The inference of gene regulatory networks (GRNs) is crucial to understanding the regulatory mechanisms that govern biological processes. GRNs may be represented as edges in a graph, and hence, it have been inferred computationally for scRNA-seq data. A wisdom of crowds approach to integrate edges from several GRNs to create one composite GRN has demonstrated improved performance when compared with individual algorithm implementations on bulk RNA-seq and microarray data. In an effort to extend this approach to scRNA-seq data, we present COFFEE (COnsensus single cell-type speciFic inFerence for gEnE regulatory networks), a Borda voting-based consensus algorithm that integrates information from 10 established GRN inference methods. We conclude that COFFEE has improved performance across synthetic, curated, and experimental datasets when compared with baseline methods. Additionally, we show that a modified version of COFFEE can be leveraged to improve performance on newer cell-type specific GRN inference methods. Overall, our results demonstrate that consensus-based methods with pertinent modifications continue to be valuable for GRN inference at the single cell level. While COFFEE is benchmarked on 10 algorithms, it is a flexible strategy that can incorporate any set of GRN inference algorithms according to user preference. A Python implementation of COFFEE may be found on GitHub: https://github.com/lodimk2/coffee.
{"title":"COFFEE: consensus single cell-type specific inference for gene regulatory networks.","authors":"Musaddiq K Lodi, Anna Chernikov, Preetam Ghosh","doi":"10.1093/bib/bbae457","DOIUrl":"10.1093/bib/bbae457","url":null,"abstract":"<p><p>The inference of gene regulatory networks (GRNs) is crucial to understanding the regulatory mechanisms that govern biological processes. GRNs may be represented as edges in a graph, and hence, it have been inferred computationally for scRNA-seq data. A wisdom of crowds approach to integrate edges from several GRNs to create one composite GRN has demonstrated improved performance when compared with individual algorithm implementations on bulk RNA-seq and microarray data. In an effort to extend this approach to scRNA-seq data, we present COFFEE (COnsensus single cell-type speciFic inFerence for gEnE regulatory networks), a Borda voting-based consensus algorithm that integrates information from 10 established GRN inference methods. We conclude that COFFEE has improved performance across synthetic, curated, and experimental datasets when compared with baseline methods. Additionally, we show that a modified version of COFFEE can be leveraged to improve performance on newer cell-type specific GRN inference methods. Overall, our results demonstrate that consensus-based methods with pertinent modifications continue to be valuable for GRN inference at the single cell level. While COFFEE is benchmarked on 10 algorithms, it is a flexible strategy that can incorporate any set of GRN inference algorithms according to user preference. A Python implementation of COFFEE may be found on GitHub: https://github.com/lodimk2/coffee.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11418232/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142280435","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}
The functional study of proteins is a critical task in modern biology, playing a pivotal role in understanding the mechanisms of pathogenesis, developing new drugs, and discovering novel drug targets. However, existing computational models for subcellular localization face significant challenges, such as reliance on known Gene Ontology (GO) annotation databases or overlooking the relationship between GO annotations and subcellular localization. To address these issues, we propose DeepMTC, an end-to-end deep learning-based multi-task collaborative training model. DeepMTC integrates the interrelationship between subcellular localization and the functional annotation of proteins, leveraging multi-task collaborative training to eliminate dependence on known GO databases. This strategy gives DeepMTC a distinct advantage in predicting newly discovered proteins without prior functional annotations. First, DeepMTC leverages pre-trained language model with high accuracy to obtain the 3D structure and sequence features of proteins. Additionally, it employs a graph transformer module to encode protein sequence features, addressing the problem of long-range dependencies in graph neural networks. Finally, DeepMTC uses a functional cross-attention mechanism to efficiently combine upstream learned functional features to perform the subcellular localization task. The experimental results demonstrate that DeepMTC outperforms state-of-the-art models in both protein function prediction and subcellular localization. Moreover, interpretability experiments revealed that DeepMTC can accurately identify the key residues and functional domains of proteins, confirming its superior performance. The code and dataset of DeepMTC are freely available at https://github.com/ghli16/DeepMTC.
