Pub Date : 2024-09-13DOI: 10.1109/TCBB.2024.3433523
Fernando H. C. Dias;Alexandru I. Tomescu
Minimum flow decomposition (MFD) is a common problem across various fields of Computer Science, where a flow is decomposed into a minimum set of weighted paths. However, in Bioinformatics applications, such as RNA transcript or quasi-species assembly, the flow is erroneous since it is obtained from noisy read coverages. Typical generalizations of the MFD problem to handle errors are based on least-squares formulations or modelling the erroneous flow values as ranges. All of these are thus focused on error handling at the level of individual edges. In this paper, we interpret the flow decomposition problem as a robust optimization problem and lift error-handling from individual edges to solution paths . As such, we introduce a new minimum path-error flow decomposition problem, for which we give an Integer Linear Programming formulation. Our experimental results reveal that our formulation can account for errors significantly better, by lowering the inaccuracy rate by 30–50% compared to previous error-handling formulations, with computational requirements that remain practical.
{"title":"Accurate Flow Decomposition via Robust Integer Linear Programming","authors":"Fernando H. C. Dias;Alexandru I. Tomescu","doi":"10.1109/TCBB.2024.3433523","DOIUrl":"10.1109/TCBB.2024.3433523","url":null,"abstract":"Minimum flow decomposition (MFD) is a common problem across various fields of Computer Science, where a flow is decomposed into a minimum set of weighted paths. However, in Bioinformatics applications, such as RNA transcript or quasi-species assembly, the flow is erroneous since it is obtained from noisy read coverages. Typical generalizations of the MFD problem to handle errors are based on least-squares formulations or modelling the erroneous flow values as ranges. All of these are thus focused on error handling at the level of individual edges. In this paper, we interpret the flow decomposition problem as a robust optimization problem and lift error-handling from individual edges to \u0000<italic>solution paths</i>\u0000. As such, we introduce a new \u0000<italic>minimum path-error flow decomposition</i>\u0000 problem, for which we give an Integer Linear Programming formulation. Our experimental results reveal that our formulation can account for errors significantly better, by lowering the inaccuracy rate by 30–50% compared to previous error-handling formulations, with computational requirements that remain practical.","PeriodicalId":13344,"journal":{"name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","volume":"21 6","pages":"1955-1964"},"PeriodicalIF":3.6,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142251664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-12DOI: 10.1109/TCBB.2024.3459960
Juan Wang;Tian-Jing Qiao;Chun-Hou Zheng;Jin-Xing Liu;Jun-Liang Shang
The advent of single-cell RNA sequencing (scRNA-seq) technology offers the opportunity to conduct biological research at the cellular level. Single-cell type identification based on unsupervised clustering is one of the fundamental tasks of scRNA-seq data analysis. Although many single-cell clustering methods have been developed recently, few can fully exploit the deep potential relationships between cells, resulting in suboptimal clustering. In this paper, we propose scGAMF, a graph autoencoder-based multi-level kernel subspace fusion framework for scRNA-seq data analysis. Based on multiple top feature sets, scGAMF unifies deep feature embedding and kernel space analysis into a single framework to learn an accurate clustering affinity matrix. First, we construct multiple top feature sets to avoid the high variability caused by single feature set learning. Second, scGAMF uses a graph autoencoder (GAEs) to extract deep information embedded in the data, and learn embeddings including gene expression patterns and cell-cell relationships. Third, to fully explore the deep potential relationships between cells, we design a multi-level kernel space fusion strategy. This strategy uses a kernel expression model with adaptive similarity preservation to learn a self-expression matrix shared by all embedding spaces of a given feature set, and a consensus affinity matrix across multiple top feature sets. Finally, the consensus affinity matrix is used for spectral clustering, visualization, and identification of gene markers. Extensive validation on real datasets shows that scGAMF achieves higher clustering accuracy than many popular single-cell analysis methods.
