: Suitable temperature, humidity, low rainfall, low wind speed, suitable sunshine time and low evaporation are more likely to cause cotton pests and diseases. Based on these associations as well as historical weather and pest records, LSTM network is a good predictor for future pest and disease occurrences. Moreover, compared to the traditional machine learning models (i.e., SVM and Random Forest), the LSTM network performs the best.

BACKGROUND: Protein-protein interactions (PPIs) play important roles in biological functions. Studies of the effects of mutants on protein interactions can provide further understanding of PPIs. Currently, many databases collect experimental mutants to assess protein interactions, but most of these databases are old and have not been updated for several years. RESULTS: To address this issue, we manually curated a kinetic and thermodynamic database of mutant protein interactions (dbMPIKT) that is freely accessible at our website. This database contains 5291 mutants in protein interactions collected from previous databases and the literature published within the last three years. Furthermore, some data analysis, such as mutation number, mutation type, protein pair source and network map construction, can be performed online. CONCLUSION: Our work can promote the study on PPIs, and novel information can be mined from the new database. Our database is available in http://DeepLearner.ahu.edu.cn/web/dbMPIKT/ for use by all, including both academics and non-academics.

BACKGROUND: Proteins have the fundamental ability to selectively bind to other molecules and perform specific functions through such interactions, such as protein-ligand binding. Accurate prediction of protein residues that physically bind to ligands is important for drug design and protein docking studies. Most of the successful protein-ligand binding predictions were based on known structures. However, structural information is not largely available in practice due to the huge gap between the number of known protein sequences and that of experimentally solved structures. RESULTS: This paper proposes a dynamic ensemble approach to identify protein-ligand binding residues by using sequence information only. To avoid problems resulting from highly imbalanced samples between the ligand-binding sites and non ligand-binding sites, we constructed several balanced data sets and we trained a random forest classifier for each of them. We dynamically selected a subset of classifiers according to the similarity between the target protein and the proteins in the training data set. The combination of the predictions of the classifier subset to each query protein target yielded the final predictions. The ensemble of these classifiers formed a sequence-based predictor to identify protein-ligand binding sites. CONCLUSIONS: Experimental results on two Critical Assessment of protein Structure Prediction datasets and the ccPDB dataset demonstrated that of our proposed method compared favorably with the state-of-the-art. AVAILABILITY: http://www2.ahu.edu.cn/pchen/web/LigandDSES.htm.

Protein interactions play vital roles in biological processes. The study for protein interface will allow people to elucidate the mechanism of protein interaction. However, a large portion of protein interface data is incorrectly collected currently. In this paper, a dataset reconstruction strategy using manifold learning method has been proposed for dealing with the noises in the interaction interface data whose definition is based on the residue distances among the different chains within protein complexes. Three support vector machine-based predictors are constructed using different protein features to identify the functional sites involved in the formation of protein interface. The experimental results achieved in this work demonstrate that our strategy can remove noises, and therefore improve the ability for identification of protein interfaces with 77.8% accuracy.

BACKGROUND: Ion mobility-mass spectrometry (IMMS), an analytical technique which combines the features of ion mobility spectrometry (IMS) and mass spectrometry (MS), can rapidly separates ions on a millisecond time-scale. IMMS becomes a powerful tool to analyzing complex mixtures, especially for the analysis of peptides in proteomics. The high-throughput nature of this technique provides a challenge for the identification of peptides in complex biological samples. As an important parameter, peptide drift time can be used for enhancing downstream data analysis in IMMS-based proteomics. RESULTS: In this paper, a model is presented based on least square support vectors regression (LS-SVR) method to predict peptide ion drift time in IMMS from the sequence-based features of peptide. Four descriptors were extracted from peptide sequence to represent peptide ions by a 34-component vector. The parameters of LS-SVR were selected by a grid searching strategy, and a 10-fold cross-validation approach was employed for the model training and testing. Our proposed method was tested on three datasets with different charge states. The high prediction performance achieve demonstrate the effectiveness and efficiency of the prediction model. CONCLUSIONS: Our proposed LS-SVR model can predict peptide drift time from sequence information in relative high prediction accuracy by a test on a dataset of 595 peptides. This work can enhance the confidence of protein identification by combining with current protein searching techniques.

