Pub Date : 2024-08-16DOI: 10.1109/TNB.2024.3444922
Xiangjin Hu;Haoran Yi;Hao Cheng;Yijing Zhao;Dongqi Zhang;Jinxin Li;Jingjing Ruan;Jin Zhang;Xinguo Lu
Computational synthetic lethality (SL) method has become a promising strategy to identify SL gene pairs for targeted cancer therapy and cancer medicine development. Feature representation for integrating various biological networks is crutial to improve the identification performance. However, previous feature representation, such as matrix factorization and graph neural network, projects gene features onto latent variables by keeping a specific geometric metric. There is a lack of models of gene representational latent space with considerating multiple dimentionalities correlation and preserving latent geometric structures in both sample and feature spaces. Therefore, we propose a novel method to model gene Latent Space using matrix Tri-Factorization (LSTF) to obtain gene representation with embedding variables resulting from the potential interpretation of synthetic lethality. Meanwhile, manifold subspace regularization is applied to the tri-factorization to capture the geometrical manifold structure in the latent space with gene PPI functional and GO semantic embeddings. Then, SL gene pairs are identified by the reconstruction of the associations with gene representations in the latent space. The experimental results illustrate that LSTF is superior to other state-of-the-art methods. Case study demonstrate the effectiveness of the predicted SL associations.
计算合成致死率（SL）方法已成为为癌症靶向治疗和癌症药物开发识别SL基因对的一种有前途的策略。整合各种生物网络的特征表示对于提高识别性能至关重要。然而，以往的特征表示方法，如矩阵因式分解和图神经网络，都是通过保持特定的几何度量将基因特征投射到潜在变量上。目前还缺乏同时考虑多维度相关性和保留样本空间与特征空间中潜在几何结构的基因表征潜在空间模型。因此，我们提出了一种利用矩阵三因子化（LSTF）对基因潜空间进行建模的新方法，以获得具有合成致死率潜在解释所产生的嵌入变量的基因表征。同时，将流形子空间正则化应用于三因子化，以捕捉潜空间中带有基因 PPI 功能嵌入和 GO 语义嵌入的几何流形结构。然后，通过重建潜空间中与基因表征的关联来识别 SL 基因对。实验结果表明，LSTF 优于其他最先进的方法。案例研究证明了预测 SL 关联的有效性。
{"title":"Multiple Heterogeneous Networks Representation With Latent Space for Synthetic Lethality Prediction","authors":"Xiangjin Hu;Haoran Yi;Hao Cheng;Yijing Zhao;Dongqi Zhang;Jinxin Li;Jingjing Ruan;Jin Zhang;Xinguo Lu","doi":"10.1109/TNB.2024.3444922","DOIUrl":"10.1109/TNB.2024.3444922","url":null,"abstract":"Computational synthetic lethality (SL) method has become a promising strategy to identify SL gene pairs for targeted cancer therapy and cancer medicine development. Feature representation for integrating various biological networks is crutial to improve the identification performance. However, previous feature representation, such as matrix factorization and graph neural network, projects gene features onto latent variables by keeping a specific geometric metric. There is a lack of models of gene representational latent space with considerating multiple dimentionalities correlation and preserving latent geometric structures in both sample and feature spaces. Therefore, we propose a novel method to model gene Latent Space using matrix Tri-Factorization (LSTF) to obtain gene representation with embedding variables resulting from the potential interpretation of synthetic lethality. Meanwhile, manifold subspace regularization is applied to the tri-factorization to capture the geometrical manifold structure in the latent space with gene PPI functional and GO semantic embeddings. Then, SL gene pairs are identified by the reconstruction of the associations with gene representations in the latent space. The experimental results illustrate that LSTF is superior to other state-of-the-art methods. Case study demonstrate the effectiveness of the predicted SL associations.","PeriodicalId":13264,"journal":{"name":"IEEE Transactions on NanoBioscience","volume":"23 4","pages":"564-571"},"PeriodicalIF":3.7,"publicationDate":"2024-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141992287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-14DOI: 10.1109/TNB.2024.3443244
Wenjie Yao;Ankang Wei;Zhen Xiao;Weizhong Zhao;Xianjun Shen;Xingpeng Jiang;Tingting He
Detecting side effects of drugs is a fundamental task in drug development. With the expansion of publicly available biomedical data, researchers have proposed many computational methods for predicting drug-side effect associations (DSAs), among which network-based methods attract wide attention in the biomedical field. However, the problem of data scarcity poses a great challenge for existing DSAs prediction models. Although several data augmentation methods have been proposed to address this issue, most of existing methods employ a random way to manipulate the original networks, which ignores the causality of existence of DSAs, leading to the poor performance on the task of DSAs prediction. In this paper, we propose a counterfactual inference-based data augmentation method for improving the performance of the task. First, we construct a heterogeneous information network (HIN) by integrating multiple biomedical data. Based on the community detection on the HIN, a counterfactual inference-based method is designed to derive augmented links, and an augmented HIN is obtained accordingly. Then, a meta-path-based graph neural network is applied to learn high-quality representations of drugs and side effects, on which the predicted DSAs are obtained. Finally, comprehensive experiments are conducted, and the results demonstrate the effectiveness of the proposed counterfactual inference-based data augmentation for the task of DSAs prediction.