蛋白质的功能研究是现代生物学的一项关键任务,在了解发病机制、开发新药和发现新的药物靶点方面发挥着举足轻重的作用。然而,现有的亚细胞定位计算模型面临着巨大的挑战,例如依赖于已知的基因本体(GO)注释数据库,或者忽视了 GO 注释与亚细胞定位之间的关系。为了解决这些问题,我们提出了基于深度学习的端到端多任务协作训练模型 DeepMTC。DeepMTC 整合了亚细胞定位与蛋白质功能注释之间的相互关系,利用多任务协作训练消除了对已知 GO 数据库的依赖。这一策略使 DeepMTC 在预测没有预先功能注释的新发现蛋白质时具有明显优势。首先,DeepMTC 利用预先训练的高精度语言模型来获取蛋白质的三维结构和序列特征。此外,它还采用了图转换器模块来编码蛋白质序列特征,从而解决了图神经网络中的长程依赖性问题。最后,DeepMTC 利用功能交叉注意机制,有效地结合上游学习到的功能特征来完成亚细胞定位任务。实验结果表明,DeepMTC 在蛋白质功能预测和亚细胞定位方面都优于最先进的模型。此外,可解释性实验表明,DeepMTC 能准确识别蛋白质的关键残基和功能域,从而证实了其卓越的性能。DeepMTC 的代码和数据集可在 https://github.com/ghli16/DeepMTC 免费获取。
{"title":"Deep learning model for protein multi-label subcellular localization and function prediction based on multi-task collaborative training.","authors":"Peihao Bai, Guanghui Li, Jiawei Luo, Cheng Liang","doi":"10.1093/bib/bbae568","DOIUrl":"10.1093/bib/bbae568","url":null,"abstract":"<p><p>The functional study of proteins is a critical task in modern biology, playing a pivotal role in understanding the mechanisms of pathogenesis, developing new drugs, and discovering novel drug targets. However, existing computational models for subcellular localization face significant challenges, such as reliance on known Gene Ontology (GO) annotation databases or overlooking the relationship between GO annotations and subcellular localization. To address these issues, we propose DeepMTC, an end-to-end deep learning-based multi-task collaborative training model. DeepMTC integrates the interrelationship between subcellular localization and the functional annotation of proteins, leveraging multi-task collaborative training to eliminate dependence on known GO databases. This strategy gives DeepMTC a distinct advantage in predicting newly discovered proteins without prior functional annotations. First, DeepMTC leverages pre-trained language model with high accuracy to obtain the 3D structure and sequence features of proteins. Additionally, it employs a graph transformer module to encode protein sequence features, addressing the problem of long-range dependencies in graph neural networks. Finally, DeepMTC uses a functional cross-attention mechanism to efficiently combine upstream learned functional features to perform the subcellular localization task. The experimental results demonstrate that DeepMTC outperforms state-of-the-art models in both protein function prediction and subcellular localization. Moreover, interpretability experiments revealed that DeepMTC can accurately identify the key residues and functional domains of proteins, confirming its superior performance. The code and dataset of DeepMTC are freely available at https://github.com/ghli16/DeepMTC.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11531862/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142567262","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}
Sébastien De Landtsheer, Apurva Badkas, Dagmar Kulms, Thomas Sauter
Stratification of patients diagnosed with cancer has become a major goal in personalized oncology. One important aspect is the accurate prediction of the response to various drugs. It is expected that the molecular characteristics of the cancer cells contain enough information to retrieve specific signatures, allowing for accurate predictions based solely on these multi-omic data. Ideally, these predictions should be explainable to clinicians, in order to be integrated in the patients care. We propose a machine-learning framework based on ensemble learning to integrate multi-omic data and predict sensitivity to an array of commonly used and experimental compounds, including chemotoxic compounds and targeted kinase inhibitors. We trained a set of classifiers on the different parts of our dataset to produce omic-specific signatures, then trained a random forest classifier on these signatures to predict drug responsiveness. We used the Cancer Cell Line Encyclopedia dataset, comprising multi-omic and drug sensitivity measurements for hundreds of cell lines, to build the predictive models, and validated the results using nested cross-validation. Our results show good performance for several compounds (Area under the Receiver-Operating Curve >79%) across the most frequent cancer types. Furthermore, the simplicity of our approach allows to examine which omic layers have a greater importance in the models and identify new putative markers of drug responsiveness. We propose several models based on small subsets of transcriptional markers with the potential to become useful tools in personalized oncology, paving the way for clinicians to use the molecular characteristics of the tumors to predict sensitivity to therapeutic compounds.