{"title":"A New Graph Autoencoder-Based Multi-Level Kernel Subspace Fusion Framework for Single-Cell Type Identification","authors":"Juan Wang;Tian-Jing Qiao;Chun-Hou Zheng;Jin-Xing Liu;Jun-Liang Shang","doi":"10.1109/TCBB.2024.3459960","DOIUrl":"10.1109/TCBB.2024.3459960","url":null,"abstract":"The advent of single-cell RNA sequencing (scRNA-seq) technology offers the opportunity to conduct biological research at the cellular level. Single-cell type identification based on unsupervised clustering is one of the fundamental tasks of scRNA-seq data analysis. Although many single-cell clustering methods have been developed recently, few can fully exploit the deep potential relationships between cells, resulting in suboptimal clustering. In this paper, we propose scGAMF, a graph autoencoder-based multi-level kernel subspace fusion framework for scRNA-seq data analysis. Based on multiple top feature sets, scGAMF unifies deep feature embedding and kernel space analysis into a single framework to learn an accurate clustering affinity matrix. First, we construct multiple top feature sets to avoid the high variability caused by single feature set learning. Second, scGAMF uses a graph autoencoder (GAEs) to extract deep information embedded in the data, and learn embeddings including gene expression patterns and cell-cell relationships. Third, to fully explore the deep potential relationships between cells, we design a multi-level kernel space fusion strategy. This strategy uses a kernel expression model with adaptive similarity preservation to learn a self-expression matrix shared by all embedding spaces of a given feature set, and a consensus affinity matrix across multiple top feature sets. Finally, the consensus affinity matrix is used for spectral clustering, visualization, and identification of gene markers. Extensive validation on real datasets shows that scGAMF achieves higher clustering accuracy than many popular single-cell analysis methods.","PeriodicalId":13344,"journal":{"name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","volume":"21 6","pages":"2292-2303"},"PeriodicalIF":3.6,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142182850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rapid advances in single-cell RNA sequencing (scRNA-seq) have made it possible to characterize cell states at a high resolution view for large scale library. scRNA-seq data contains a great deal of biological information, which can be mainly used to discover cell subtypes and track cell development. However, traditional methods face many challenges in addressing scRNA-seq data with high dimensions and high sparsity. For better analysis of scRNA-seq data, we propose a new framework called MSVGAE based on variational graph auto-encoder and graph attention networks. Specifically, we introduce multiple encoders to learn features at different scales and control for uninformative features. Moreover, different noises are added to encoders to promote the propagation of graph structural information and distribution uncertainty. Therefore, some complex posterior distributions can be captured by our model. MSVGAE maps scRNA-seq data with high dimensions and high noise into the low-dimensional latent space, which is beneficial for downstream tasks. In particular, MSVGAE can handle extremely sparse data. Before the experiment, we create 24 simulated datasets to simulate various biological scenarios and collect 8 real-world datasets. The experimental results of clustering, visualization and marker genes analysis indicate that MSVGAE model has excellent accuracy and robustness in analyzing scRNA-seq data.