{"title":"An Improved Framework for Drug-Side Effect Associations Prediction via Counterfactual Inference-Based Data Augmentation","authors":"Wenjie Yao;Ankang Wei;Zhen Xiao;Weizhong Zhao;Xianjun Shen;Xingpeng Jiang;Tingting He","doi":"10.1109/TNB.2024.3443244","DOIUrl":"10.1109/TNB.2024.3443244","url":null,"abstract":"Detecting side effects of drugs is a fundamental task in drug development. With the expansion of publicly available biomedical data, researchers have proposed many computational methods for predicting drug-side effect associations (DSAs), among which network-based methods attract wide attention in the biomedical field. However, the problem of data scarcity poses a great challenge for existing DSAs prediction models. Although several data augmentation methods have been proposed to address this issue, most of existing methods employ a random way to manipulate the original networks, which ignores the causality of existence of DSAs, leading to the poor performance on the task of DSAs prediction. In this paper, we propose a counterfactual inference-based data augmentation method for improving the performance of the task. First, we construct a heterogeneous information network (HIN) by integrating multiple biomedical data. Based on the community detection on the HIN, a counterfactual inference-based method is designed to derive augmented links, and an augmented HIN is obtained accordingly. Then, a meta-path-based graph neural network is applied to learn high-quality representations of drugs and side effects, on which the predicted DSAs are obtained. Finally, comprehensive experiments are conducted, and the results demonstrate the effectiveness of the proposed counterfactual inference-based data augmentation for the task of DSAs prediction.","PeriodicalId":13264,"journal":{"name":"IEEE Transactions on NanoBioscience","volume":"23 4","pages":"540-547"},"PeriodicalIF":3.7,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141982181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-13DOI: 10.1109/TNB.2024.3442912
Ghazaleh Babanejaddehaki;Aijun An;Heidar Davoudi
Given the persistent global challenge presented by rapidly spreading diseases, as evidenced notably by the widespread impact of the COVID-19 pandemic on both human health and economies worldwide, the necessity of developing effective infectious disease prediction models has become of utmost importance. In this context, the utilization of online social media platforms as valuable tools in healthcare settings has gained prominence, offering direct avenues for disseminating critical health information to the public in a timely and accessible manner. Propelled by the ubiquitous accessibility of the internet through computers and mobile devices, these platforms promise to revolutionize traditional detection methods, providing more immediate and reliable epidemiological insights. Leveraging this paradigm shift, our proposed framework harnesses Twitter data associated with infectious disease symptoms, employing ontology to identify and curate relevant tweets. Central to our methodology is a hybrid model that integrates XGBoost and Bidirectional Long Short-Term Memory (BiLSTM) architectures. The integration of XGBoost addresses the challenge of handling small dataset sizes, inherent during outbreaks due to limited time series data. XGBoost serves as a cornerstone for minimizing the loss function and identifying optimal features from our multivariate time series data. Subsequently, the combined dataset, comprising original features and predicted values by XGBoost, is channeled into the BiLSTM for further processing. Through extensive experimentation with a dataset spanning multiple infectious disease outbreaks, our hybrid model demonstrates superior predictive performance compared to state-of-the-art and baseline models. By enhancing forecasting accuracy and outbreak tracking capabilities, our model offers promising prospects for assisting health authorities in mitigating fatalities and proactively preparing for potential outbreaks.