{"title":"Model ensembling as a tool to form interpretable multi-omic predictors of cancer pharmacosensitivity.","authors":"Sébastien De Landtsheer, Apurva Badkas, Dagmar Kulms, Thomas Sauter","doi":"10.1093/bib/bbae567","DOIUrl":"10.1093/bib/bbae567","url":null,"abstract":"<p><p>Stratification of patients diagnosed with cancer has become a major goal in personalized oncology. One important aspect is the accurate prediction of the response to various drugs. It is expected that the molecular characteristics of the cancer cells contain enough information to retrieve specific signatures, allowing for accurate predictions based solely on these multi-omic data. Ideally, these predictions should be explainable to clinicians, in order to be integrated in the patients care. We propose a machine-learning framework based on ensemble learning to integrate multi-omic data and predict sensitivity to an array of commonly used and experimental compounds, including chemotoxic compounds and targeted kinase inhibitors. We trained a set of classifiers on the different parts of our dataset to produce omic-specific signatures, then trained a random forest classifier on these signatures to predict drug responsiveness. We used the Cancer Cell Line Encyclopedia dataset, comprising multi-omic and drug sensitivity measurements for hundreds of cell lines, to build the predictive models, and validated the results using nested cross-validation. Our results show good performance for several compounds (Area under the Receiver-Operating Curve >79%) across the most frequent cancer types. Furthermore, the simplicity of our approach allows to examine which omic layers have a greater importance in the models and identify new putative markers of drug responsiveness. We propose several models based on small subsets of transcriptional markers with the potential to become useful tools in personalized oncology, paving the way for clinicians to use the molecular characteristics of the tumors to predict sensitivity to therapeutic compounds.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11532660/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142567268","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}
Advancements in peptidomics have revealed numerous small open reading frames with coding potential and revealed that some of these micropeptides are closely related to human cancer. However, the systematic analysis and integration from sequence to structure and function remains largely undeveloped. Here, as a solution, we built a workflow for the collection and analysis of proteomic data, transcriptomic data, and clinical outcomes for cancer-associated micropeptides using publicly available datasets from large cohorts. We initially identified 19 586 novel micropeptides by reanalyzing proteomic profile data from 3753 samples across 8 cancer types. Further quantitative analysis of these micropeptides, along with associated clinical data, identified 3065 that were dysregulated in cancer, with 370 of them showing a strong association with prognosis. Moreover, we employed a deep learning framework to construct a micropeptide-protein interaction network for further bioinformatics analysis, revealing that micropeptides are involved in multiple biological processes as bioactive molecules. Taken together, our atlas provides a benchmark for high-throughput prediction and functional exploration of micropeptides, providing new insights into their biological mechanisms in cancer. The HMPA is freely available at http://hmpa.zju.edu.cn.
