IEEE/ACM Transactions on Computational Biology and Bioinformatics最新文献

AutoDock Vina and its derivatives have established themselves as a prevailing pipeline for virtual screening in contemporary drug discovery. Our Vina-GPU method leverages the parallel computing power of GPUs to accelerate AutoDock Vina, and Vina-GPU 2.0 further enhances the speed of AutoDock Vina and its derivatives. Given the prevalence of large virtual screens in modern drug discovery, the improvement of speed and accuracy in virtual screening has become a longstanding challenge. In this study, we propose Vina-GPU 2.1, aimed at enhancing the docking speed and precision of AutoDock Vina and its derivatives through the integration of novel algorithms to facilitate improved docking and virtual screening outcomes. Building upon the foundations laid by Vina-GPU 2.0, we introduce a novel algorithm, namely Reduced Iteration and Low Complexity BFGS (RILC-BFGS), designed to expedite the most time-consuming operation. Additionally, we implement grid cache optimization to further enhance the docking speed. Furthermore, we employ optimal strategies to individually optimize the structures of ligands, receptors, and binding pockets, thereby enhancing the docking precision. To assess the performance of Vina-GPU 2.1, we conduct extensive virtual screening experiments on three prominent targets, utilizing two fundamental compound libraries and seven docking tools. Our results demonstrate that Vina-GPU 2.1 achieves an average 4.97-fold acceleration in docking speed and an average 342% improvement in EF1% compared to Vina-GPU 2.0. The source code and tools for Vina-GPU 2.1 are freely available accompanied by comprehensive instructions and illustrative examples.

Protein-metal ion interactions play a central role in the onset of numerous diseases. When amino acid changes lead to missense mutations in metal-binding sites, the disrupted interaction with metal ions can compromise protein function, potentially causing severe human ailments. Identifying these disease-associated mutation sites within metal-binding regions is paramount for understanding protein function and fostering innovative drug development. While some computational methods aim to tackle this challenge, they often fall short in accuracy, commonly due to manual feature extraction and the absence of structural data. We introduce MetalPrognosis, an innovative, alignment-free solution that predicts disease-associated mutations within metal-binding sites of metalloproteins with heightened precision. Rather than relying on manual feature extraction, MetalPrognosis employs sliding window sequences as input, extracting deep semantic insights from pre-trained protein language models. These insights are then incorporated into a convolutional neural network, facilitating the derivation of intricate features. Comparative evaluations show MetalPrognosis outperforms leading methodologies like MCCNN and M-Ionic across various metalloprotein test sets. Furthermore, an ablation study reiterates the effectiveness of our model architecture. To facilitate public use, we have made the datasets, source codes, and trained models for MetalPrognosis online available at http://metalprognosis.unimelb-biotools.cloud.edu.au/.

Alignment-free analysis of sequences has revolutionized the high-throughput processing of sequencing data within numerous bioinformatics pipelines. Hashing k-mers represents a common function across various alignment-free applications, serving as a crucial tool for indexing, querying, and rapid similarity searching. More recently, spaced seeds, a specialized pattern that accommodates errors or mutations, have become a standard choice over traditional k-mers. Spaced seeds offer enhanced sensitivity in many applications when compared to k-mers. However, it's important to note that hashing spaced seeds significantly increases computational time. Furthermore, if multiple spaced seeds are employed, accuracy can be further improved, albeit at the expense of longer processing times. This paper addresses the challenge of efficiently hashing multiple spaced seeds. The proposed algorithms leverage the similarity of adjacent spaced seed hash values within an input sequence, allowing for the swift computation of subsequent hashes. Our experimental results, conducted across various tests, demonstrate a remarkable performance improvement over previously suggested algorithms, with potential speedups of up to 20 times. Additionally, we apply these efficient spaced seed hashing algorithms to a metagenomic application, specifically the classification of reads using Clark-S [Ounit and Lonardi, 2016]. Our findings reveal a substantial speedup, effectively mitigating the slowdown caused by the utilization of multiple spaced seeds.

Graph neural networks offer an effective avenue for predicting drug-target interactions. In this domain, researchers have found that constructing heterogeneous information networks based on metapaths using diverse biological datasets enhances prediction performance. However, the performance of such methods is closely tied to the selection of metapaths and the compatibility between metapath subgraphs and graph neural networks. Most existing approaches still rely on fixed strategies for selecting metapaths and often fail to fully exploit node information along the metapaths, limiting the improvement in model performance. This paper introduces a novel method for predicting drug-target interactions by optimizing metapaths in heterogeneous information networks. On one hand, the method formulates the metapath optimization problem as a Markov decision process, using the enhancement of downstream network performance as a reward signal. Through iterative training of a reinforcement learning agent, a high-quality set of metapaths is learned. On the other hand, to fully leverage node information along the metapaths, the paper constructs subgraphs based on nodes along the metapaths. Different depths of subgraphs are processed using different graph convolutional neural network. The proposed method is validated using standard heterogeneous biological benchmark datasets. Experimental results on standard datasets show significant advantages over traditional methods.

