James S L Browning, Daniel R Tauritz, John Beckmann
The genetic blueprint for the essential functions of life is encoded in DNA, which is translated into proteins-the engines driving most of our metabolic processes. Recent advancements in genome sequencing have unveiled a vast diversity of protein families, but compared with the massive search space of all possible amino acid sequences, the set of known functional families is minimal. One could say nature has a limited protein "vocabulary." A major question for computational biologists, therefore, is whether this vocabulary can be expanded to include useful proteins that went extinct long ago or have never evolved (yet). By merging evolutionary algorithms, machine learning, and bioinformatics, we can develop highly customized "designer proteins." We dub the new subfield of computational evolution, which employs evolutionary algorithms with DNA string representations, biologically accurate molecular evolution, and bioinformatics-informed fitness functions, Evolutionary Algorithms Simulating Molecular Evolution.
{"title":"Evolutionary algorithms simulating molecular evolution: a new field proposal.","authors":"James S L Browning, Daniel R Tauritz, John Beckmann","doi":"10.1093/bib/bbae360","DOIUrl":"10.1093/bib/bbae360","url":null,"abstract":"<p><p>The genetic blueprint for the essential functions of life is encoded in DNA, which is translated into proteins-the engines driving most of our metabolic processes. Recent advancements in genome sequencing have unveiled a vast diversity of protein families, but compared with the massive search space of all possible amino acid sequences, the set of known functional families is minimal. One could say nature has a limited protein \"vocabulary.\" A major question for computational biologists, therefore, is whether this vocabulary can be expanded to include useful proteins that went extinct long ago or have never evolved (yet). By merging evolutionary algorithms, machine learning, and bioinformatics, we can develop highly customized \"designer proteins.\" We dub the new subfield of computational evolution, which employs evolutionary algorithms with DNA string representations, biologically accurate molecular evolution, and bioinformatics-informed fitness functions, Evolutionary Algorithms Simulating Molecular Evolution.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11317538/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141916159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Haoyang Mi, Shamilene Sivagnanam, Won Jin Ho, Shuming Zhang, Daniel Bergman, Atul Deshpande, Alexander S Baras, Elizabeth M Jaffee, Lisa M Coussens, Elana J Fertig, Aleksander S Popel
Advancements in imaging technologies have revolutionized our ability to deeply profile pathological tissue architectures, generating large volumes of imaging data with unparalleled spatial resolution. This type of data collection, namely, spatial proteomics, offers invaluable insights into various human diseases. Simultaneously, computational algorithms have evolved to manage the increasing dimensionality of spatial proteomics inherent in this progress. Numerous imaging-based computational frameworks, such as computational pathology, have been proposed for research and clinical applications. However, the development of these fields demands diverse domain expertise, creating barriers to their integration and further application. This review seeks to bridge this divide by presenting a comprehensive guideline. We consolidate prevailing computational methods and outline a roadmap from image processing to data-driven, statistics-informed biomarker discovery. Additionally, we explore future perspectives as the field moves toward interfacing with other quantitative domains, holding significant promise for precision care in immuno-oncology.