{"title":"Ontology-Based Data Collection for a Hybrid Outbreak Detection Method Using Social Media","authors":"Ghazaleh Babanejaddehaki;Aijun An;Heidar Davoudi","doi":"10.1109/TNB.2024.3442912","DOIUrl":"10.1109/TNB.2024.3442912","url":null,"abstract":"Given the persistent global challenge presented by rapidly spreading diseases, as evidenced notably by the widespread impact of the COVID-19 pandemic on both human health and economies worldwide, the necessity of developing effective infectious disease prediction models has become of utmost importance. In this context, the utilization of online social media platforms as valuable tools in healthcare settings has gained prominence, offering direct avenues for disseminating critical health information to the public in a timely and accessible manner. Propelled by the ubiquitous accessibility of the internet through computers and mobile devices, these platforms promise to revolutionize traditional detection methods, providing more immediate and reliable epidemiological insights. Leveraging this paradigm shift, our proposed framework harnesses Twitter data associated with infectious disease symptoms, employing ontology to identify and curate relevant tweets. Central to our methodology is a hybrid model that integrates XGBoost and Bidirectional Long Short-Term Memory (BiLSTM) architectures. The integration of XGBoost addresses the challenge of handling small dataset sizes, inherent during outbreaks due to limited time series data. XGBoost serves as a cornerstone for minimizing the loss function and identifying optimal features from our multivariate time series data. Subsequently, the combined dataset, comprising original features and predicted values by XGBoost, is channeled into the BiLSTM for further processing. Through extensive experimentation with a dataset spanning multiple infectious disease outbreaks, our hybrid model demonstrates superior predictive performance compared to state-of-the-art and baseline models. By enhancing forecasting accuracy and outbreak tracking capabilities, our model offers promising prospects for assisting health authorities in mitigating fatalities and proactively preparing for potential outbreaks.","PeriodicalId":13264,"journal":{"name":"IEEE Transactions on NanoBioscience","volume":"23 4","pages":"591-602"},"PeriodicalIF":3.7,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141975609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-12DOI: 10.1109/TNB.2024.3441689
Yan Wang;Jie Hong;Yuting Lu;Nan Sheng;Yuan Fu;Lili Yang;Lingyu Meng;Lan Huang;Hao Wang
Pancreatic cancer is one of the most malignant cancers with rapid progression and poor prognosis. The use of transcriptional data can be effective in finding new biomarkers for pancreatic cancer. Many network-based methods used to identify cancer biomarkers are proposed, among which the combination of network controllability appears. However, most of the existing methods do not study RNA, rely on priori and mutations information, or can only achieve classification tasks. In this study, we propose a method combined Relational Graph Convolutional Network and Deep Q-Network called RDDriver to identify pancreatic cancer biomarkers based on multi-layer heterogeneous transcriptional regulation network. Firstly, we construct a regulation network containing long non-coding RNA, microRNA, and messenger RNA. Secondly, Relational Graph Convolutional Network is used to learn the node representation. Finally, we use the idea of Deep Q-Network to build a model, which score and prioritize each RNA with the Popov-Belevitch-Hautus criterion. We train RDDriver on three small simulated networks, and calculate the average score after applying the model parameters to the regulation networks separately. To demonstrate the effectiveness of the method, we perform experiments for comparison between RDDriver and other eight methods based on the approximate benchmark of three types cancer drivers RNAs.
{"title":"A Controllability Reinforcement Learning Method for Pancreatic Cancer Biomarker Identification","authors":"Yan Wang;Jie Hong;Yuting Lu;Nan Sheng;Yuan Fu;Lili Yang;Lingyu Meng;Lan Huang;Hao Wang","doi":"10.1109/TNB.2024.3441689","DOIUrl":"10.1109/TNB.2024.3441689","url":null,"abstract":"Pancreatic cancer is one of the most malignant cancers with rapid progression and poor prognosis. The use of transcriptional data can be effective in finding new biomarkers for pancreatic cancer. Many network-based methods used to identify cancer biomarkers are proposed, among which the combination of network controllability appears. However, most of the existing methods do not study RNA, rely on priori and mutations information, or can only achieve classification tasks. In this study, we propose a method combined Relational Graph Convolutional Network and Deep Q-Network called RDDriver to identify pancreatic cancer biomarkers based on multi-layer heterogeneous transcriptional regulation network. Firstly, we construct a regulation network containing long non-coding RNA, microRNA, and messenger RNA. Secondly, Relational Graph Convolutional Network is used to learn the node representation. Finally, we use the idea of Deep Q-Network to build a model, which score and prioritize each RNA with the Popov-Belevitch-Hautus criterion. We train RDDriver on three small simulated networks, and calculate the average score after applying the model parameters to the regulation networks separately. To demonstrate the effectiveness of the method, we perform experiments for comparison between RDDriver and other eight methods based on the approximate benchmark of three types cancer drivers RNAs.","PeriodicalId":13264,"journal":{"name":"IEEE Transactions on NanoBioscience","volume":"23 4","pages":"556-563"},"PeriodicalIF":3.7,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10633729","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141971020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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 : 2024-08-12DOI: 10.1109/TNB.2024.3441590
Xiwei Tang;Yiqiang Zhou;Mengyun Yang;Wenjun Li