{"title":"HMPA: a pioneering framework for the noncanonical peptidome from discovery to functional insights.","authors":"Xinwan Su, Chengyu Shi, Fangzhou Liu, Manman Tan, Ying Wang, Linyu Zhu, Yu Chen, Meng Yu, Xinyi Wang, Jian Liu, Yang Liu, Weiqiang Lin, Zhaoyuan Fang, Qiang Sun, Tianhua Zhou, Aifu Lin","doi":"10.1093/bib/bbae510","DOIUrl":"https://doi.org/10.1093/bib/bbae510","url":null,"abstract":"<p><p>Advancements in peptidomics have revealed numerous small open reading frames with coding potential and revealed that some of these micropeptides are closely related to human cancer. However, the systematic analysis and integration from sequence to structure and function remains largely undeveloped. Here, as a solution, we built a workflow for the collection and analysis of proteomic data, transcriptomic data, and clinical outcomes for cancer-associated micropeptides using publicly available datasets from large cohorts. We initially identified 19 586 novel micropeptides by reanalyzing proteomic profile data from 3753 samples across 8 cancer types. Further quantitative analysis of these micropeptides, along with associated clinical data, identified 3065 that were dysregulated in cancer, with 370 of them showing a strong association with prognosis. Moreover, we employed a deep learning framework to construct a micropeptide-protein interaction network for further bioinformatics analysis, revealing that micropeptides are involved in multiple biological processes as bioactive molecules. Taken together, our atlas provides a benchmark for high-throughput prediction and functional exploration of micropeptides, providing new insights into their biological mechanisms in cancer. The HMPA is freely available at http://hmpa.zju.edu.cn.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11483136/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142458374","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}
Matthijs Vynck, Wim Trypsteen, Olivier Thas, Jo Vandesompele, Ward De Spiegelaere
Digital polymerase chain reaction (dPCR) is a best-in-class molecular biology technique for the accurate and precise quantification of nucleic acids. The recent maturation of dPCR technology allows the quantification of up to thousands of targeted nucleic acids per instrument per day. A key step in the dPCR data analysis workflow is the classification of partitions into two classes based on their partition intensities: partitions either containing or lacking target nucleic acids of interest. Much effort has been invested in the design and tailoring of automated dPCR partition classification procedures, and such procedures will be increasingly important as the technology ventures into high-throughput applications. However, automated partition classification is not fail-safe, and evaluation of its accuracy is highly advised. This accuracy evaluation is a manual endeavor and is becoming a bottleneck for high-throughput dPCR applications. Here, we introduce dipcensR, the first data-analysis procedure that automates the assessment of any linear partition classifier's partition classification accuracy, offering potentially substantial efficiency gains. dipcensR is based on a robustness evaluation of said partition classification and flags classifications with low robustness as needing review. Additionally, dipcensR's robustness analysis underpins (optional) automatic optimization of partition classification to achieve maximal robustness. A freely available R implementation supports dipcensR's use.
{"title":"Digital PCR threshold robustness analysis and optimization using dipcensR.","authors":"Matthijs Vynck, Wim Trypsteen, Olivier Thas, Jo Vandesompele, Ward De Spiegelaere","doi":"10.1093/bib/bbae507","DOIUrl":"https://doi.org/10.1093/bib/bbae507","url":null,"abstract":"<p><p>Digital polymerase chain reaction (dPCR) is a best-in-class molecular biology technique for the accurate and precise quantification of nucleic acids. The recent maturation of dPCR technology allows the quantification of up to thousands of targeted nucleic acids per instrument per day. A key step in the dPCR data analysis workflow is the classification of partitions into two classes based on their partition intensities: partitions either containing or lacking target nucleic acids of interest. Much effort has been invested in the design and tailoring of automated dPCR partition classification procedures, and such procedures will be increasingly important as the technology ventures into high-throughput applications. However, automated partition classification is not fail-safe, and evaluation of its accuracy is highly advised. This accuracy evaluation is a manual endeavor and is becoming a bottleneck for high-throughput dPCR applications. Here, we introduce dipcensR, the first data-analysis procedure that automates the assessment of any linear partition classifier's partition classification accuracy, offering potentially substantial efficiency gains. dipcensR is based on a robustness evaluation of said partition classification and flags classifications with low robustness as needing review. Additionally, dipcensR's robustness analysis underpins (optional) automatic optimization of partition classification to achieve maximal robustness. A freely available R implementation supports dipcensR's use.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11472245/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142458371","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}