BACKGROUND: Protein-protein interactions (PPIs) play crucial roles in the execution of various cellular processes and form the basis of biological mechanisms. Although large amount of PPIs data for different species has been generated by high-throughput experimental techniques, current PPI pairs obtained with experimental methods cover only a fraction of the complete PPI networks, and further, the experimental methods for identifying PPIs are both time-consuming and expensive. Hence, it is urgent and challenging to develop automated computational methods to efficiently and accurately predict PPIs. RESULTS: We present here a novel hierarchical PCA-EELM (principal component analysis-ensemble extreme learning machine) model to predict protein-protein interactions only using the information of protein sequences. In the proposed method, 11188 protein pairs retrieved from the DIP database were encoded into feature vectors by using four kinds of protein sequences information. Focusing on dimension reduction, an effective feature extraction method PCA was then employed to construct the most discriminative new feature set. Finally, multiple extreme learning machines were trained and then aggregated into a consensus classifier by majority voting. The ensembling of extreme learning machine removes the dependence of results on initial random weights and improves the prediction performance. CONCLUSIONS: When performed on the PPI data of Saccharomyces cerevisiae, the proposed method achieved 87.00% prediction accuracy with 86.15% sensitivity at the precision of 87.59%. Extensive experiments are performed to compare our method with state-of-the-art techniques Support Vector Machine (SVM). Experimental results demonstrate that proposed PCA-EELM outperforms the SVM method by 5-fold cross-validation. Besides, PCA-EELM performs faster than PCA-SVM based method. Consequently, the proposed approach can be considered as a new promising and powerful tools for predicting PPI with excellent performance and less time.

MOTIVATION: Comprehensive two-dimensional gas chromatography mass spectrometry (GC × GC-MS) brings much increased separation capacity, chemical selectivity and sensitivity for metabolomics and provides more accurate information about metabolite retention times and mass spectra. However, there is always a shift of retention times in the two columns that makes it difficult to compare metabolic profiles obtained from multiple samples exposed to different experimental conditions. RESULTS: The existing peak alignment algorithms for GC × GC-MS data use the peak distance and the spectra similarity sequentially and require predefined either distance-based window and/or spectral similarity-based window. To overcome the limitations of the current alignment methods, we developed an optimal peak alignment using a novel mixture similarity by employing the peak distance and the spectral similarity measures simultaneously without any variation windows. In addition, we examined the effect of the four different distance measures such as Euclidean, Maximum, Manhattan and Canberra distances on the peak alignment. The performance of our proposed peak alignment algorithm was compared with the existing alignment methods on the two sets of GC × GC-MS data. Our analysis showed that Canberra distance performed better than other distances and the proposed mixture similarity peak alignment algorithm prevailed against all literature reported methods. AVAILABILITY: The data and software mSPA are available at http://stage.louisville.edu/faculty/x0zhan17/software/software-development.

In current proteomics research, a big challenge is to differentiate the correlative proteins for a given biological function from all existing proteins, and if it does, how strong is the relationship between the proteins and function. Statistical significance testing can be used to address this question. However, every traditional statistical test method may suffer from the inability to identify important differentially expressed proteins if the biological samples do not completely meet the assumptions of each test method [ 1 ]. To detect the regulated proteins for differential proteomics, we analyze multiple significance test methods and discover some significance proteins. We use the four statistical methods, i.e., Kolmogorov-Smirnov test (KS-test), Baumgartner-Weib-Schindler test (BWS-test), T-test, Brunner-Munzel test (BM-test) to measure the difference of the expression level of individual protein under two experimental conditions, respectively. The results had been successfully used for the discovery of protein biomarkers in breast cancer.

BACKGROUND: There is an increasing usage of ion mobility-mass spectrometry (IMMS) in proteomics. IMMS combines the features of ion mobility spectrometry (IMS) and mass spectrometry (MS). It separates and detects peptide ions on a millisecond time-scale. IMS separates peptide ions based on drift time that is determined by the collision cross-section of each peptide ion in a given experiment condition. A peptide ion's collision cross-section is related to the ion size and shape resulted from the peptide amino acid sequence and their modifications. This inherent relation between the drift time of peptide ion and peptide sequence indicates that the drift time of peptide ions can be used to infer peptide sequence and therefore, for peptide identification. RESULTS: This paper describes an artificial neural networks (ANNs) regression model for the prediction of peptide ion drift time in IMMS. Each peptide in this work was represented using three descriptors (i.e., molecular weight, sequence length and a two-dimensional sequence index). An ANN predictor consisting of four input nodes, three hidden nodes and one output node was constructed for peptide ion drift time prediction. For the model training and testing, a 10-fold cross-validation strategy was employed for three datasets each containing different charge states. Dataset one contains 212 singly-charged peptide ions, dataset two has 306 doubly-charged peptide ions, and dataset three has 77 triply-charged peptide ions. Our proposed method achieved 94.4%, 93.6% and 74.2% prediction accuracy for singly-, doubly- and triply-charged peptide ions, respectively. CONCLUSIONS: An ANN-based method has been developed for predicting the drift time of peptide ions in IMMS. The results achieved here demonstrate the effectiveness and efficiency of the prediction model. This work can enhance the confidence of protein identification by combining with current database search approaches for protein identification.