{"title":"Using Multi-Encoder Semi-Implicit Graph Variational Autoencoder to Analyze Single-Cell RNA Sequencing Data","authors":"Shengwen Tian;Cunmei Ji;Jiancheng Ni;Yutian Wang;Chunhou Zheng","doi":"10.1109/TCBB.2024.3458170","DOIUrl":"10.1109/TCBB.2024.3458170","url":null,"abstract":"Rapid advances in single-cell RNA sequencing (scRNA-seq) have made it possible to characterize cell states at a high resolution view for large scale library. scRNA-seq data contains a great deal of biological information, which can be mainly used to discover cell subtypes and track cell development. However, traditional methods face many challenges in addressing scRNA-seq data with high dimensions and high sparsity. For better analysis of scRNA-seq data, we propose a new framework called MSVGAE based on variational graph auto-encoder and graph attention networks. Specifically, we introduce multiple encoders to learn features at different scales and control for uninformative features. Moreover, different noises are added to encoders to promote the propagation of graph structural information and distribution uncertainty. Therefore, some complex posterior distributions can be captured by our model. MSVGAE maps scRNA-seq data with high dimensions and high noise into the low-dimensional latent space, which is beneficial for downstream tasks. In particular, MSVGAE can handle extremely sparse data. Before the experiment, we create 24 simulated datasets to simulate various biological scenarios and collect 8 real-world datasets. The experimental results of clustering, visualization and marker genes analysis indicate that MSVGAE model has excellent accuracy and robustness in analyzing scRNA-seq data.","PeriodicalId":13344,"journal":{"name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","volume":"21 6","pages":"2280-2291"},"PeriodicalIF":3.6,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142182856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-10DOI: 10.1109/TCBB.2024.3457807
Yang Hua;Zhenhua Feng;Xiaoning Song;Hui Li;Tianyang Xu;Xiao-Jun Wu;Dong-Jun Yu
Recently, mask-fill-based 3D Molecular Generation (MG) methods have become very popular in virtual drug design. However, the existing MG methods ignore the chemical properties of atoms and contain inappropriate atomic position training data, which limits their generation capability. To mitigate the above issues, this paper presents a novel mask-fill-based 3D molecule generation model driven by atomic chemical properties (APMG). Specifically, we construct a new attention-MPNN-based encoder and introduce the electronic information into atom representations to enrich chemical properties. Also, a multi-functional classifier is designed to predict the electronic information of each generated atom, guiding the type prediction of elements and bonds. By design, the proposed method uses the chemical properties of atoms and their correlations for high-quality molecule generation. Second, to optimize the atomic position training data, we propose a novel atomic training position generation approach using the Chi-Square distribution. We evaluate our APMG method on the CrossDocked dataset and visualize the docking states of the pockets and generated molecules. The obtained results demonstrate the superiority and merits of APMG over the state-of-the-art approaches.
{"title":"APMG: 3D Molecule Generation Driven by Atomic Chemical Properties","authors":"Yang Hua;Zhenhua Feng;Xiaoning Song;Hui Li;Tianyang Xu;Xiao-Jun Wu;Dong-Jun Yu","doi":"10.1109/TCBB.2024.3457807","DOIUrl":"10.1109/TCBB.2024.3457807","url":null,"abstract":"Recently, mask-fill-based 3D Molecular Generation (MG) methods have become very popular in virtual drug design. However, the existing MG methods ignore the chemical properties of atoms and contain inappropriate atomic position training data, which limits their generation capability. To mitigate the above issues, this paper presents a novel mask-fill-based 3D molecule generation model driven by atomic chemical properties (APMG). Specifically, we construct a new attention-MPNN-based encoder and introduce the electronic information into atom representations to enrich chemical properties. Also, a multi-functional classifier is designed to predict the electronic information of each generated atom, guiding the type prediction of elements and bonds. By design, the proposed method uses the chemical properties of atoms and their correlations for high-quality molecule generation. Second, to optimize the atomic position training data, we propose a novel atomic training position generation approach using the Chi-Square distribution. We evaluate our APMG method on the CrossDocked dataset and visualize the docking states of the pockets and generated molecules. The obtained results demonstrate the superiority and merits of APMG over the state-of-the-art approaches.","PeriodicalId":13344,"journal":{"name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","volume":"21 6","pages":"2269-2279"},"PeriodicalIF":3.6,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142182853","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-10DOI: 10.1109/TCBB.2024.3456302
Vincent Deman;Marine Ciantar;Laurent Naudin;Philippe Castera;Anne-Sophie Beignon
Large amounts of knowledge regarding biological processes are readily available in the literature and aggregated in diverse databases. Boolean networks are powerful tools to render that knowledge into models that can mimic and simulate biological phenomena at multiple scales. Yet, when a model is required to understand or predict the behavior of a biological system in given conditions, existing information often does not completely match this context. Networks built from only prior knowledge can overlook mechanisms, lack specificity, and just partially recapitulate experimental observations. To address this limitation, context-specific data needs to be integrated. However, the brute-force identification of qualitative rules matching these data becomes infeasible as the number of candidates explodes for increasingly complex systems. Here, we used Zhegalkin polynomials to transform this identification into a binary value assignment for exponentially fewer variables, which we addressed with a state-of-the-art SAT solver. We evaluated our implemented method alongside two widely recognized tools, CellNetOptimizer and Caspo-ts, on both artificial toy models and large-scale models based on experimental data from the HPN-DREAM challenge. Our approach demonstrated benchmark-leading capabilities on networks of significant size and intricate complexity. It thus appears promising for the in silico modeling of ever more comprehensive biological systems.