Bioinformatics is a rapidly evolving field that applies computational methods to analyze and interpret biological data. A key task in bioinformatics is identifying novel drug-target interactions (DTIs), which plays a crucial role in drug discovery. Most computational approaches treat DTI prediction as a binary classification problem, determining whether drug-target pairs interact. However, with the growing availability of drug-target binding affinity data, this binary task can be reframed as a regression problem focused on drug-target affinity (DTA). DTA quantifies the strength of drug-target binding, offering more detailed insights than DTI and serving as a valuable tool for virtual screening in drug discovery. Accurately predicting compound interactions with targets can accelerate the drug development process. In this study, we introduce a deep learning model named TC-DTA for DTA prediction, leveraging convolutional neural networks (CNN) and the encoder module of the transformer architecture. We begin by extracting raw drug SMILES strings and protein amino acid sequences from the dataset, which are then represented using various encoding methods. Subsequently, we employ CNN and the transformer’s encoder module to extract features from the drug SMILES strings and protein sequences, respectively. Finally, the feature information is concatenated and input into a multi-layer perceptron to predict binding affinity scores. We evaluated our model on two benchmark DTA datasets, Davis and KIBA, comparing it with methods such as KronRLS, SimBoost, and DeepDTA. Our model, TC-DTA, outperformed these baseline methods based on evaluation metrics like Mean Squared Error (MSE), Concordance Index (CI), and Regression towards the Mean Index ( ${r}_{m}^{{2}}$ ). These results highlight the effectiveness of the Transformer’s encoder and CNN in extracting meaningful representations from sequences, thereby enhancing DTA prediction accuracy. This deep learning model can accelerate drug discovery by identifying drug candidates with high binding affinity to specific targets. Compared to traditional methods, machine learning technology offers a more effective and efficient approach to drug discovery.
{"title":"TC-DTA: Predicting Drug-Target Binding Affinity With Transformer and Convolutional Neural Networks","authors":"Xiwei Tang;Yiqiang Zhou;Mengyun Yang;Wenjun Li","doi":"10.1109/TNB.2024.3441590","DOIUrl":"10.1109/TNB.2024.3441590","url":null,"abstract":"Bioinformatics is a rapidly evolving field that applies computational methods to analyze and interpret biological data. A key task in bioinformatics is identifying novel drug-target interactions (DTIs), which plays a crucial role in drug discovery. Most computational approaches treat DTI prediction as a binary classification problem, determining whether drug-target pairs interact. However, with the growing availability of drug-target binding affinity data, this binary task can be reframed as a regression problem focused on drug-target affinity (DTA). DTA quantifies the strength of drug-target binding, offering more detailed insights than DTI and serving as a valuable tool for virtual screening in drug discovery. Accurately predicting compound interactions with targets can accelerate the drug development process. In this study, we introduce a deep learning model named TC-DTA for DTA prediction, leveraging convolutional neural networks (CNN) and the encoder module of the transformer architecture. We begin by extracting raw drug SMILES strings and protein amino acid sequences from the dataset, which are then represented using various encoding methods. Subsequently, we employ CNN and the transformer’s encoder module to extract features from the drug SMILES strings and protein sequences, respectively. Finally, the feature information is concatenated and input into a multi-layer perceptron to predict binding affinity scores. We evaluated our model on two benchmark DTA datasets, Davis and KIBA, comparing it with methods such as KronRLS, SimBoost, and DeepDTA. Our model, TC-DTA, outperformed these baseline methods based on evaluation metrics like Mean Squared Error (MSE), Concordance Index (CI), and Regression towards the Mean Index (\u0000<inline-formula> <tex-math>${r}_{m}^{{2}}$ </tex-math></inline-formula>\u0000). These results highlight the effectiveness of the Transformer’s encoder and CNN in extracting meaningful representations from sequences, thereby enhancing DTA prediction accuracy. This deep learning model can accelerate drug discovery by identifying drug candidates with high binding affinity to specific targets. Compared to traditional methods, machine learning technology offers a more effective and efficient approach to drug discovery.","PeriodicalId":13264,"journal":{"name":"IEEE Transactions on NanoBioscience","volume":"23 4","pages":"572-578"},"PeriodicalIF":3.7,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141971022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-12DOI: 10.1109/TNB.2024.3441533
Hailin Yue;Jin Liu;Lina Zhao;Hulin Kuang;Jianhong Cheng;Junjian Li;Mengshen He;Jie Gong;Jianxin Wang
Esophageal cancer is a common malignant tumor, precisely predicting survival of esophageal cancer is crucial for personalized treatment. However, current region of interest (ROI) based methodologies not only necessitate prior medical knowledge for tumor delineation, but may also cause the model to be overly sensitive to ROI. To address these challenges, we develop an automated Hybrid Transformer based learning that integrates a Hybrid Transformer size-aware U-Net with a ranked survival prediction network to enable automatic survival prediction for esophageal cancer. Specifically, we first incorporate the Transformer with shifted windowing multi-head self-attention mechanism (SW-MSA) into the base of the U-Net encoder to capture the long-range dependency in CT images. Furthermore, to alleviate the imbalance between the ROI and the background in CT images, we devise a size-aware coefficient for the segmentation loss. Finally, we also design a ranked pair sorting loss to more comprehensively capture the ranked information inherent in CT images. We evaluate our proposed method on a dataset comprising 759 samples with esophageal cancer. Experimental results demonstrate the superior performance of our proposed method in survival prediction, even without ROI ground truth.
