Pub Date : 2021-10-13DOI: 10.1109/CIBCB49929.2021.9562890
Surbhi Gupta, Manoj Gupta
Cancer is one of the most significant causes of death worldwide, accounting for millions of deaths each year. The fatality rate of cancer is getting higher. Over the last three decades, deep neural networks have been critical in cancer research. This article described the development of a system for fully automated segmentation of brain tumor. In this study, we have proposed a unique ensemble of Convolutional Neural Networks (ConvNet) for segmenting gliomas from MR images. Two fully linked ConvNets constituted the ensemble model (2D-ConvNet and 3-D ConvNet). The novel model is validated against a single dataset from the Brain Tumor Segmentation (BraTS) challenge, specifically BraTS_2018. The prediction results obtained using the proposed methodology on the BraTS_2018 datasets demonstrate the suggested architecture's efficiency.
{"title":"Deep Learning for Brain Tumor Segmentation using Magnetic Resonance Images","authors":"Surbhi Gupta, Manoj Gupta","doi":"10.1109/CIBCB49929.2021.9562890","DOIUrl":"https://doi.org/10.1109/CIBCB49929.2021.9562890","url":null,"abstract":"Cancer is one of the most significant causes of death worldwide, accounting for millions of deaths each year. The fatality rate of cancer is getting higher. Over the last three decades, deep neural networks have been critical in cancer research. This article described the development of a system for fully automated segmentation of brain tumor. In this study, we have proposed a unique ensemble of Convolutional Neural Networks (ConvNet) for segmenting gliomas from MR images. Two fully linked ConvNets constituted the ensemble model (2D-ConvNet and 3-D ConvNet). The novel model is validated against a single dataset from the Brain Tumor Segmentation (BraTS) challenge, specifically BraTS_2018. The prediction results obtained using the proposed methodology on the BraTS_2018 datasets demonstrate the suggested architecture's efficiency.","PeriodicalId":163387,"journal":{"name":"2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128121856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-13DOI: 10.1109/CIBCB49929.2021.9562949
Sheriff Abouchekeir, A. Tchagang, Yifeng Li
The design of a new therapeutic agent is a time-consuming and expensive process. The rise of machine intelligence provides a grand opportunity of expeditiously discovering novel drug candidates through smart search in the vast molecular structural space. In this paper, we propose a new approach called adversarial deep evolutionary learning (ADEL) to search for novel molecules in the latent space of an adversarial generative model and keep improving the latent representation space. In ADEL, a custom-made adversarial autoencoder (AAE) model is developed and trained under a deep evolutionary learning (DEL) process. This involves an initial training of the AAE model, followed by an integration of multi-objective evolutionary optimization in the continuous latent representation space of the AAE rather than the discrete structural space of molecules. By using the AAE, an arbitrary distribution can be provided to the training of AAE such that the latent representation space is set to that distribution. This allows for a starting latent space from which new samples can be produced. Throughout the process of learning, new samples of high-quality are generated after each iteration of training and then added back into the full dataset. Therefore, allowing for a more comprehensive procedure of understanding the data structure. This combination of evolving data and continuous learning not only enables improvement in the generative model, but the data as well. By comparing ADEL to the previous work in DEL, we see that ADEL can obtain better property distributions.
