Malsite-Deep: Prediction of protein malonylation sites through deep learning and multi-information fusion based on NearMiss-2 strategy

A review of machine learning methods for imbalanced data challenges in chemistry

Imbalanced data, where certain classes are significantly underrepresented in a dataset, is a widespread machine learning (ML) challenge across various fields of chemistry, yet it remains inadequately addressed. This data imbalance can lead to biased ML or deep learning (DL) models, which fail to accurately predict the underrepresented classes, thus limiting the robustness and applicability of these models. With the rapid advancement of ML and DL algorithms, several promising solutions to this issue have emerged, prompting the need for a comprehensive review of current methodologies. In this review, we examine the prominent ML approaches used to tackle the imbalanced data challenge in different areas of chemistry, including resampling techniques, data augmentation techniques, algorithmic approaches, and feature engineering strategies. Each of these methods is evaluated in the context of its application across various aspects of chemistry, such as drug discovery, materials science, cheminformatics, and catalysis. We also explore future directions for overcoming the imbalanced data challenge and emphasize data augmentation via physical models, large language models (LLMs), and advanced mathematics. The benefit of balanced data in new material design and production and the persistent challenges are discussed. Overall, this review aims to elucidate the prevalent ML techniques applied to mitigate the impacts of imbalanced data within the field of chemistry and offer insights into future directions for research and application.

SIPSC-Kac: Integrating swarm intelligence and protein spatial characteristics for enhanced lysine acetylation site identification

Elucidation of post-translational modifications (PTMs), such as lysine acetylation (Kac), is crucial for understanding protein function and regulation. Although traditional experimental methods for identifying Kac sites are accurate, they are time-consuming and costly, leading to incomplete acetylome mapping. Computational approaches, particularly those incorporating machine learning, offer a rapid alternative, but face challenges owing to dataset imbalance, limited feature space, and the need for more effective feature-selection algorithms. To address these challenges, we present SIPSC-Kac, a novel computational method that integrates swarm intelligence algorithms with protein spatial characteristics to enhance the prediction of Kac sites. We used the AlphaFold system for spatial feature extraction and employed swarm intelligence for optimal feature selection, outperforming existing methods in terms of accuracy and computational efficiency. SIPSC-Kac demonstrated superior performance across multiple bacterial species, which was validated by its high performance in evaluation metrics. Our web server provides researchers with a user-friendly platform for Kac site prediction, thereby contributing to the advancement of bioinformatics and proteomic research. The SIPSC-Kac code and web server are accessible, thereby promoting broad applications in the scientific community.

Res-GCN: Identification of protein phosphorylation sites using graph convolutional network and residual network

An essential post-translational modification, phosphorylation is intimately related with a wide range of biological activities. The advancement of effective computational methods for correctly recognizing phosphorylation sites is important for in-depth understanding of various physiological phenomena. However, the traditional method of identifying phosphorylation sites experimentally is time-consuming and laborious, which makes it difficult to meet the processing demands of today's big data. This research proposes the use of a novel model, Res-GCN, to recognize the phosphorylation sites of SARS-CoV-2. Firstly, eight feature extraction strategies are utilized to digitize the protein sequence from multiple viewpoints, including amino acid property encodings (AAindex), pseudo-amino acid composition (PseAAC), adapted normal distribution bi-profile Bayes (ANBPB), dipeptide composition (DC), binary encoding (BE), enhanced amino acid composition (EAAC), Word2Vec, and BLOSUM62 matrices. Secondly, elastic net is utilized to eliminate redundant data in the fused matrix. Finally, a combination of graph convolutional network (GCN) and residual network (ResNet) is used to classify the phosphorylated sites and output predictions using a fully connected layer (FC). The performance of Res-GCN is tested by 5-fold cross-validation and independent testing, and excellent results are obtained on S/T and Y datasets. This demonstrates that the Res-GCN model exhibits exceptional predictive performance and generalizability.