食管癌是一种常见的恶性肿瘤，精确预测食管癌的生存率对个性化治疗至关重要。然而，目前基于兴趣区域（ROI）的方法不仅需要事先掌握肿瘤划分的医学知识，还可能导致模型对 ROI 过度敏感。为了应对这些挑战，我们开发了一种基于混合变形器的自动学习方法，它将混合变形器尺寸感知 U-Net 与排序生存预测网络整合在一起，实现了食管癌的自动生存预测。具体来说，我们首先在 UNet 编码器的基础上加入了带有移位窗口多头自关注机制（SW-MSA）的变换器，以捕捉 CT 图像中的长程依赖性。此外，为了缓解 CT 图像中 ROI 与背景之间的不平衡，我们设计了一个尺寸感知系数来计算分割损失。最后，我们还设计了排序对排序损失，以更全面地捕捉 CT 图像中固有的排序信息。我们在由 759 个食道癌样本组成的数据集上评估了我们提出的方法。实验结果表明，即使在没有 ROI 地面实况的情况下，我们提出的方法在生存预测方面也表现出色。
{"title":"A2HTL: An Automated Hybrid Transformer-Based Learning for Predicting Survival of Esophageal Cancer Using CT Images","authors":"Hailin Yue;Jin Liu;Lina Zhao;Hulin Kuang;Jianhong Cheng;Junjian Li;Mengshen He;Jie Gong;Jianxin Wang","doi":"10.1109/TNB.2024.3441533","DOIUrl":"10.1109/TNB.2024.3441533","url":null,"abstract":"Esophageal cancer is a common malignant tumor, precisely predicting survival of esophageal cancer is crucial for personalized treatment. However, current region of interest (ROI) based methodologies not only necessitate prior medical knowledge for tumor delineation, but may also cause the model to be overly sensitive to ROI. To address these challenges, we develop an automated Hybrid Transformer based learning that integrates a Hybrid Transformer size-aware U-Net with a ranked survival prediction network to enable automatic survival prediction for esophageal cancer. Specifically, we first incorporate the Transformer with shifted windowing multi-head self-attention mechanism (SW-MSA) into the base of the U-Net encoder to capture the long-range dependency in CT images. Furthermore, to alleviate the imbalance between the ROI and the background in CT images, we devise a size-aware coefficient for the segmentation loss. Finally, we also design a ranked pair sorting loss to more comprehensively capture the ranked information inherent in CT images. We evaluate our proposed method on a dataset comprising 759 samples with esophageal cancer. Experimental results demonstrate the superior performance of our proposed method in survival prediction, even without ROI ground truth.","PeriodicalId":13264,"journal":{"name":"IEEE Transactions on NanoBioscience","volume":"23 4","pages":"548-555"},"PeriodicalIF":3.7,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141971021","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-07DOI: 10.1109/TNB.2024.3436022
Kathan S. Joshi;Dhaval K. Patel;Shivam Thakker;Miguel López-Benítez;Janne J. Lehtomäki
Molecular communication via diffusion (MCvD) expects Brownian motions of the information molecules to transmit information. However, the signal propagation largely depends on the geometric characteristics of the assumed flow model, i.e., the characteristics of the environment, design, and position of the transmitter and receiver, respectively. These characteristics are assumed to be lucid in many ways by either consideration of one-dimensional diffusion, unbounded environment, or constant drift. In reality, diffusion often occurs in blood-vessel-like channels. To this aim, we try to study the effect of the biological environment on channel performance. The Red-Blood Cells (RBCs) found in blood vessels enforces a higher concentration of molecules towards the vessel walls, leading to better reception. Therefore, in this paper we derive an analytical expression of Channel Impulse Response (CIR) for a dispersion-advection-based regime, contemplating the influence of RBCs in the model and considering a point source transmitter and a realistic design of the receiver.