{"title":"Adversarial Deep Evolutionary Learning for Drug Design","authors":"Sheriff Abouchekeir, A. Tchagang, Yifeng Li","doi":"10.1109/CIBCB49929.2021.9562949","DOIUrl":"https://doi.org/10.1109/CIBCB49929.2021.9562949","url":null,"abstract":"The design of a new therapeutic agent is a time-consuming and expensive process. The rise of machine intelligence provides a grand opportunity of expeditiously discovering novel drug candidates through smart search in the vast molecular structural space. In this paper, we propose a new approach called adversarial deep evolutionary learning (ADEL) to search for novel molecules in the latent space of an adversarial generative model and keep improving the latent representation space. In ADEL, a custom-made adversarial autoencoder (AAE) model is developed and trained under a deep evolutionary learning (DEL) process. This involves an initial training of the AAE model, followed by an integration of multi-objective evolutionary optimization in the continuous latent representation space of the AAE rather than the discrete structural space of molecules. By using the AAE, an arbitrary distribution can be provided to the training of AAE such that the latent representation space is set to that distribution. This allows for a starting latent space from which new samples can be produced. Throughout the process of learning, new samples of high-quality are generated after each iteration of training and then added back into the full dataset. Therefore, allowing for a more comprehensive procedure of understanding the data structure. This combination of evolving data and continuous learning not only enables improvement in the generative model, but the data as well. By comparing ADEL to the previous work in DEL, we see that ADEL can obtain better property distributions.","PeriodicalId":163387,"journal":{"name":"2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122815010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-13DOI: 10.1109/CIBCB49929.2021.9562919
Jongwoo Kim, L. Tran
Optical Coherence Tomography (OCT) is a noninvasive test that takes cross-section pictures of the retina layer of the eye and allows ophthalmologists to diagnose based on the retina's layers. Therefore, it is an important modality for the detection and quantification of retinal diseases and retinal abnormalities. Since OCT provides several images for each patient, it is a time consuming work for ophthalmologists to analyze the images. This paper proposes deep learning models that categorize patients' OCT images into four categories such as Choroidal neovascularization (CNV), Diabetic macular edema (DME), Drusen, and Normal. Two different models are proposed. One is using three binary Convolutional Neural Network (CNN) classifiers and the other is using four binary CNN classifiers. Several CNNs, such as VGG16, VGG19, ResNet50, ResNet152, DenseNet121, and InceptionV3, are adapted as feature extractors to develop the binary classifiers. Among them, the proposed model using VGG16 for CNV vs. Other classes, VGG16 for DME vs. other classes, VGG19 for Drusen vs. Other classes, and InceptionV3 for Normal vs. other classes shows the best performance with 0.987 accuracy, 0.987 sensitivity, and 0.996 specificity. The binary classifier for Normal class has 0.999 accuracy. These results show their potential to work as a second reader for ophthalmologists.
光学相干断层扫描(OCT)是一种非侵入性检查，它可以拍摄眼睛视网膜层的横截面照片，并允许眼科医生根据视网膜层进行诊断。因此，它是检测和定量视网膜疾病和视网膜异常的重要方式。由于OCT为每位患者提供多张图像，因此眼科医生分析图像是一项耗时的工作。本文提出了深度学习模型，将患者的OCT图像分为脉络膜新生血管(CNV)、糖尿病性黄斑水肿(DME)、Drusen和正常四类。提出了两种不同的模型。一种是使用三个二进制卷积神经网络(CNN)分类器，另一种是使用四个二进制CNN分类器。采用VGG16、VGG19、ResNet50、ResNet152、DenseNet121、InceptionV3等几种cnn作为特征提取器开发二值分类器。其中，采用VGG16对CNV vs. Other类、VGG16对DME vs. Other类、VGG19对Drusen vs. Other类、InceptionV3对Normal vs. Other类的模型，准确率0.987、灵敏度0.987、特异性0.996，表现最佳。对于Normal类，二元分类器的准确率为0.999。这些结果显示了它们作为眼科医生的第二阅读器的潜力。
{"title":"Retinal Disease Classification from OCT Images Using Deep Learning Algorithms","authors":"Jongwoo Kim, L. Tran","doi":"10.1109/CIBCB49929.2021.9562919","DOIUrl":"https://doi.org/10.1109/CIBCB49929.2021.9562919","url":null,"abstract":"Optical Coherence Tomography (OCT) is a noninvasive test that takes cross-section pictures of the retina layer of the eye and allows ophthalmologists to diagnose based on the retina's layers. Therefore, it is an important modality for the detection and quantification of retinal diseases and retinal abnormalities. Since OCT provides several images for each patient, it is a time consuming work for ophthalmologists to analyze the images. This paper proposes deep learning models that categorize patients' OCT images into four categories such as Choroidal neovascularization (CNV), Diabetic macular edema (DME), Drusen, and Normal. Two different models are proposed. One is using three binary Convolutional Neural Network (CNN) classifiers and the other is using four binary CNN classifiers. Several CNNs, such as VGG16, VGG19, ResNet50, ResNet152, DenseNet121, and InceptionV3, are adapted as feature extractors to develop the binary classifiers. Among them, the proposed model using VGG16 for CNV vs. Other classes, VGG16 for DME vs. other classes, VGG19 for Drusen vs. Other classes, and InceptionV3 for Normal vs. other classes shows the best performance with 0.987 accuracy, 0.987 sensitivity, and 0.996 specificity. The binary classifier for Normal class has 0.999 accuracy. These results show their potential to work as a second reader for ophthalmologists.","PeriodicalId":163387,"journal":{"name":"2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123235276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-13DOI: 10.1109/CIBCB49929.2021.9562881
Hasini Nakulugamuwa Gamage, M. Chetty, Adrian B. R. Shatte, J. Hallinan