{"title":"Combining Zhegalkin Polynomials and SAT Solving for Context-Specific Boolean Modeling of Biological Systems","authors":"Vincent Deman;Marine Ciantar;Laurent Naudin;Philippe Castera;Anne-Sophie Beignon","doi":"10.1109/TCBB.2024.3456302","DOIUrl":"10.1109/TCBB.2024.3456302","url":null,"abstract":"Large amounts of knowledge regarding biological processes are readily available in the literature and aggregated in diverse databases. Boolean networks are powerful tools to render that knowledge into models that can mimic and simulate biological phenomena at multiple scales. Yet, when a model is required to understand or predict the behavior of a biological system in given conditions, existing information often does not completely match this context. Networks built from only prior knowledge can overlook mechanisms, lack specificity, and just partially recapitulate experimental observations. To address this limitation, context-specific data needs to be integrated. However, the brute-force identification of qualitative rules matching these data becomes infeasible as the number of candidates explodes for increasingly complex systems. Here, we used Zhegalkin polynomials to transform this identification into a binary value assignment for exponentially fewer variables, which we addressed with a state-of-the-art SAT solver. We evaluated our implemented method alongside two widely recognized tools, CellNetOptimizer and Caspo-ts, on both artificial toy models and large-scale models based on experimental data from the HPN-DREAM challenge. Our approach demonstrated benchmark-leading capabilities on networks of significant size and intricate complexity. It thus appears promising for the \u0000<italic>in silico</i>\u0000 modeling of ever more comprehensive biological systems.","PeriodicalId":13344,"journal":{"name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","volume":"21 6","pages":"2188-2199"},"PeriodicalIF":3.6,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10671585","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142182852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-10DOI: 10.1109/TCBB.2024.3457875
Lars Berling;Remco Bouckaert;Alex Gavryushkin
Assessing convergence of Markov chain Monte Carlo (MCMC) based analyses is crucial but challenging, especially so in high dimensional and complex spaces such as the space of phylogenetic trees (treespace). In practice, it is assumed that the target distribution is the unique stationary distribution of the MCMC and convergence is achieved when samples appear to be stationary. Here we leverage recent advances in computational geometry of the treespace and introduce a method that combines classical statistical techniques and algorithms with geometric properties of the treespace to automatically evaluate and assess practical convergence of phylogenetic MCMC analyses. Our method monitors convergence across multiple MCMC chains and achieves high accuracy in detecting both practical convergence and convergence issues within treespace. Furthermore, our approach is developed to allow for real-time evaluation during the MCMC algorithm run, eliminating any of the chain post-processing steps that are currently required. Our tool therefore improves reliability and efficiency of MCMC based phylogenetic inference methods and makes analyses easier to reproduce and compare. We demonstrate the efficacy of our diagnostic via a well-calibrated simulation study and provide examples of its performance on real data sets. Although our method performs well in practice, a significant part of the underlying treespace probability theory is still missing, which creates an excellent opportunity for future mathematical research in this area.