ML-FGAT: Identification of multi-label protein subcellular localization by interpretable graph attention networks and feature-generative adversarial networks

The prediction of multi-label protein subcellular localization (SCL) is a pivotal area in bioinformatics research. Recent advancements in protein structure research have facilitated the application of graph neural networks. This paper introduces a novel approach termed ML-FGAT. The approach begins by extracting node information of proteins from sequence data, physical-chemical properties, evolutionary insights, and structural details. Subsequently, various evolutionary techniques are integrated to consolidate multi-view information. A linear discriminant analysis framework, grounded on entropy weight, is then employed to reduce the dimensionality of the merged features. To enhance the robustness of the model, the training dataset is augmented using feature-generative adversarial networks. For the primary prediction step, graph attention networks are employed to determine multi-label protein SCL, leveraging both node and neighboring information. The interpretability is enhanced by analyzing the attention weight parameters. The training is based on the Gram-positive bacteria dataset, while validation employs newly constructed datasets: human, virus, Gram-negative bacteria, plant, and SARS-CoV-2. Following a leave-one-out cross-validation procedure, ML-FGAT demonstrates noteworthy superiority in this domain.

Analysis and review of techniques and tools based on machine learning and deep learning for prediction of lysine malonylation sites in protein sequences

The post-translational modifications occur as crucial molecular regulatory mechanisms utilized to regulate diverse cellular processes. Malonylation of proteins, a reversible post-translational modification of lysine/k residues, is linked to a variety of biological functions, such as cellular regulation and pathogenesis. This modification plays a crucial role in metabolic pathways, mitochondrial functions, fatty acid oxidation and other life processes. However, accurately identifying malonylation sites is crucial to understand the molecular mechanism of malonylation, and the experimental identification can be a challenging and costly task. Recently, approaches based on machine learning (ML) have been suggested to address this issue. It has been demonstrated that these procedures improve accuracy while lowering costs and time constraints. However, these approaches also have specific shortcomings, including inappropriate feature extraction out of protein sequences, high-dimensional features and inefficient underlying classifiers. As a result, there is an urgent need for effective predictors and calculation methods. In this study, we provide a comprehensive analysis and review of existing prediction models, tools and benchmark datasets for predicting malonylation sites in protein sequences followed by a comparison study. The review consists of the specifications of benchmark datasets, explanation of features and encoding methods, descriptions of the predictions approaches and their embedding ML or deep learning models and the description and comparison of the existing tools in this domain. To evaluate and compare the prediction capability of the tools, a new bunch of data has been extracted based on the most updated database and the tools have been assessed based on the extracted data. Finally, a hybrid architecture consisting of several classifiers including classical ML models and a deep learning model has been proposed to ensemble the prediction results. This approach demonstrates the better performance in comparison with all prediction tools included in this study (the source codes of the models presented in this manuscript are available in https://github.com/Malonylation). Database URL: https://github.com/A-Golshan/Malonylation.

BiGRUD-SA: Protein S-sulfenylation sites prediction based on BiGRU and self-attention

S-sulfenylation is a vital post-translational modification (PTM) of proteins, which is an intermediate in other redox reactions and has implications for signal transduction and protein function regulation. However, there are many restrictions on the experimental identification of S-sulfenylation sites. Therefore, predicting S-sulfoylation sites by computational methods is fundamental to studying protein function and related biological mechanisms. In this paper, we propose a method named BiGRUD-SA based on bi-directional gated recurrent unit (BiGRU) and self-attention mechanism to predict protein S-sulfenylation sites. We first use AAC, BLOSUM62, AAindex, EAAC and GAAC to extract features, and do feature fusion to obtain original feature space. Next, we use SMOTE-Tomek method to handle data imbalance. Then, we input the processed data to the BiGRU and use self-attention mechanism to do further feature extraction. Finally, we input the data obtained to the deep neural networks (DNN) to identify S-sulfenylation sites. The accuracies of training set and independent test set are 96.66% and 95.91% respectively, which indicates that our method is conducive to identifying S-sulfenylation sites. Furthermore, we use a data set of S-sulfenylation sites in Arabidopsis thaliana to effectively verify the generalization ability of BiGRUD-SA method, and obtain better prediction results.