{"title":"Influence of Red Blood Cells on Channel Characterization in Cylindrical Vasculature","authors":"Kathan S. Joshi;Dhaval K. Patel;Shivam Thakker;Miguel López-Benítez;Janne J. Lehtomäki","doi":"10.1109/TNB.2024.3436022","DOIUrl":"10.1109/TNB.2024.3436022","url":null,"abstract":"Molecular communication via diffusion (MCvD) expects Brownian motions of the information molecules to transmit information. However, the signal propagation largely depends on the geometric characteristics of the assumed flow model, i.e., the characteristics of the environment, design, and position of the transmitter and receiver, respectively. These characteristics are assumed to be lucid in many ways by either consideration of one-dimensional diffusion, unbounded environment, or constant drift. In reality, diffusion often occurs in blood-vessel-like channels. To this aim, we try to study the effect of the biological environment on channel performance. The Red-Blood Cells (RBCs) found in blood vessels enforces a higher concentration of molecules towards the vessel walls, leading to better reception. Therefore, in this paper we derive an analytical expression of Channel Impulse Response (CIR) for a dispersion-advection-based regime, contemplating the influence of RBCs in the model and considering a point source transmitter and a realistic design of the receiver.","PeriodicalId":13264,"journal":{"name":"IEEE Transactions on NanoBioscience","volume":"24 1","pages":"113-119"},"PeriodicalIF":3.7,"publicationDate":"2024-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141901589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-17DOI: 10.1109/TNB.2024.3426291
Ghaleb A. Husseini;Rana Sabouni;Vladimir Puzyrev;Mehdi Ghommem
The need to mitigate the adverse effects of chemotherapy has driven the exploration of innovative drug delivery approaches. One emerging trend in cancer treatment is the utilization of Drug Delivery Systems (DDSs), facilitated by nanotechnology. Nanoparticles, ranging from 1 nm to 1000 nm, act as carriers for chemotherapeutic agents, enabling precise drug delivery. The triggered release of these agents is vital for advancing this novel drug delivery system. Our research investigated this multifaceted delivery capability using liposomes and metal organic frameworks as nanocarriers and utilizing all three targeting techniques: passive, active, and triggered. Liposomes are modified using targeting ligands to render them more targeted toward certain cancers. Moieties are conjugated to the surfaces of these nanocarriers to allow for their binding to receptors overexpressed on cancer cells, thus increasing the accumulation of the agent at the tumor site. A novel class of nanocarriers, namely metal organic frameworks, has emerged, showing promise in cancer treatment. Triggering techniques (both intrinsic and extrinsic) can be used to release therapeutic agents from nanoparticles, thus enhancing the efficacy of drug delivery. In this study, we develop a predictive model combining experimental measurements with deep learning techniques. The model accurately predicts drug release from liposomes and MOFs under various conditions, including low- and high-frequency ultrasound (extrinsic triggering), microwave exposure (extrinsic triggering), ultraviolet light exposure (extrinsic triggering), and different pH levels (intrinsic triggering). The deep learning-based predictions significantly outperform linear predictions, proving the utility of advanced computational methods in drug delivery. Our findings demonstrate the potential of these nanocarriers and highlight the efficacy of deep learning models in predicting drug release behavior, paving the way for enhanced cancer treatment strategies.
{"title":"Deep Learning for the Accurate Prediction of Triggered Drug Delivery","authors":"Ghaleb A. Husseini;Rana Sabouni;Vladimir Puzyrev;Mehdi Ghommem","doi":"10.1109/TNB.2024.3426291","DOIUrl":"10.1109/TNB.2024.3426291","url":null,"abstract":"The need to mitigate the adverse effects of chemotherapy has driven the exploration of innovative drug delivery approaches. One emerging trend in cancer treatment is the utilization of Drug Delivery Systems (DDSs), facilitated by nanotechnology. Nanoparticles, ranging from 1 nm to 1000 nm, act as carriers for chemotherapeutic agents, enabling precise drug delivery. The triggered release of these agents is vital for advancing this novel drug delivery system. Our research investigated this multifaceted delivery capability using liposomes and metal organic frameworks as nanocarriers and utilizing all three targeting techniques: passive, active, and triggered. Liposomes are modified using targeting ligands to render them more targeted toward certain cancers. Moieties are conjugated to