The clinical adoption of small interfering RNAs (siRNAs) has prompted the development of various computational strategies for siRNA design, from traditional data analysis to advanced machine learning techniques. However, previous studies have inadequately considered the full complexity of the siRNA silencing mechanism, neglecting critical elements such as siRNA positioning on mRNA, RNA base-pairing probabilities, and RNA-AGO2 interactions, thereby limiting the insight and accuracy of existing models. Here, we introduce siRNADiscovery, a Graph Neural Network (GNN) framework that leverages both non-empirical and empirical rule-based features of siRNA and mRNA to effectively capture the complex dynamics of gene silencing. On multiple internal datasets, siRNADiscovery achieves state-of-the-art performance. Significantly, siRNADiscovery also outperforms existing methodologies in in vitro studies and on an externally validated dataset. Additionally, we develop a new data-splitting methodology that addresses the data leakage issue, a frequently overlooked problem in previous studies, ensuring the robustness and stability of our model under various experimental settings. Through rigorous testing, siRNADiscovery has demonstrated remarkable predictive accuracy and robustness, making significant contributions to the field of gene silencing. Furthermore, our approach to redefining data-splitting standards aims to set new benchmarks for future research in the domain of predictive biological modeling for siRNA.
{"title":"siRNADiscovery: a graph neural network for siRNA efficacy prediction via deep RNA sequence analysis.","authors":"Rongzhuo Long, Ziyu Guo, Da Han, Boxiang Liu, Xudong Yuan, Guangyong Chen, Pheng-Ann Heng, Liang Zhang","doi":"10.1093/bib/bbae563","DOIUrl":"10.1093/bib/bbae563","url":null,"abstract":"<p><p>The clinical adoption of small interfering RNAs (siRNAs) has prompted the development of various computational strategies for siRNA design, from traditional data analysis to advanced machine learning techniques. However, previous studies have inadequately considered the full complexity of the siRNA silencing mechanism, neglecting critical elements such as siRNA positioning on mRNA, RNA base-pairing probabilities, and RNA-AGO2 interactions, thereby limiting the insight and accuracy of existing models. Here, we introduce siRNADiscovery, a Graph Neural Network (GNN) framework that leverages both non-empirical and empirical rule-based features of siRNA and mRNA to effectively capture the complex dynamics of gene silencing. On multiple internal datasets, siRNADiscovery achieves state-of-the-art performance. Significantly, siRNADiscovery also outperforms existing methodologies in in vitro studies and on an externally validated dataset. Additionally, we develop a new data-splitting methodology that addresses the data leakage issue, a frequently overlooked problem in previous studies, ensuring the robustness and stability of our model under various experimental settings. Through rigorous testing, siRNADiscovery has demonstrated remarkable predictive accuracy and robustness, making significant contributions to the field of gene silencing. Furthermore, our approach to redefining data-splitting standards aims to set new benchmarks for future research in the domain of predictive biological modeling for siRNA.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11539000/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142582071","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}
Despite advanced diagnostics, 3%-5% of cases remain classified as cancer of unknown primary (CUP). DNA methylation, an important epigenetic feature, is essential for determining the origin of metastatic tumors. We presented PathMethy, a novel Transformer model integrated with functional categories and crosstalk of pathways, to accurately trace the origin of tumors in CUP samples based on DNA methylation. PathMethy outperformed seven competing methods in F1-score across nine cancer datasets and predicted accurately the molecular subtypes within nine primary tumor types. It not only excelled at tracing the origins of both primary and metastatic tumors but also demonstrated a high degree of agreement with previously diagnosed sites in cases of CUP. PathMethy provided biological insights by highlighting key pathways, functional categories, and their interactions. Using functional categories of pathways, we gained a global understanding of biological processes. For broader access, a user-friendly web server for researchers and clinicians is available at https://cup.pathmethy.com.