DBGRU-SE: predicting drug-drug interactions based on double BiGRU and squeeze-and-excitation attention mechanism

The prediction of drug-drug interactions (DDIs) is essential for the development and repositioning of new drugs. Meanwhile, they play a vital role in the fields of biopharmaceuticals, disease diagnosis and pharmacological treatment. This article proposes a new method called DBGRU-SE for predicting DDIs. Firstly, FP3 fingerprints, MACCS fingerprints, Pubchem fingerprints and 1D and 2D molecular descriptors are used to extract the feature information of the drugs. Secondly, Group Lasso is used to remove redundant features. Then, SMOTE-ENN is applied to balance the data to obtain the best feature vectors. Finally, the best feature vectors are fed into the classifier combining BiGRU and squeeze-and-excitation (SE) attention mechanisms to predict DDIs. After applying five-fold cross-validation, The ACC values of DBGRU-SE model on the two datasets are 97.51 and 94.98%, and the AUC are 99.60 and 98.85%, respectively. The results showed that DBGRU-SE had good predictive performance for drug-drug interactions.

DE-MHAIPs: Identification of SARS-CoV-2 phosphorylation sites based on differential evolution multi-feature learning and multi-head attention mechanism

The rapid spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) around the world affects the normal lives of people all over the world. The computational methods can be used to accurately identify SARS-CoV-2 phosphorylation sites. In this paper, a new prediction model of SARS-CoV-2 phosphorylation sites, called DE-MHAIPs, is proposed. First, we use six feature extraction methods to extract protein sequence information from different perspectives. For the first time, we use a differential evolution (DE) algorithm to learn individual feature weights and fuse multi-information in a weighted combination. Next, Group LASSO is used to select a subset of good features. Then, the important protein information is given higher weight through multi-head attention. After that, the processed data is fed into long short-term memory network (LSTM) to further enhance model's ability to learn features. Finally, the data from LSTM are input into fully connected neural network (FCN) to predict SARS-CoV-2 phosphorylation sites. The AUC values of the S/T and Y datasets under 5-fold cross-validation reach 91.98% and 98.32%, respectively. The AUC values of the two datasets on the independent test set reach 91.72% and 97.78%, respectively. The experimental results show that the DE-MHAIPs method exhibits excellent predictive ability compared with other methods.

Cooperation of local features and global representations by a dual-branch network for transcription factor binding sites prediction

Interactions between DNA and transcription factors (TFs) play an essential role in understanding transcriptional regulation mechanisms and gene expression. Due to the large accumulation of training data and low expense, deep learning methods have shown huge potential in determining the specificity of TFs-DNA interactions. Convolutional network-based and self-attention network-based methods have been proposed for transcription factor binding sites (TFBSs) prediction. Convolutional operations are efficient to extract local features but easy to ignore global information, while self-attention mechanisms are expert in capturing long-distance dependencies but difficult to pay attention to local feature details. To discover comprehensive features for a given sequence as far as possible, we propose a Dual-branch model combining Self-Attention and Convolution, dubbed as DSAC, which fuses local features and global representations in an interactive way. In terms of features, convolution and self-attention contribute to feature extraction collaboratively, enhancing the representation learning. In terms of structure, a lightweight but efficient architecture of network is designed for the prediction, in particular, the dual-branch structure makes the convolution and the self-attention mechanism can be fully utilized to improve the predictive ability of our model. The experiment results on 165 ChIP-seq datasets show that DSAC obviously outperforms other five deep learning based methods and demonstrate that our model can effectively predict TFBSs based on sequence feature alone. The source code of DSAC is available at https://github.com/YuBinLab-QUST/DSAC/.

A hybrid feature extraction scheme for efficient malonylation site prediction

Lysine malonylation is one of the most important post-translational modifications (PTMs). It affects the functionality of cells. Malonylation site prediction in proteins can unfold the mechanisms of cellular functionalities. Experimental methods are one of the due prediction approaches. But they are typically costly and time-consuming to implement. Recently, methods based on machine-learning solutions have been proposed to tackle this problem. Such practices have been shown to reduce costs and time complexities and increase accuracy. However, these approaches also have specific shortcomings, including inappropriate feature extraction out of protein sequences, high-dimensional features, and inefficient underlying classifiers. A machine learning-based method is proposed in this paper to cope with these problems. In the proposed approach, seven different features are extracted. Then, the extracted features are combined, ranked based on the Fisher's score (F-score), and the most efficient ones are selected. Afterward, malonylation sites are predicted using various classifiers. Simulation results show that the proposed method has acceptable performance compared with some state-of-the-art approaches. In addition, the XGBOOST classifier, founded on extracted features such as TFCRF, has a higher prediction rate than the other methods. The codes are publicly available at: https://github.com/jimy2020/Malonylation-site-prediction.