{"title":"An Automated Convergence Diagnostic for Phylogenetic MCMC Analyses","authors":"Lars Berling;Remco Bouckaert;Alex Gavryushkin","doi":"10.1109/TCBB.2024.3457875","DOIUrl":"10.1109/TCBB.2024.3457875","url":null,"abstract":"Assessing convergence of Markov chain Monte Carlo (MCMC) based analyses is crucial but challenging, especially so in high dimensional and complex spaces such as the space of phylogenetic trees (treespace). In practice, it is assumed that the target distribution is the unique stationary distribution of the MCMC and convergence is achieved when samples appear to be stationary. Here we leverage recent advances in computational geometry of the treespace and introduce a method that combines classical statistical techniques and algorithms with geometric properties of the treespace to automatically evaluate and assess practical convergence of phylogenetic MCMC analyses. Our method monitors convergence across multiple MCMC chains and achieves high accuracy in detecting both practical convergence and convergence issues within treespace. Furthermore, our approach is developed to allow for real-time evaluation during the MCMC algorithm run, eliminating any of the chain post-processing steps that are currently required. Our tool therefore improves reliability and efficiency of MCMC based phylogenetic inference methods and makes analyses easier to reproduce and compare. We demonstrate the efficacy of our diagnostic via a well-calibrated simulation study and provide examples of its performance on real data sets. Although our method performs well in practice, a significant part of the underlying treespace probability theory is still missing, which creates an excellent opportunity for future mathematical research in this area.","PeriodicalId":13344,"journal":{"name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","volume":"21 6","pages":"2246-2257"},"PeriodicalIF":3.6,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10675342","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142182854","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-09DOI: 10.1109/TCBB.2024.3456575
Takatora Suzuki;Han Guo;Momoko Hayamizu
Phylogenetic networks are a useful model that can represent reticulate evolution and complex biological data. In recent years, mathematical and computational aspects of tree-based networks have been well studied. However, not all phylogenetic networks are tree-based, so it is meaningful to consider how close a given network is to being tree-based; Francis–Steel–Semple (2018) proposed several different indices to measure the degree of deviation of a phylogenetic network from being tree-based. One is the minimum number of leaves that need to be added to convert a given network to tree-based, and another is the number of vertices that are not included in the largest subtree covering its leaf-set. Both values are zero if and only if the network is tree-based. Both deviation indices can be computed efficiently, but the relationship between the above two is unknown, as each has been studied using different approaches. In this study, we derive a tight inequality for the values of the two measures and also give a characterisation of phylogenetic networks such that they coincide. This characterisation yields a new efficient algorithm for the Maximum Covering Subtree Problem based on the maximal zig-zag trail decomposition.
{"title":"Bridging Between Deviation Indices for Non-Tree-Based Phylogenetic Networks","authors":"Takatora Suzuki;Han Guo;Momoko Hayamizu","doi":"10.1109/TCBB.2024.3456575","DOIUrl":"10.1109/TCBB.2024.3456575","url":null,"abstract":"Phylogenetic networks are a useful model that can represent reticulate evolution and complex biological data. In recent years, mathematical and computational aspects of tree-based networks have been well studied. However, not all phylogenetic networks are tree-based, so it is meaningful to consider how close a given network is to being tree-based; Francis–Steel–Semple (2018) proposed several different indices to measure the degree of deviation of a phylogenetic network from being tree-based. One is the minimum number of leaves that need to be added to convert a given network to tree-based, and another is the number of vertices that are not included in the largest subtree covering its leaf-set. Both values are zero if and only if the network is tree-based. Both deviation indices can be computed efficiently, but the relationship between the above two is unknown, as each has been studied using different approaches. In this study, we derive a tight inequality for the values of the two measures and also give a characterisation of phylogenetic networks such that they coincide. This characterisation yields a new efficient algorithm for the Maximum Covering Subtree Problem based on the maximal zig-zag trail decomposition.","PeriodicalId":13344,"journal":{"name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","volume":"21 6","pages":"2226-2234"},"PeriodicalIF":3.6,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10670207","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142182857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-06DOI: 10.1109/TCBB.2024.3451348
Zhijing Li;Liwei Tian;Yiping Jiang;Yucheng Huang
Relation extraction, a crucial task in understanding the intricate relationships between entities in biomedical domains, has predominantly focused on binary relations within single sentences. However, in practical biomedical scenarios, relationships often extend across multiple sentences, leading to extraction errors with potential impacts on clinical decision-making and medical diagnosis. To overcome this limitation, we present a novel cross-sentence relation extraction framework that integrates and enhances coreference resolution and relation extraction models. Coreference resolution serves as the foundation, breaking sentence boundaries and linking entities across sentences. Our framework incorporates pre-trained deep language representations and leverages graph LSTMs to effectively model cross-sentence entity mentions. The use of a self-attentive Transformer architecture and external semantic information further enhances the modeling of intricate relationships. Comprehensive experiments conducted on two standard datasets, namely the BioNLP dataset and THYME dataset, demonstrate the state-of-the-art performance of our proposed approach.