the surfaces of these nanocarriers to allow for their binding to receptors overexpressed on cancer cells, thus increasing the accumulation of the agent at the tumor site. A novel class of nanocarriers, namely metal organic frameworks, has emerged, showing promise in cancer treatment. Triggering techniques (both intrinsic and extrinsic) can be used to release therapeutic agents from nanoparticles, thus enhancing the efficacy of drug delivery. In this study, we develop a predictive model combining experimental measurements with deep learning techniques. The model accurately predicts drug release from liposomes and MOFs under various conditions, including low- and high-frequency ultrasound (extrinsic triggering), microwave exposure (extrinsic triggering), ultraviolet light exposure (extrinsic triggering), and different pH levels (intrinsic triggering). The deep learning-based predictions significantly outperform linear predictions, proving the utility of advanced computational methods in drug delivery. Our findings demonstrate the potential of these nanocarriers and highlight the efficacy of deep learning models in predicting drug release behavior, paving the way for enhanced cancer treatment strategies.","PeriodicalId":13264,"journal":{"name":"IEEE Transactions on NanoBioscience","volume":"24 1","pages":"102-112"},"PeriodicalIF":3.7,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10601231","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141633393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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 : 2024-07-08DOI: 10.1109/TNB.2024.3424576
Yitong Ma;Shuai Chen;Qi Xu;Zuhong Lu;Kun Bi
Traditional DNA storage technologies rely on passive filtering methods for error correction during synthesis and sequencing, which result in redundancy and inadequate error correction. Addressing this, the Low Quality Sequence Filter (LQSF) was introduced, an innovative method employing deep learning models to predict high-risk sequences. The LQSF approach leverages a classification model trained on error-prone sequences, enabling efficient pre-sequencing filtration of low-quality sequences and reducing time and resources in subsequent stages. Analysis has demonstrated a clear distinction between high and low-quality sequences, confirming the efficacy of the LQSF method. Extensive training and testing were conducted across various neural networks and test sets. The results showed all models achieving an AUC value above 0.91 on ROC curves and over 0.95 on PR curves across different datasets. Notably, models such as Alexnet, VGG16, and VGG19 achieved a perfect AUC of 1.0 on the Original dataset, highlighting their precision in classification. Further validation using Illumina sequencing data substantiated a strong correlation between model scores and sequence error-proneness, emphasizing the model’s applicability. The LQSF method marks a significant advancement in DNA storage technology, introducing active sequence filtering at the encoding stage. This pioneering approach holds substantial promise for future DNA storage research and applications.
传统的 DNA 存储技术依赖被动过滤方法在合成和测序过程中进行纠错，这导致了冗余和不充分的纠错。针对这一问题，推出了低质量序列过滤器（LQSF），这是一种采用深度学习模型预测高风险序列的创新方法。LQSF 方法利用在易出错序列上训练的分类模型，实现了对低质量序列的高效预序列过滤，减少了后续阶段的时间和资源。分析表明，高质量和低质量序列之间有明显的区别，证实了 LQSF 方法的有效性。对各种神经网络和测试集进行了广泛的训练和测试。结果显示，在不同数据集上，所有模型的 ROC 曲线 AUC 值均超过 0.91，PR 曲线 AUC 值均超过 0.95。值得注意的是，Alexnet、VGG16 和 VGG19 等模型在原始数据集上的 AUC 值达到了完美的 1.0，突出了它们的分类精度。使用 Illumina 测序数据进行的进一步验证证实了模型得分与序列错误率之间的强相关性，强调了模型的适用性。LQSF 方法标志着 DNA 储存技术的重大进步，它在编码阶段引入了主动序列过滤技术。这种开创性的方法为未来的 DNA 存储研究和应用带来了巨大的希望。
{"title":"High-Risk Sequence Prediction Model in DNA Storage: The LQSF Method","authors":"Yitong Ma;Shuai Chen;Qi Xu;Zuhong Lu;Kun Bi","doi":"10.1109/TNB.2024.3424576","DOIUrl":"10.1109/TNB.2024.3424576","url":null,"abstract":"Traditional DNA storage technologies rely on passive filtering methods for error correction during synthesis and sequencing, which result in redundancy and inadequate error correction. Addressing this, the Low Quality Sequence Filter (LQSF) was introduced, an innovative method employing deep learning models to predict high-risk sequences. The LQSF approach leverages a classification model trained on error-prone sequences, enabling efficient pre-sequencing filtration of low-quality sequences and reducing time and resources in subsequent stages. Analysis has demonstrated a clear distinction between high and low-quality sequences, confirming the efficacy of the LQSF method. Extensive training and testing were conducted across various neural networks and test sets. The results showed all models achieving an AUC value above 0.91 on ROC curves and over 0.95 on PR curves across different datasets. Notably, models such as Alexnet, VGG16, and