{"title":"Computational methods and biomarker discovery strategies for spatial proteomics: a review in immuno-oncology.","authors":"Haoyang Mi, Shamilene Sivagnanam, Won Jin Ho, Shuming Zhang, Daniel Bergman, Atul Deshpande, Alexander S Baras, Elizabeth M Jaffee, Lisa M Coussens, Elana J Fertig, Aleksander S Popel","doi":"10.1093/bib/bbae421","DOIUrl":"10.1093/bib/bbae421","url":null,"abstract":"<p><p>Advancements in imaging technologies have revolutionized our ability to deeply profile pathological tissue architectures, generating large volumes of imaging data with unparalleled spatial resolution. This type of data collection, namely, spatial proteomics, offers invaluable insights into various human diseases. Simultaneously, computational algorithms have evolved to manage the increasing dimensionality of spatial proteomics inherent in this progress. Numerous imaging-based computational frameworks, such as computational pathology, have been proposed for research and clinical applications. However, the development of these fields demands diverse domain expertise, creating barriers to their integration and further application. This review seeks to bridge this divide by presenting a comprehensive guideline. We consolidate prevailing computational methods and outline a roadmap from image processing to data-driven, statistics-informed biomarker discovery. Additionally, we explore future perspectives as the field moves toward interfacing with other quantitative domains, holding significant promise for precision care in immuno-oncology.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11343572/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142046352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Genome-scale metabolic models (GEMs) are powerful tools for predicting cellular metabolic and physiological states. However, there are still missing reactions in GEMs due to incomplete knowledge. Recent gaps filling methods suggest directly predicting missing responses without relying on phenotypic data. However, they do not differentiate between substrates and products when constructing the prediction models, which affects the predictive performance of the models. In this paper, we propose a hyperedge prediction model that distinguishes substrates and products based on dual-scale fused hypergraph convolution, DSHCNet, for inferring the missing reactions to effectively fill gaps in the GEM. First, we model each hyperedge as a heterogeneous complete graph and then decompose it into three subgraphs at both homogeneous and heterogeneous scales. Then we design two graph convolution-based models to, respectively, extract features of the vertices in two scales, which are then fused via the attention mechanism. Finally, the features of all vertices are further pooled to generate the representative feature of the hyperedge. The strategy of graph decomposition in DSHCNet enables the vertices to engage in message passing independently at both scales, thereby enhancing the capability of information propagation and making the obtained product and substrate features more distinguishable. The experimental results show that the average recovery rate of missing reactions obtained by DSHCNet is at least 11.7% higher than that of the state-of-the-art methods, and that the gap-filled GEMs based on our DSHCNet model achieve the best prediction performance, demonstrating the superiority of our method.
{"title":"A dual-scale fused hypergraph convolution-based hyperedge prediction model for predicting missing reactions in genome-scale metabolic networks.","authors":"Weihong Huang, Feng Yang, Qiang Zhang, Juan Liu","doi":"10.1093/bib/bbae383","DOIUrl":"10.1093/bib/bbae383","url":null,"abstract":"<p><p>Genome-scale metabolic models (GEMs) are powerful tools for predicting cellular metabolic and physiological states. However, there are still missing reactions in GEMs due to incomplete knowledge. Recent gaps filling methods suggest directly predicting missing responses without relying on phenotypic data. However, they do not differentiate between substrates and products when constructing the prediction models, which affects the predictive performance of the models. In this paper, we propose a hyperedge prediction model that distinguishes substrates and products based on dual-scale fused hypergraph convolution, DSHCNet, for inferring the missing reactions to effectively fill gaps in the GEM. First, we model each hyperedge as a heterogeneous complete graph and then decompose it into three subgraphs at both homogeneous and heterogeneous scales. Then we design two graph convolution-based models to, respectively, extract features of the vertices in two scales, which are then fused via the attention mechanism. Finally, the features of all vertices are further pooled to generate the representative feature of the hyperedge. The strategy of graph decomposition in DSHCNet enables the vertices to engage in message passing independently at both scales, thereby enhancing the capability of information propagation and making the obtained product and substrate features more distinguishable. The experimental results show that the average recovery rate of missing reactions obtained by DSHCNet is at least 11.7% higher than that of the state-of-the-art methods, and that the gap-filled GEMs based on our DSHCNet model achieve the best prediction performance, demonstrating the superiority of our method.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11299038/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141888485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Genomic selection (GS) has emerged as an effective technology to accelerate crop hybrid breeding by enabling early selection prior to phenotype collection. Genomic best linear unbiased prediction (GBLUP) is a robust method that has been routinely used in GS breeding programs. However, GBLUP assumes that markers contribute equally to the total genetic variance, which may not be the case. In this study, we developed a novel GS method called GA-GBLUP that leverages the genetic algorithm (GA) to select markers related to the target trait. We defined four fitness functions for optimization, including AIC, BIC, R2, and HAT, to improve the predictability and bin adjacent markers based on the principle of linkage disequilibrium to reduce model dimension. The results demonstrate that the GA-GBLUP model, equipped with R2 and HAT fitness function, produces much higher predictability than GBLUP for most traits in rice and maize datasets, particularly for traits with low heritability. Moreover, we have developed a user-friendly R package, GAGBLUP, for GS, and the package is freely available on CRAN (https://CRAN.R-project.org/package=GAGBLUP).