The inference of Gene Regulatory Networks (GRNs) from time series gene expression data is an effective approach for unveiling important underlying gene-gene relationships and dynamics. While various computational models exist for accurate inference of GRNs, many are computationally inefficient, and do not focus on simultaneous inference of both network topology and dynamics. In this paper, we introduce a simple, Boolean network model-based solution for efficient inference of GRNs. First, the microarray expression data are discretized using the average gene expression value as a threshold. This step permits an experimental approach of defining the maximum indegree of a network. Next, regulatory genes, including the self-regulations for each target gene, are inferred using estimated multivariate mutual information-based Min-Redundancy Max-Relevance Criterion, and further accurate inference is performed by a swapping operation. Subsequently, we introduce a new method, combining Boolean network regulation modelling and Pearson correlation coefficient to identify the interaction types (inhibition or activation) of the regulatory genes. This method is utilized for the efficient determination of the optimal regulatory rule, consisting AND, OR, and NOT operators, by defining the accurate application of the NOT operation in conjunction and disjunction Boolean functions. The proposed approach is evaluated using two real gene expression datasets for an Escherichia coli gene regulatory network and a fission yeast cell cycle network. Although the Structural Accuracy is approximately the same as existing methods (MIBNI, REVEAL, Best-Fit, BIBN, and CST), the proposed method outperforms all these methods with respect to efficiency and Dynamic Accuracy.
{"title":"An Efficient Boolean Modelling Approach for Genetic Network Inference","authors":"Hasini Nakulugamuwa Gamage, M. Chetty, Adrian B. R. Shatte, J. Hallinan","doi":"10.1109/CIBCB49929.2021.9562881","DOIUrl":"https://doi.org/10.1109/CIBCB49929.2021.9562881","url":null,"abstract":"The inference of Gene Regulatory Networks (GRNs) from time series gene expression data is an effective approach for unveiling important underlying gene-gene relationships and dynamics. While various computational models exist for accurate inference of GRNs, many are computationally inefficient, and do not focus on simultaneous inference of both network topology and dynamics. In this paper, we introduce a simple, Boolean network model-based solution for efficient inference of GRNs. First, the microarray expression data are discretized using the average gene expression value as a threshold. This step permits an experimental approach of defining the maximum indegree of a network. Next, regulatory genes, including the self-regulations for each target gene, are inferred using estimated multivariate mutual information-based Min-Redundancy Max-Relevance Criterion, and further accurate inference is performed by a swapping operation. Subsequently, we introduce a new method, combining Boolean network regulation modelling and Pearson correlation coefficient to identify the interaction types (inhibition or activation) of the regulatory genes. This method is utilized for the efficient determination of the optimal regulatory rule, consisting AND, OR, and NOT operators, by defining the accurate application of the NOT operation in conjunction and disjunction Boolean functions. The proposed approach is evaluated using two real gene expression datasets for an Escherichia coli gene regulatory network and a fission yeast cell cycle network. Although the Structural Accuracy is approximately the same as existing methods (MIBNI, REVEAL, Best-Fit, BIBN, and CST), the proposed method outperforms all these methods with respect to efficiency and Dynamic Accuracy.","PeriodicalId":163387,"journal":{"name":"2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127872118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-13DOI: 10.1109/CIBCB49929.2021.9562938
Miria Bernardino, R. Beiko
Proteins are responsible for many tasks including cell growth and metabolism. Transcription, the process where genes are used as templates for the production of a messenger RNA intermediate used in the synthesis of proteins, is regulated to ensure that the cell has the appropriate response according to its current needs. An essential step in transcription is the binding of a group of proteins, collectively known as RNA polymerase, to short promoter sequences upstream of the genes to be transcribed. Automated identification of promoters and nearby regulatory sequences can help to predict which genes are likely to be active under a given set of conditions. However, promoters are short, highly variable, and belong to subclasses that sometimes overlap, making their recognition a very difficult problem. Several tools have been developed to identify promoters in DNA, but methods are generally tested on small, balanced subsets of genomic sequence, and the results may not reflect their expected performance on genomes with millions of DNA base pairs in length where only $sim$ 1% of sequence is expected to correspond to promoters. Here we introduce Expositor, a neural-network-based method that uses different types of DNA encodings and tunable sensitivity and specificity parameters. Although the performance of Expositor on balanced datasets was comparable to that of other approaches, at the genome scale our approach finds the highest number of promoters (70% against 46%) with the smallest number of false positives. We also examined the accuracy of Expositor in distinguishing different classes of promoters, and found that misclassification between classes was consistent with the biological similarity between promoters. Expositor source code and pretrained model, and the datasets used for training and testing can be accessed at https://github.com/beiko-lab/Expositor.