{"title":"Relation Extraction in Biomedical Texts: A Cross-Sentence Approach","authors":"Zhijing Li;Liwei Tian;Yiping Jiang;Yucheng Huang","doi":"10.1109/TCBB.2024.3451348","DOIUrl":"10.1109/TCBB.2024.3451348","url":null,"abstract":"Relation extraction, a crucial task in understanding the intricate relationships between entities in biomedical domains, has predominantly focused on binary relations within single sentences. However, in practical biomedical scenarios, relationships often extend across multiple sentences, leading to extraction errors with potential impacts on clinical decision-making and medical diagnosis. To overcome this limitation, we present a novel cross-sentence relation extraction framework that integrates and enhances coreference resolution and relation extraction models. Coreference resolution serves as the foundation, breaking sentence boundaries and linking entities across sentences. Our framework incorporates pre-trained deep language representations and leverages graph LSTMs to effectively model cross-sentence entity mentions. The use of a self-attentive Transformer architecture and external semantic information further enhances the modeling of intricate relationships. Comprehensive experiments conducted on two standard datasets, namely the BioNLP dataset and THYME dataset, demonstrate the state-of-the-art performance of our proposed approach.","PeriodicalId":13344,"journal":{"name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","volume":"21 6","pages":"2156-2166"},"PeriodicalIF":3.6,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142142977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-06DOI: 10.1109/TCBB.2024.3455381
Hao Lu;Zhiqiang Wei;Kun Zhang;Xuze Wang;Liaqat Ali;Hao Liu
Retrosynthesis prediction is a fundamental problem in organic chemistry and drug synthesis. We proposed an end-to-end deep learning model called CTsynther (Contrastive Transformer for single-step retrosynthesis prediction model) that could provide single-step retrosynthesis prediction without external reaction templates or specialized knowledge. The model introduced the concept of contrastive learning in Transformer architecture and employed a contrastive learning language representation model at the SMILES sentence level to enhance model inference by learning similarities and differences between various samples. Mixed global and local attention mechanisms allow the model to capture features and dependencies between different atoms to improve generalization. We further investigated the embedding representations of SMILES learned automatically from the model. Visualization results show that the model could effectively acquire information about identical molecules and improve prediction performance. Experiments showed that the accuracy of retrosynthesis reached 53.5% and 64.4% for with and without reaction types, respectively. The validity of the predicted reactants is improved, showing competitiveness compared with semi-template methods.