基因组选择(GS)通过在收集表型之前进行早期选择,已成为加速作物杂交育种的有效技术。基因组最佳线性无偏预测(GBLUP)是一种稳健的方法,已被常规用于基因组选择育种项目。然而,GBLUP 假设标记对总遗传变异的贡献相同,而实际情况可能并非如此。在本研究中,我们开发了一种名为 GA-GBLUP 的新型基因组学方法,利用遗传算法(GA)来选择与目标性状相关的标记。我们定义了 AIC、BIC、R2 和 HAT 等四种适合度函数进行优化,以提高可预测性,并根据连锁不平衡原理将相邻标记进行分选,以减少模型维度。结果表明,对于水稻和玉米数据集中的大多数性状,尤其是遗传率较低的性状,配备 R2 和 HAT 健身函数的 GA-GBLUP 模型比 GBLUP 产生的预测性要高得多。此外,我们还为 GS 开发了一个用户友好型 R 软件包 GAGBLUP,该软件包可在 CRAN(https://CRAN.R-project.org/package=GAGBLUP)上免费获取。
{"title":"GA-GBLUP: leveraging the genetic algorithm to improve the predictability of genomic selection.","authors":"Yang Xu, Yuxiang Zhang, Yanru Cui, Kai Zhou, Guangning Yu, Wenyan Yang, Xin Wang, Furong Li, Xiusheng Guan, Xuecai Zhang, Zefeng Yang, Shizhong Xu, Chenwu Xu","doi":"10.1093/bib/bbae385","DOIUrl":"10.1093/bib/bbae385","url":null,"abstract":"<p><p>Genomic selection (GS) has emerged as an effective technology to accelerate crop hybrid breeding by enabling early selection prior to phenotype collection. Genomic best linear unbiased prediction (GBLUP) is a robust method that has been routinely used in GS breeding programs. However, GBLUP assumes that markers contribute equally to the total genetic variance, which may not be the case. In this study, we developed a novel GS method called GA-GBLUP that leverages the genetic algorithm (GA) to select markers related to the target trait. We defined four fitness functions for optimization, including AIC, BIC, R2, and HAT, to improve the predictability and bin adjacent markers based on the principle of linkage disequilibrium to reduce model dimension. The results demonstrate that the GA-GBLUP model, equipped with R2 and HAT fitness function, produces much higher predictability than GBLUP for most traits in rice and maize datasets, particularly for traits with low heritability. Moreover, we have developed a user-friendly R package, GAGBLUP, for GS, and the package is freely available on CRAN (https://CRAN.R-project.org/package=GAGBLUP).</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11299030/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141888487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yang Li, Anjun Ma, Yizhong Wang, Qi Guo, Cankun Wang, Hongjun Fu, Bingqiang Liu, Qin Ma
Deciphering the intricate relationships between transcription factors (TFs), enhancers, and genes through the inference of enhancer-driven gene regulatory networks (eGRNs) is crucial in understanding gene regulatory programs in a complex biological system. This study introduces STREAM, a novel method that leverages a Steiner forest problem model, a hybrid biclustering pipeline, and submodular optimization to infer eGRNs from jointly profiled single-cell transcriptome and chromatin accessibility data. Compared to existing methods, STREAM demonstrates enhanced performance in terms of TF recovery, TF-enhancer linkage prediction, and enhancer-gene relation discovery. Application of STREAM to an Alzheimer's disease dataset and a diffuse small lymphocytic lymphoma dataset reveals its ability to identify TF-enhancer-gene relations associated with pseudotime, as well as key TF-enhancer-gene relations and TF cooperation underlying tumor cells.