Cancer is a complex genomic mutation disease, and identifying cancer driver genes promotes the development of targeted drugs and personalized therapies. The current computational method takes less consideration of the relationship among features and the effect of noise in protein-protein interaction(PPI) data, resulting in a low recognition rate. In this paper, we propose a cancer driver genes identification method based on dynamic incentive model, DIM. This method firstly constructs a hypergraph to reduce the impact of false positive data in PPI. Then, the importance of genes in each hyperedge in hypergraph is considered from three perspectives, network and functional score(NFS) is proposed. By analyzing the relation among features, the dynamic incentive model is proposed to fuse NFS, the differential expression score of mRNA and the differential expression score of miRNA. DIM is compared with some classical methods on breast cancer, lung cancer, prostate cancer, and pan-cancer datasets. The results show that DIM has the best performance on statistical evaluation indicators, functional consistency and the partial area under the ROC curve, and has good cross-cancer capability.

Genome Rearrangement distance problems are used in Computational Biology to estimate the evolutionary distance between genomes. These problems consist of minimizing the number of rearrangement events necessary to transform one genome into another. Two commonly used rearrangement events are reversal and transposition. The first studied problems ignored nucleotides outside genes (called intergenic regions), or assumed that genomes have a single copy of each gene. Recent works made advancements in more general problems considering the number of nucleotides in intergenic regions, and replicated genes. Nevertheless, genomes tend to have wildly different quantities of nucleotides on their intergenic regions, which poses a problem when comparing these regions exactly. To overcome this limitation, our work considers some flexibility when matching intergenic regions that do not have the same number of nucleotides. We propose new problems seeking the minimum number of reversals, or reversals and transpositions, necessary to transform one genome into another, while considering flexible intergenic region information. We show approximations for these problems by exploring their relationship with the Signed Minimum Common Flexible Intergenic String Partition problem. We also present different heuristics for the partition problem, and conduct experimental tests on simulated genomes to assess the performance of our algorithms.

Accurate identification of antifreeze proteins (AFPs) is crucial in developing biomimetic synthetic anti-icing materials and low-temperature organ preservation materials. Although numerous machine learning-based methods have been proposed for AFPs prediction, the complex and diverse nature of AFPs limits the prediction performance of existing methods. In this study, we propose AFP-Deep, a new deep learning method to predict antifreeze proteins by integrating embedding from protein sequences with pre-trained protein language models and evolutionary contexts with hybrid feature extraction networks. The experimental results demonstrated that the main advantage of AFP-Deep is its utilization of pre-trained protein language models, which can extract discriminative global contextual features from protein sequences. Additionally, the hybrid deep neural networks designed for protein language models and evolutionary context feature extraction enhance the correlation between embeddings and antifreeze pattern. The performance evaluation results show that AFP-Deep achieves superior performance compared to state-of-the-art models on benchmark datasets, achieving an AUPRC of 0.724 and 0.924, respectively.

N⁷ -methylguanosine (m7G), one of the mainstream post-transcriptional RNA modifications, occupies an exceedingly significant place in medical treatments. However, classic approaches for identifying m7G sites are costly both in time and equipment. Meanwhile, the existing machine learning methods extract limited hidden information from RNA sequences, thus making it difficult to improve the accuracy. Therefore, we put forward to a deep learning network, called "GenoM7GNet," for m7G site identification. This model utilizes a Bidirectional Encoder Representation from Transformers (BERT) and is pretrained on nucleotide sequences data to capture hidden patterns from RNA sequences for m7G site prediction. Moreover, through detailed comparative experiments with various deep learning models, we discovered that the one-dimensional convolutional neural network (CNN) exhibits outstanding performance in sequence feature learning and classification. The proposed GenoM7GNet model achieved 0.953in accuracy, 0.932in sensitivity, 0.976in specificity, 0.907in Matthews Correlation Coefficient and 0.984in Area Under the receiver operating characteristic Curve on performance evaluation. Extensive experimental results further prove that our GenoM7GNet model markedly surpasses other state-of-the-art models in predicting m7G sites, exhibiting high computing performance.