尽管诊断手段先进,但仍有 3%-5% 的病例被归类为原发灶不明的癌症(CUP)。DNA 甲基化是一种重要的表观遗传特征,对于确定转移性肿瘤的起源至关重要。我们提出了 PathMethy,这是一种新型的 Transformer 模型,集成了功能分类和路径串联,可根据 DNA 甲基化准确追踪 CUP 样本中肿瘤的来源。在九个癌症数据集中,PathMethy 的 F1 分数超过了七种竞争方法,并准确预测了九种原发性肿瘤类型中的分子亚型。它不仅在追踪原发性肿瘤和转移性肿瘤的起源方面表现出色,而且与之前诊断出的 CUP 病例的部位高度吻合。PathMethy 通过突出关键通路、功能类别及其相互作用来提供生物学见解。通过途径的功能类别,我们对生物过程有了全面的了解。为了扩大访问范围,我们还为研究人员和临床医生提供了一个用户友好型网络服务器,网址是 https://cup.pathmethy.com。
{"title":"PathMethy: an interpretable AI framework for cancer origin tracing based on DNA methylation.","authors":"Jiajing Xie, Yuhang Song, Hailong Zheng, Shijie Luo, Ying Chen, Chen Zhang, Rongshan Yu, Mengsha Tong","doi":"10.1093/bib/bbae497","DOIUrl":"10.1093/bib/bbae497","url":null,"abstract":"<p><p>Despite advanced diagnostics, 3%-5% of cases remain classified as cancer of unknown primary (CUP). DNA methylation, an important epigenetic feature, is essential for determining the origin of metastatic tumors. We presented PathMethy, a novel Transformer model integrated with functional categories and crosstalk of pathways, to accurately trace the origin of tumors in CUP samples based on DNA methylation. PathMethy outperformed seven competing methods in F1-score across nine cancer datasets and predicted accurately the molecular subtypes within nine primary tumor types. It not only excelled at tracing the origins of both primary and metastatic tumors but also demonstrated a high degree of agreement with previously diagnosed sites in cases of CUP. PathMethy provided biological insights by highlighting key pathways, functional categories, and their interactions. Using functional categories of pathways, we gained a global understanding of biological processes. For broader access, a user-friendly web server for researchers and clinicians is available at https://cup.pathmethy.com.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11467402/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142399351","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}
Mediation analysis has been widely utilized to identify potential pathways connecting exposures and outcomes. However, there remains a lack of analytical methods for high-dimensional mediation analysis in longitudinal data. To tackle this concern, we proposed an effective and novel approach with variable selection and the indirect effect (IE) assessment based on both linear mixed-effect model and generalized estimating equation. Initially, we employ sure independence screening to reduce the dimension of candidate mediators. Subsequently, we implement the Sobel test with the Bonferroni correction for IE hypothesis testing. Through extensive simulation studies, we demonstrate the performance of our proposed procedure with a higher F$_{1}$ score (0.8056 and 0.9983 at sample sizes of 150 and 500, respectively) compared with the linear method (0.7779 and 0.9642 at the same sample sizes), along with more accurate parameter estimation and a significantly lower false discovery rate. Moreover, we apply our methodology to explore the mediation mechanisms involving over 730 000 DNA methylation sites with potential effects between the paternal body mass index (BMI) and offspring growing BMI in the Shanghai sleeping birth cohort data, leading to the identification of two previously undiscovered mediating CpG sites.