{"title":"Enhancer-driven gene regulatory networks inference from single-cell RNA-seq and ATAC-seq data.","authors":"Yang Li, Anjun Ma, Yizhong Wang, Qi Guo, Cankun Wang, Hongjun Fu, Bingqiang Liu, Qin Ma","doi":"10.1093/bib/bbae369","DOIUrl":"10.1093/bib/bbae369","url":null,"abstract":"<p><p>Deciphering the intricate relationships between transcription factors (TFs), enhancers, and genes through the inference of enhancer-driven gene regulatory networks (eGRNs) is crucial in understanding gene regulatory programs in a complex biological system. This study introduces STREAM, a novel method that leverages a Steiner forest problem model, a hybrid biclustering pipeline, and submodular optimization to infer eGRNs from jointly profiled single-cell transcriptome and chromatin accessibility data. Compared to existing methods, STREAM demonstrates enhanced performance in terms of TF recovery, TF-enhancer linkage prediction, and enhancer-gene relation discovery. Application of STREAM to an Alzheimer's disease dataset and a diffuse small lymphocytic lymphoma dataset reveals its ability to identify TF-enhancer-gene relations associated with pseudotime, as well as key TF-enhancer-gene relations and TF cooperation underlying tumor cells.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11289686/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141854883","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Metabolic processes can transform a drug into metabolites with different properties that may affect its efficacy and safety. Therefore, investigation of the metabolic fate of a drug candidate is of great significance for drug discovery. Computational methods have been developed to predict drug metabolites, but most of them suffer from two main obstacles: the lack of model generalization due to restrictions on metabolic transformation rules or specific enzyme families, and high rate of false-positive predictions. Here, we presented MetaPredictor, a rule-free, end-to-end and prompt-based method to predict possible human metabolites of small molecules including drugs as a sequence translation problem. We innovatively introduced prompt engineering into deep language models to enrich domain knowledge and guide decision-making. The results showed that using prompts that specify the sites of metabolism (SoMs) can steer the model to propose more accurate metabolite predictions, achieving a 30.4% increase in recall and a 16.8% reduction in false positives over the baseline model. The transfer learning strategy was also utilized to tackle the limited availability of metabolic data. For the adaptation to automatic or non-expert prediction, MetaPredictor was designed as a two-stage schema consisting of automatic identification of SoMs followed by metabolite prediction. Compared to four available drug metabolite prediction tools, our method showed comparable performance on the major enzyme families and better generalization that could additionally identify metabolites catalyzed by less common enzymes. The results indicated that MetaPredictor could provide a more comprehensive and accurate prediction of drug metabolism through the effective combination of transfer learning and prompt-based learning strategies.
{"title":"MetaPredictor: in silico prediction of drug metabolites based on deep language models with prompt engineering.","authors":"Keyun Zhu, Mengting Huang, Yimeng Wang, Yaxin Gu, Weihua Li, Guixia Liu, Yun Tang","doi":"10.1093/bib/bbae374","DOIUrl":"10.1093/bib/bbae374","url":null,"abstract":"<p><p>Metabolic processes can transform a drug into metabolites with different properties that may affect its efficacy and safety. Therefore, investigation of the metabolic fate of a drug candidate is of great significance for drug discovery. Computational methods have been developed to predict drug metabolites, but most of them suffer from two main obstacles: the lack of model generalization due to restrictions on metabolic transformation rules or specific enzyme families, and high rate of false-positive predictions. Here, we presented MetaPredictor, a rule-free, end-to-end and prompt-based method to predict possible human metabolites of small molecules including drugs as a sequence translation problem. We innovatively introduced prompt engineering into deep language models to enrich domain knowledge and guide decision-making. The results showed that using prompts that specify the sites of metabolism (SoMs) can steer the model to propose more accurate metabolite predictions, achieving a 30.4% increase in recall and a 16.8% reduction in false positives over the baseline model. The transfer learning strategy was also utilized to tackle the limited availability of metabolic data. For the adaptation to automatic or non-expert prediction, MetaPredictor was designed as a two-stage schema consisting of automatic identification of SoMs followed by metabolite prediction. Compared to four available drug metabolite prediction tools, our method showed comparable performance on the major enzyme families and better generalization that could additionally identify metabolites catalyzed by less common enzymes. The results indicated that MetaPredictor could provide a more comprehensive and accurate prediction of drug metabolism through the effective combination of transfer learning and prompt-based learning strategies.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11289679/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141854886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Histone modifications, known as histone marks, are pivotal in regulating gene expression within cells. The vast array of potential combinations of histone marks presents a considerable challenge in decoding the regulatory mechanisms solely through biological experimental approaches. To overcome this challenge, we have developed a method called CatLearning. It utilizes a modified convolutional neural network architecture with a specialized adaptation Residual Network to quantitatively interpret histone marks and predict gene expression. This architecture integrates long-range histone information up to 500Kb and learns chromatin interaction features without 3D information. By using only one histone mark, CatLearning achieves a high level of accuracy. Furthermore, CatLearning predicts gene expression by simulating changes in histone modifications at enhancers and throughout the genome. These findings help comprehend the architecture of histone marks and develop diagnostic and therapeutic targets for diseases with epigenetic changes.