{"title":"CTsynther: Contrastive Transformer Model for End-to-End Retrosynthesis Prediction","authors":"Hao Lu;Zhiqiang Wei;Kun Zhang;Xuze Wang;Liaqat Ali;Hao Liu","doi":"10.1109/TCBB.2024.3455381","DOIUrl":"10.1109/TCBB.2024.3455381","url":null,"abstract":"Retrosynthesis prediction is a fundamental problem in organic chemistry and drug synthesis. We proposed an end-to-end deep learning model called CTsynther (Contrastive Transformer for single-step retrosynthesis prediction model) that could provide single-step retrosynthesis prediction without external reaction templates or specialized knowledge. The model introduced the concept of contrastive learning in Transformer architecture and employed a contrastive learning language representation model at the SMILES sentence level to enhance model inference by learning similarities and differences between various samples. Mixed global and local attention mechanisms allow the model to capture features and dependencies between different atoms to improve generalization. We further investigated the embedding representations of SMILES learned automatically from the model. Visualization results show that the model could effectively acquire information about identical molecules and improve prediction performance. Experiments showed that the accuracy of retrosynthesis reached 53.5% and 64.4% for with and without reaction types, respectively. The validity of the predicted reactants is improved, showing competitiveness compared with semi-template methods.","PeriodicalId":13344,"journal":{"name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","volume":"21 6","pages":"2235-2245"},"PeriodicalIF":3.6,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142142976","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-03DOI: 10.1109/TCBB.2024.3453499
Bin Liu;Grigorios Tsoumakas
In drug discovery, identifying drug-target interactions (DTIs) via experimental approaches is a tedious and expensive procedure. Computational methods efficiently predict DTIs and recommend a small part of potential interacting pairs for further experimental confirmation, accelerating the drug discovery process. Although fusing heterogeneous drug and target similarities can improve the prediction ability, the existing similarity combination methods ignore the interaction consistency for neighbour entities. Furthermore, area under the precision-recall curve (AUPR) and area under the receiver operating characteristic curve (AUC) are two widely used evaluation metrics in DTI prediction. However, the two metrics are seldom considered as losses within existing DTI prediction methods. We propose a local interaction consistency (LIC) aware similarity integration method to fuse vital information from diverse views for DTI prediction models. Furthermore, we propose two matrix factorization (MF) methods that optimize AUPR and AUC using convex surrogate losses respectively, and then develop an ensemble MF approach that takes advantage of the two area under the curve metrics by combining the two single metric based MF models. Experimental results under different prediction settings show that the proposed methods outperform various competitors in terms of the metric(s) they optimize and are reliable in discovering potential new DTIs.
{"title":"Integrating Similarities via Local Interaction Consistency and Optimizing Area Under the Curve Measures via Matrix Factorization for Drug-Target Interaction Prediction","authors":"Bin Liu;Grigorios Tsoumakas","doi":"10.1109/TCBB.2024.3453499","DOIUrl":"10.1109/TCBB.2024.3453499","url":null,"abstract":"In drug discovery, identifying drug-target interactions (DTIs) via experimental approaches is a tedious and expensive procedure. Computational methods efficiently predict DTIs and recommend a small part of potential interacting pairs for further experimental confirmation, accelerating the drug discovery process. Although fusing heterogeneous drug and target similarities can improve the prediction ability, the existing similarity combination methods ignore the interaction consistency for neighbour entities. Furthermore, area under the precision-recall curve (AUPR) and area under the receiver operating characteristic curve (AUC) are two widely used evaluation metrics in DTI prediction. However, the two metrics are seldom considered as losses within existing DTI prediction methods. We propose a local interaction consistency (LIC) aware similarity integration method to fuse vital information from diverse views for DTI prediction models. Furthermore, we propose two matrix factorization (MF) methods that optimize AUPR and AUC using convex surrogate losses respectively, and then develop an ensemble MF approach that takes advantage of the two area under the curve metrics by combining the two single metric based MF models. Experimental results under different prediction settings show that the proposed methods outperform various competitors in terms of the metric(s) they optimize and are reliable in discovering potential new DTIs.","PeriodicalId":13344,"journal":{"name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","volume":"21 6","pages":"2212-2225"},"PeriodicalIF":3.6,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142125626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：