Theoretic study in this paper shows that we can obtain exact long-range contacts by adopting one classifier if the centers of sequence profiles of residue pairs for long-range contacts and non-long-range contacts are known. The adopted classifier, referred to as multiple conditional probability mass function classifier (MCPMFC), can find an optimized transformation of the variables for each of the classes and therefore resulting in K separate classifiers. As a result, about 44.48% long-range contacts are around at the sequence profile (SP) centre for long-range contacts and about 20.9% long-range contacts are correctly predicted when considering the top L/5 (L is the protein sequence length) predicted contacts and the residue pair with 24 apart. The highest cluster result gives us a clue that SP center should be a sound pathway to investigate contact map in protein structures.

Many computational methods have been proposed for inference of protein-protein interactions as protein-protein interaction plays an important role in many cellular processes. One of methods is to infer protein-protein interactions based on domain-domain interactions, and the preliminary results have represented their feasibility. In this paper, we use the neural networks for predicting the strengths of protein interaction. This method is capable of exploring all possible interactions between domains and make predictions based on all the domains. Compared to expectation-maximization method and association method, the experimental results show that the proposed schemes can infer strengths of protein-protein interactions with better performances.

This paper analyzes the long-range interactions, which plays a fundamental and important role in many biologic fields, between residues in protein using principal component analysis (PCA). Firstly, one angular coordinate system of long-range interaction regions is constructed conveniently. Afterwards, a matrix of the angular values of residues can be analyzed by principal component analysis technique. Projecting the angular matrix onto its eigenvectors, it can be found that the projection is to satisfy Boltzmann distribution. By analyzing the thermodynamic environment of the interaction region and scaling the interaction regions, it can be concluded that the distribution of long-range interactions may also be obtained and as a result applied in prediction of contact map.

Identifying protein-protein interaction sites is crucial for understanding of the principles of biological systems and processes, as well as mutant design. This paper describes a novel method that can predict protein interaction sites in heterocomplexes using information of evolutionary conservation and spatial sequence profile. A predictor was generated to distinguish the interface residues from protein surface region by radial basis neural networks, which is trained by expectation maximization algorithm. Based on a non-redundant data set of heterodimers consisting of 75 protein chains, the efficiency and the effectiveness of our proposed approach can be validated by a better performance such as the accuracy of 0.60, the sensitivity of 58.3% and the specificity of 59.9%.

This paper presents a novel method to solve the protein's three-dimensional structure prediction problem. It is a machine learning approach by integrating probabilistic neural network (PNN) with conformational energy function (CEF) based on chemico-physical knowledge of amino acids. In this method, firstly, the principal components are extracted from selected protein structures with lower sequence identity, and an initial matrix of contact map is constructed by K-L expansion. Secondly, PNN is used for predicting the long-range interaction of amino acids in protein. In particular, this method uses the CEF and chemico-physical characteristics of amino acids to run the PNN predictor. Consequently, it was found that our proposed method is better than existing methods, such as the hybrid method of HMMSTR and the correlated mutation analysis method. As a result, this method can accurately predict 31% of contacts at a distance cutoff of 8/spl Aring/ for proteins whose sequence length is up to 200.

This paper proposes a new method that can predict the interactions between proteins intermediated by the protein-domain relations. We utilize the lazy expectation maximization (LEM) to compute an improved maximization likelihood estimation (MLE) model. The protein-domain relationships are extruded from Flam database and the combined data set of Uetz and Ito are used as the source of protein-protein interactions. Finally, the efficiency and the effectiveness of our proposed approach can be validated by a better performance such as the sensitivity of 80.1%, the specificity of 43.5%, and the lesser computational cost.