{"title":"CatLearning: highly accurate gene expression prediction from histone mark.","authors":"Weining Lu, Yin Tang, Yu Liu, Shiyi Lin, Qifan Shuai, Bin Liang, Rongqing Zhang, Yu Cheng, Dong Fang","doi":"10.1093/bib/bbae373","DOIUrl":"10.1093/bib/bbae373","url":null,"abstract":"<p><p>Histone modifications, known as histone marks, are pivotal in regulating gene expression within cells. The vast array of potential combinations of histone marks presents a considerable challenge in decoding the regulatory mechanisms solely through biological experimental approaches. To overcome this challenge, we have developed a method called CatLearning. It utilizes a modified convolutional neural network architecture with a specialized adaptation Residual Network to quantitatively interpret histone marks and predict gene expression. This architecture integrates long-range histone information up to 500Kb and learns chromatin interaction features without 3D information. By using only one histone mark, CatLearning achieves a high level of accuracy. Furthermore, CatLearning predicts gene expression by simulating changes in histone modifications at enhancers and throughout the genome. These findings help comprehend the architecture of histone marks and develop diagnostic and therapeutic targets for diseases with epigenetic changes.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11285185/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141787300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shunjie Zhang, Pan Li, Shenghan Wang, Jijun Zhu, Zhongting Huang, Fuqiang Cai, Sebastian Freidel, Fei Ling, Emanuel Schwarz, Junfang Chen
Navigating the complex landscape of high-dimensional omics data with machine learning models presents a significant challenge. The integration of biological domain knowledge into these models has shown promise in creating more meaningful stratifications of predictor variables, leading to algorithms that are both more accurate and generalizable. However, the wider availability of machine learning tools capable of incorporating such biological knowledge remains limited. Addressing this gap, we introduce BioM2, a novel R package designed for biologically informed multistage machine learning. BioM2 uniquely leverages biological information to effectively stratify and aggregate high-dimensional biological data in the context of machine learning. Demonstrating its utility with genome-wide DNA methylation and transcriptome-wide gene expression data, BioM2 has shown to enhance predictive performance, surpassing traditional machine learning models that operate without the integration of biological knowledge. A key feature of BioM2 is its ability to rank predictor variables within biological categories, specifically Gene Ontology pathways. This functionality not only aids in the interpretability of the results but also enables a subsequent modular network analysis of these variables, shedding light on the intricate systems-level biology underpinning the predictive outcome. We have proposed a biologically informed multistage machine learning framework termed BioM2 for phenotype prediction based on omics data. BioM2 has been incorporated into the BioM2 CRAN package (https://cran.r-project.org/web/packages/BioM2/index.html).