VGG19 achieved a perfect AUC of 1.0 on the Original dataset, highlighting their precision in classification. Further validation using Illumina sequencing data substantiated a strong correlation between model scores and sequence error-proneness, emphasizing the model’s applicability. The LQSF method marks a significant advancement in DNA storage technology, introducing active sequence filtering at the encoding stage. This pioneering approach holds substantial promise for future DNA storage research and applications.","PeriodicalId":13264,"journal":{"name":"IEEE Transactions on NanoBioscience","volume":"24 1","pages":"89-101"},"PeriodicalIF":3.7,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141558613","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-04DOI: 10.1109/TNB.2024.3423020
Parvathy Nair;Khairunnisa Amreen;R. N. Ponnalagu;Sanket Goel
The identification of biomarkers has significant benefits for early disease diagnosis and treatment. Hence, there is an increasing demand for low-cost, disposable point-of-care diagnostic devices for rapid and specific biomarker detection, with good sensitivity and range. Interdigitated electrodes (IDEs) are among the most widely used transducers, especially in chemical and biological sensors, because of their high sensitivity, low cost, and straightforward manufacturing procedure. In this work, a simple 3D printed IDE structure has been developed for cardiac troponin I detection to indicate the risk of acute myocardial infarction (AMI). IDEs have been fabricated using 3D printing technique and the electrically conductive composite polylactic acid (PLA) filament being utilized for the fabrication of electrodes. The demonstrated cardiac troponin I sensor has a calculated quantification limit and detection limit of 0.233 ng ml $^{mathbf {-{1}}}$ and 76.97 pg ml $^{mathbf {-{1}}}$ , respectively which are clinically significant ranges for AMI identification. Electrochemical analytical techniques, such as electrochemical impedance spectroscopy (EIS) and cyclic voltammetry (CV), were carried out for the detection of analyte concentration. Furthermore, using this fabrication methodology IDEs can be fabricated for under US 0.4 which can be utilized to detect several other biomarkers.
生物标记物的鉴定对疾病的早期诊断和治疗有重大好处。因此，对快速、特异、灵敏度高、范围广的生物标记物检测所需的低成本、一次性护理点诊断设备的需求与日俱增。插入式电极（IDE）因其灵敏度高、成本低和制造过程简单而成为应用最广泛的传感器之一，尤其是在化学和生物传感器中。在这项工作中，开发了一种简单的三维打印 IDE 结构，用于检测心肌肌钙蛋白 I，以提示急性心肌梗死（AMI）的风险。IDE 采用三维打印技术制造，电极的制造使用了导电复合材料聚乳酸（PLA）长丝。经计算，该心肌肌钙蛋白 I 传感器的定量限和检测限分别为 0.233 纳克/毫升-1 和 76.97 皮克/毫升-1，这两个数值对于急性心肌梗死的鉴定具有重要的临床意义。为检测分析物浓度，还采用了电化学阻抗光谱法（EIS）和循环伏安法（CV）等电化学分析技术。此外，利用这种制造方法可以制造出 IDE，价格低于 0.4 美元，可用于检测其他几种生物标记物。
{"title":"3D Printed Interdigitated Electrodes for Cardiac Biomarker Detection","authors":"Parvathy Nair;Khairunnisa Amreen;R. N. Ponnalagu;Sanket Goel","doi":"10.1109/TNB.2024.3423020","DOIUrl":"10.1109/TNB.2024.3423020","url":null,"abstract":"The identification of biomarkers has significant benefits for early disease diagnosis and treatment. Hence, there is an increasing demand for low-cost, disposable point-of-care diagnostic devices for rapid and specific biomarker detection, with good sensitivity and range. Interdigitated electrodes (IDEs) are among the most widely used transducers, especially in chemical and biological sensors, because of their high sensitivity, low cost, and straightforward manufacturing procedure. In this work, a simple 3D printed IDE structure has been developed for cardiac troponin I detection to indicate the risk of acute myocardial infarction (AMI). IDEs have been fabricated using 3D printing technique and the electrically conductive composite polylactic acid (PLA) filament being utilized for the fabrication of electrodes. The demonstrated cardiac troponin I sensor has a calculated quantification limit and detection limit of 0.233 ng ml\u0000<inline-formula> <tex-math>$^{mathbf {-{1}}}$ </tex-math></inline-formula>\u0000 and 76.97 pg ml\u0000<inline-formula> <tex-math>$^{mathbf {-{1}}}$ </tex-math></inline-formula>\u0000, respectively which are clinically significant ranges for AMI identification. Electrochemical analytical techniques, such as electrochemical impedance spectroscopy (EIS) and cyclic voltammetry (CV), were carried out for the detection of analyte concentration. Furthermore, using this fabrication methodology IDEs can be fabricated for under US 0.4 which can be utilized to detect several other biomarkers.","PeriodicalId":13264,"journal":{"name":"IEEE Transactions on NanoBioscience","volume":"24 1","pages":"63-69"},"PeriodicalIF":3.7,"publicationDate":"2024-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141534287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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：