{"title":"Mediation analysis in longitudinal study with high-dimensional methylation mediators.","authors":"Yidan Cui, Qingmin Lin, Xin Yuan, Fan Jiang, Shiyang Ma, Zhangsheng Yu","doi":"10.1093/bib/bbae496","DOIUrl":"https://doi.org/10.1093/bib/bbae496","url":null,"abstract":"<p><p>Mediation analysis has been widely utilized to identify potential pathways connecting exposures and outcomes. However, there remains a lack of analytical methods for high-dimensional mediation analysis in longitudinal data. To tackle this concern, we proposed an effective and novel approach with variable selection and the indirect effect (IE) assessment based on both linear mixed-effect model and generalized estimating equation. Initially, we employ sure independence screening to reduce the dimension of candidate mediators. Subsequently, we implement the Sobel test with the Bonferroni correction for IE hypothesis testing. Through extensive simulation studies, we demonstrate the performance of our proposed procedure with a higher F$_{1}$ score (0.8056 and 0.9983 at sample sizes of 150 and 500, respectively) compared with the linear method (0.7779 and 0.9642 at the same sample sizes), along with more accurate parameter estimation and a significantly lower false discovery rate. Moreover, we apply our methodology to explore the mediation mechanisms involving over 730 000 DNA methylation sites with potential effects between the paternal body mass index (BMI) and offspring growing BMI in the Shanghai sleeping birth cohort data, leading to the identification of two previously undiscovered mediating CpG sites.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11479716/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142458376","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}
Sheng Liu, Hye Seung Nam, Ziyu Zeng, Xuehong Deng, Elnaz Pashaei, Yong Zang, Lei Yang, Chenglong Li, Jiaoti Huang, Michael K Wendt, Xin Lu, Rong Huang, Jun Wan
Prostate cancer (PCa) is the most prevalent cancer affecting American men. Castration-resistant prostate cancer (CRPC) can emerge during hormone therapy for PCa, manifesting with elevated serum prostate-specific antigen levels, continued disease progression, and/or metastasis to the new sites, resulting in a poor prognosis. A subset of CRPC patients shows a neuroendocrine (NE) phenotype, signifying reduced or no reliance on androgen receptor signaling and a particularly unfavorable prognosis. In this study, we incorporated computational approaches based on both gene expression profiles and protein-protein interaction networks. We identified 500 potential marker genes, which are significantly enriched in cell cycle and neuronal processes. The top 40 candidates, collectively named CDHu40, demonstrated superior performance in distinguishing NE PCa (NEPC) and non-NEPC samples based on gene expression profiles. CDHu40 outperformed most of the other published marker sets, excelling particularly at the prognostic level. Notably, some marker genes in CDHu40, absent in the other marker sets, have been reported to be associated with NEPC in the literature, such as DDC, FOLH1, BEX1, MAST1, and CACNA1A. Importantly, elevated CDHu40 scores derived from our predictive model showed a robust correlation with unfavorable survival outcomes in patients, indicating the potential of the CDHu40 score as a promising indicator for predicting the survival prognosis of those patients with the NE phenotype. Motif enrichment analysis on the top candidates suggests that REST and E2F6 may serve as key regulators in the NEPC progression.
{"title":"CDHu40: a novel marker gene set of neuroendocrine prostate cancer.","authors":"Sheng Liu, Hye Seung Nam, Ziyu Zeng, Xuehong Deng, Elnaz Pashaei, Yong Zang, Lei Yang, Chenglong Li, Jiaoti Huang, Michael K Wendt, Xin Lu, Rong Huang, Jun Wan","doi":"10.1093/bib/bbae471","DOIUrl":"10.1093/bib/bbae471","url":null,"abstract":"<p><p>Prostate cancer (PCa) is the most prevalent cancer affecting American men. Castration-resistant prostate cancer (CRPC) can emerge during hormone therapy for PCa, manifesting with elevated serum prostate-specific antigen levels, continued disease progression, and/or metastasis to the new sites, resulting in a poor prognosis. A subset of CRPC patients shows a neuroendocrine (NE) phenotype, signifying reduced or no reliance on androgen receptor signaling and a particularly unfavorable prognosis. In this study, we incorporated computational approaches based on both gene expression profiles and protein-protein interaction networks. We identified 500 potential marker genes, which are significantly enriched in cell cycle and neuronal processes. The top 40 candidates, collectively named CDHu40, demonstrated superior performance in distinguishing NE PCa (NEPC) and non-NEPC samples based on gene expression profiles. CDHu40 outperformed most of the other published marker sets, excelling particularly at the prognostic level. Notably, some marker genes in CDHu40, absent in the other marker sets, have been reported to be associated with NEPC in the literature, such as DDC, FOLH1, BEX1, MAST1, and CACNA1A. Importantly, elevated CDHu40 scores derived from our predictive model showed a robust correlation with unfavorable survival outcomes in patients, indicating the potential of the CDHu40 score as a promising indicator for predicting the survival prognosis of those patients with the NE phenotype. Motif enrichment analysis on the top candidates suggests that REST and E2F6 may serve as key regulators in the NEPC progression.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11422505/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142341934","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}