利用机器学习模型浏览复杂的高维 omics 数据是一项重大挑战。将生物领域知识整合到这些模型中,有望对预测变量进行更有意义的分层,从而使算法更准确、更具有普适性。然而,能够将此类生物知识融入机器学习工具的可用性仍然有限。为了填补这一空白,我们推出了 BioM2,这是一个新颖的 R 软件包,专为生物信息多阶段机器学习而设计。BioM2 可独特地利用生物信息,在机器学习中有效地分层和聚合高维生物数据。BioM2 在全基因组 DNA 甲基化和全转录组基因表达数据中的应用表明,它能提高预测性能,超越了没有整合生物知识的传统机器学习模型。BioM2 的一个主要特点是它能在生物类别(特别是基因本体论途径)内对预测变量进行排序。这一功能不仅有助于结果的可解释性,还能对这些变量进行后续的模块化网络分析,从而揭示支撑预测结果的错综复杂的系统级生物学。我们提出了一种基于生物信息的多阶段机器学习框架,称为 BioM2,用于基于 omics 数据的表型预测。BioM2 已被纳入 BioM2 CRAN 软件包 (https://cran.r-project.org/web/packages/BioM2/index.html)。
{"title":"BioM2: biologically informed multi-stage machine learning for phenotype prediction using omics data.","authors":"Shunjie Zhang, Pan Li, Shenghan Wang, Jijun Zhu, Zhongting Huang, Fuqiang Cai, Sebastian Freidel, Fei Ling, Emanuel Schwarz, Junfang Chen","doi":"10.1093/bib/bbae384","DOIUrl":"10.1093/bib/bbae384","url":null,"abstract":"<p><p>Navigating the complex landscape of high-dimensional omics data with machine learning models presents a significant challenge. The integration of biological domain knowledge into these models has shown promise in creating more meaningful stratifications of predictor variables, leading to algorithms that are both more accurate and generalizable. However, the wider availability of machine learning tools capable of incorporating such biological knowledge remains limited. Addressing this gap, we introduce BioM2, a novel R package designed for biologically informed multistage machine learning. BioM2 uniquely leverages biological information to effectively stratify and aggregate high-dimensional biological data in the context of machine learning. Demonstrating its utility with genome-wide DNA methylation and transcriptome-wide gene expression data, BioM2 has shown to enhance predictive performance, surpassing traditional machine learning models that operate without the integration of biological knowledge. A key feature of BioM2 is its ability to rank predictor variables within biological categories, specifically Gene Ontology pathways. This functionality not only aids in the interpretability of the results but also enables a subsequent modular network analysis of these variables, shedding light on the intricate systems-level biology underpinning the predictive outcome. We have proposed a biologically informed multistage machine learning framework termed BioM2 for phenotype prediction based on omics data. BioM2 has been incorporated into the BioM2 CRAN package (https://cran.r-project.org/web/packages/BioM2/index.html).</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11316398/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141911770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Immunotherapy with immune checkpoint inhibitors (ICIs) is increasingly used to treat various tumor types. Determining patient responses to ICIs presents a significant clinical challenge. Although components of the tumor microenvironment (TME) are used to predict patient outcomes, comprehensive assessments of the TME are frequently overlooked. Using a top-down approach, the TME was divided into five layers-outcome, immune role, cell, cellular component, and gene. Using this structure, a neural network called TME-NET was developed to predict responses to ICIs. Model parameter weights and cell ablation studies were used to investigate the influence of TME components. The model was developed and evaluated using a pan-cancer cohort of 948 patients across four cancer types, with Area Under the Curve (AUC) and accuracy as performance metrics. Results show that TME-NET surpasses established models such as support vector machine and k-nearest neighbors in AUC and accuracy. Visualization of model parameter weights showed that at the cellular layer, Th1 cells enhance immune responses, whereas myeloid-derived suppressor cells and M2 macrophages show strong immunosuppressive effects. Cell ablation studies further confirmed the impact of these cells. At the gene layer, the transcription factors STAT4 in Th1 cells and IRF4 in M2 macrophages significantly affect TME dynamics. Additionally, the cytokine-encoding genes IFNG from Th1 cells and ARG1 from M2 macrophages are crucial for modulating immune responses within the TME. Survival data from immunotherapy cohorts confirmed the prognostic ability of these markers, with p-values <0.01. In summary, TME-NET performs well in predicting immunotherapy responses and offers interpretable insights into the immunotherapy process. It can be customized at https://immbal.shinyapps.io/TME-NET.