{"title":"Genome-scale prediction of bacterial promoters","authors":"Miria Bernardino, R. Beiko","doi":"10.1109/CIBCB49929.2021.9562938","DOIUrl":"https://doi.org/10.1109/CIBCB49929.2021.9562938","url":null,"abstract":"Proteins are responsible for many tasks including cell growth and metabolism. Transcription, the process where genes are used as templates for the production of a messenger RNA intermediate used in the synthesis of proteins, is regulated to ensure that the cell has the appropriate response according to its current needs. An essential step in transcription is the binding of a group of proteins, collectively known as RNA polymerase, to short promoter sequences upstream of the genes to be transcribed. Automated identification of promoters and nearby regulatory sequences can help to predict which genes are likely to be active under a given set of conditions. However, promoters are short, highly variable, and belong to subclasses that sometimes overlap, making their recognition a very difficult problem. Several tools have been developed to identify promoters in DNA, but methods are generally tested on small, balanced subsets of genomic sequence, and the results may not reflect their expected performance on genomes with millions of DNA base pairs in length where only $sim$ 1% of sequence is expected to correspond to promoters. Here we introduce Expositor, a neural-network-based method that uses different types of DNA encodings and tunable sensitivity and specificity parameters. Although the performance of Expositor on balanced datasets was comparable to that of other approaches, at the genome scale our approach finds the highest number of promoters (70% against 46%) with the smallest number of false positives. We also examined the accuracy of Expositor in distinguishing different classes of promoters, and found that misclassification between classes was consistent with the biological similarity between promoters. Expositor source code and pretrained model, and the datasets used for training and testing can be accessed at https://github.com/beiko-lab/Expositor.","PeriodicalId":163387,"journal":{"name":"2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128969118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-13DOI: 10.1109/CIBCB49929.2021.9562888
T. H. Rafi, R. Shubair
Every year, doctors diagnose skin cancer in around 3 million or more patients across the globe. Currently, it is one of the most widely recognized kinds of cancers for human health. Hence, we need an early diagnosis to prevail any critical condition of the infected patients. Apparently, it can treat with topical drugs, if it diagnoses in an early stage. Hence as an outcome, skin cancer is responsible for less than 1% of all cancer deaths. There are two types of tumors in the skin cancer diseases domain, such as benign and malignant. To develop a robust and early screening system to diagnose skin cancer, it requires an efficient algorithm for prediction, trained with a large dataset. The primary aim of this research is to develop an efficient skin cancer screening process using a robust deep neural network with a large dataset. In this paper, we intend to determine considerate and dangerous types of skin cancer tumors using dermoscopic images from a publicly available dataset. We proposed an efficient and fast scaled 2D-CNN based on EfficientNet-B7 deep neural architecture with image preprocessing. This paper also uses two different pre-trained deep neural architectures, such as VGG19, and ResNet-50 to compare the performance with the proposed architecture. The proposed architecture outperformed the other pre-trained CNN models whereas the proposed architecture achieved higher AUC and accuracy compared to other architectures.