Junxin Li, Linbu Liao, Chao Zhang, Kaifang Huang, Pengfei Zhang, John Z H Zhang, Xiaochun Wan, Haiping Zhang
High affinity is crucial for the efficacy and specificity of antibody. Due to involving high-throughput screens, biological experiments for antibody affinity maturation are time-consuming and have a low success rate. Precise computational-assisted antibody design promises to accelerate this process, but there is still a lack of effective computational methods capable of pinpointing beneficial mutations within the complementarity-determining region (CDR) of antibodies. Moreover, random mutations often lead to challenges in antibody expression and immunogenicity. In this study, to enhance the affinity of a human antibody against avian influenza virus, a CDR library was constructed and evolutionary information was acquired through sequence alignment to restrict the mutation positions and types. Concurrently, a statistical potential methodology was developed based on amino acid interactions between antibodies and antigens to calculate potential affinity-enhanced antibodies, which were further subjected to molecular dynamics simulations. Subsequently, experimental validation confirmed that a point mutation enhancing 2.5-fold affinity was obtained from 10 designs, resulting in the antibody affinity of 2 nM. A predictive model for antibody-antigen interactions based on the binding interface was also developed, achieving an Area Under the Curve (AUC) of 0.83 and a precision of 0.89 on the test set. Lastly, a novel approach involving combinations of affinity-enhancing mutations and an iterative mutation optimization scheme similar to the Monte Carlo method were proposed. This study presents computational methods that rapidly and accurately enhance antibody affinity, addressing issues related to antibody expression and immunogenicity.
{"title":"Development and experimental validation of computational methods for human antibody affinity enhancement.","authors":"Junxin Li, Linbu Liao, Chao Zhang, Kaifang Huang, Pengfei Zhang, John Z H Zhang, Xiaochun Wan, Haiping Zhang","doi":"10.1093/bib/bbae488","DOIUrl":"10.1093/bib/bbae488","url":null,"abstract":"<p><p>High affinity is crucial for the efficacy and specificity of antibody. Due to involving high-throughput screens, biological experiments for antibody affinity maturation are time-consuming and have a low success rate. Precise computational-assisted antibody design promises to accelerate this process, but there is still a lack of effective computational methods capable of pinpointing beneficial mutations within the complementarity-determining region (CDR) of antibodies. Moreover, random mutations often lead to challenges in antibody expression and immunogenicity. In this study, to enhance the affinity of a human antibody against avian influenza virus, a CDR library was constructed and evolutionary information was acquired through sequence alignment to restrict the mutation positions and types. Concurrently, a statistical potential methodology was developed based on amino acid interactions between antibodies and antigens to calculate potential affinity-enhanced antibodies, which were further subjected to molecular dynamics simulations. Subsequently, experimental validation confirmed that a point mutation enhancing 2.5-fold affinity was obtained from 10 designs, resulting in the antibody affinity of 2 nM. A predictive model for antibody-antigen interactions based on the binding interface was also developed, achieving an Area Under the Curve (AUC) of 0.83 and a precision of 0.89 on the test set. Lastly, a novel approach involving combinations of affinity-enhancing mutations and an iterative mutation optimization scheme similar to the Monte Carlo method were proposed. This study presents computational methods that rapidly and accurately enhance antibody affinity, addressing issues related to antibody expression and immunogenicity.</p>","PeriodicalId":9209,"journal":{"name":"Briefings in bioinformatics","volume":null,"pages":null},"PeriodicalIF":6.8,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11446602/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142364431","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}