{"title":"TME-NET: an interpretable deep neural network for predicting pan-cancer immune checkpoint inhibitor responses.","authors":"Xiaobao Ding, Lin Zhang, Ming Fan, Lihua Li","doi":"10.1093/bib/bbae410","DOIUrl":"10.1093/bib/bbae410","url":null,"abstract":"<p><p>Immunotherapy with immune checkpoint inhibitors (ICIs) is increasingly used to treat various tumor types. Determining patient responses to ICIs presents a significant clinical challenge. Although components of the tumor microenvironment (TME) are used to predict patient outcomes, comprehensive assessments of the TME are frequently overlooked. Using a top-down approach, the TME was divided into five layers-outcome, immune role, cell, cellular component, and gene. Using this structure, a neural network called TME-NET was developed to predict responses to ICIs. Model parameter weights and cell ablation studies were used to investigate the influence of TME components. The model was developed and evaluated using a pan-cancer cohort of 948 patients across four cancer types, with Area Under the Curve (AUC) and accuracy as performance metrics. Results show that TME-NET surpasses established models such as support vector machine and k-nearest neighbors in AUC and accuracy. Visualization of model parameter weights showed that at the cellular layer, Th1 cells enhance immune responses, whereas myeloid-derived suppressor cells and M2 macrophages show strong immunosuppressive effects. Cell ablation studies further confirmed the impact of these cells. At the gene layer, the transcription factors STAT4 in Th1 cells and IRF4 in M2 macrophages significantly affect TME dynamics. Additionally, the cytokine-encoding genes IFNG from Th1 cells and ARG1 from M2 macrophages are crucial for modulating immune responses within the TME. Survival data from immunotherapy cohorts confirmed the prognostic ability of these markers, with p-values <0.01. In summary, TME-NET performs well in predicting immunotherapy responses and offers interpretable insights into the immunotherapy process. It can be customized at https://immbal.shinyapps.io/TME-NET.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11337220/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142016418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hamed Meshkin, Joel Zirkle, Ghazal Arabidarrehdor, Anik Chaturbedi, Shilpa Chakravartula, John Mann, Bradlee Thrasher, Zhihua Li
Large language models (LLMs) are sophisticated AI-driven models trained on vast sources of natural language data. They are adept at generating responses that closely mimic human conversational patterns. One of the most notable examples is OpenAI's ChatGPT, which has been extensively used across diverse sectors. Despite their flexibility, a significant challenge arises as most users must transmit their data to the servers of companies operating these models. Utilizing ChatGPT or similar models online may inadvertently expose sensitive information to the risk of data breaches. Therefore, implementing LLMs that are open source and smaller in scale within a secure local network becomes a crucial step for organizations where ensuring data privacy and protection has the highest priority, such as regulatory agencies. As a feasibility evaluation, we implemented a series of open-source LLMs within a regulatory agency's local network and assessed their performance on specific tasks involving extracting relevant clinical pharmacology information from regulatory drug labels. Our research shows that some models work well in the context of few- or zero-shot learning, achieving performance comparable, or even better than, neural network models that needed thousands of training samples. One of the models was selected to address a real-world issue of finding intrinsic factors that affect drugs' clinical exposure without any training or fine-tuning. In a dataset of over 700 000 sentences, the model showed a 78.5% accuracy rate. Our work pointed to the possibility of implementing open-source LLMs within a secure local network and using these models to perform various natural language processing tasks when large numbers of training examples are unavailable.
{"title":"Harnessing large language models' zero-shot and few-shot learning capabilities for regulatory research.","authors":"Hamed Meshkin, Joel Zirkle, Ghazal Arabidarrehdor, Anik Chaturbedi, Shilpa Chakravartula, John Mann, Bradlee Thrasher, Zhihua Li","doi":"10.1093/bib/bbae354","DOIUrl":"10.1093/bib/bbae354","url":null,"abstract":"<p><p>Large language models (LLMs) are sophisticated AI-driven models trained on vast sources of natural language data. They are adept at generating responses that closely mimic human conversational patterns. One of the most notable examples is OpenAI's ChatGPT, which has been extensively used across diverse sectors. Despite their flexibility, a significant challenge arises as most users must transmit their data to the servers of companies operating these models. Utilizing ChatGPT or similar models online may inadvertently expose sensitive information to the risk of data breaches. Therefore, implementing LLMs that are open source and smaller in scale within a secure local network becomes a crucial step for organizations where ensuring data privacy and protection has the highest priority, such as regulatory agencies. As a feasibility evaluation, we implemented a series of open-source LLMs within a regulatory agency's local network and assessed their performance on specific tasks involving extracting relevant clinical pharmacology information from regulatory drug labels. Our research shows that some models work well in the context of few- or zero-shot learning, achieving performance comparable, or even better than, neural network models that needed thousands of training samples. One of the models was selected to address a real-world issue of finding intrinsic factors that affect drugs' clinical exposure without any training or fine-tuning. In a dataset of over 700 000 sentences, the model showed a 78.5% accuracy rate. Our work pointed to the possibility of implementing open-source LLMs within a secure local network and using these models to perform various natural language processing tasks when large numbers of training examples are unavailable.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11342240/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142035262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}