{"title":"A Scaled-2D CNN for Skin Cancer Diagnosis","authors":"T. H. Rafi, R. Shubair","doi":"10.1109/CIBCB49929.2021.9562888","DOIUrl":"https://doi.org/10.1109/CIBCB49929.2021.9562888","url":null,"abstract":"Every year, doctors diagnose skin cancer in around 3 million or more patients across the globe. Currently, it is one of the most widely recognized kinds of cancers for human health. Hence, we need an early diagnosis to prevail any critical condition of the infected patients. Apparently, it can treat with topical drugs, if it diagnoses in an early stage. Hence as an outcome, skin cancer is responsible for less than 1% of all cancer deaths. There are two types of tumors in the skin cancer diseases domain, such as benign and malignant. To develop a robust and early screening system to diagnose skin cancer, it requires an efficient algorithm for prediction, trained with a large dataset. The primary aim of this research is to develop an efficient skin cancer screening process using a robust deep neural network with a large dataset. In this paper, we intend to determine considerate and dangerous types of skin cancer tumors using dermoscopic images from a publicly available dataset. We proposed an efficient and fast scaled 2D-CNN based on EfficientNet-B7 deep neural architecture with image preprocessing. This paper also uses two different pre-trained deep neural architectures, such as VGG19, and ResNet-50 to compare the performance with the proposed architecture. The proposed architecture outperformed the other pre-trained CNN models whereas the proposed architecture achieved higher AUC and accuracy compared to other architectures.","PeriodicalId":163387,"journal":{"name":"2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116702978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-13DOI: 10.1109/CIBCB49929.2021.9562920
Benan Bardak, Mehmet Tan
Accurately predicting desired gene expression effects by using the representations of drugs and genes in silico is a key task in chemogenomics. This paper proposes DeepGREP, a deep learning model that can predict small molecules' gene regulation effects. The main motivation of this work is improving chemical-induced differential gene expression prediction by using a convolutional-based architecture to represent drugs and genes more effectively. To evaluate the performance of the DeepGREP, we conducted several experiments and compared them with DeepCop, the baseline model. The results show that DeepGREP outperforms the baseline model and significantly improves the gene expression prediction for AUC by around 4%, F-Score by around 15%, and Enrichment Factor by around 22%. We also demonstrate that the proposed method mostly outperforms the baseline in more difficulties setting of generalization to unseen molecules by using cold-drug splitting.
{"title":"DeepGREP: A deep convolutional neural network for predicting gene-regulating effects of small molecules","authors":"Benan Bardak, Mehmet Tan","doi":"10.1109/CIBCB49929.2021.9562920","DOIUrl":"https://doi.org/10.1109/CIBCB49929.2021.9562920","url":null,"abstract":"Accurately predicting desired gene expression effects by using the representations of drugs and genes in silico is a key task in chemogenomics. This paper proposes DeepGREP, a deep learning model that can predict small molecules' gene regulation effects. The main motivation of this work is improving chemical-induced differential gene expression prediction by using a convolutional-based architecture to represent drugs and genes more effectively. To evaluate the performance of the DeepGREP, we conducted several experiments and compared them with DeepCop, the baseline model. The results show that DeepGREP outperforms the baseline model and significantly improves the gene expression prediction for AUC by around 4%, F-Score by around 15%, and Enrichment Factor by around 22%. We also demonstrate that the proposed method mostly outperforms the baseline in more difficulties setting of generalization to unseen molecules by using cold-drug splitting.","PeriodicalId":163387,"journal":{"name":"2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127013392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-13DOI: 10.1109/CIBCB49929.2021.9562871
D. Ashlock, J. A. Brown, S. Houghten, M. Makhmutov
This study introduces a new game that models competition in foraging behavior. Two moose decide, in each time period, which of three foraging areas to visit. Moose in the same foraging area fight, gaining no forage and also damaging some forage during their conflict. Moose alone in a foraging area eat, with the forage in each field being replenished with a logistic growth model. This creates a relatively complex game with a rich strategy space in which the moose try to maximize their forage intake. The game is a coordination game, as the moose try to avoid conflict which does not maximize forage intake. The paper reports the results of two student competitions at Innopolis University and performs agent evolution to verify the existence of a rich strategy space for the game.
{"title":"One Moose, Two Moose, Three Fields, More?","authors":"D. Ashlock, J. A. Brown, S. Houghten, M. Makhmutov","doi":"10.1109/CIBCB49929.2021.9562871","DOIUrl":"https://doi.org/10.1109/CIBCB49929.2021.9562871","url":null,"abstract":"This study introduces a new game that models competition in foraging behavior. Two moose decide, in each time period, which of three foraging areas to visit. Moose in the same foraging area fight, gaining no forage and also damaging some forage during their conflict. Moose alone in a foraging area eat, with the forage in each field being replenished with a logistic growth model. This creates a relatively complex game with a rich strategy space in which the moose try to maximize their forage intake. The game is a coordination game, as the moose try to avoid conflict which does not maximize forage intake. The paper reports the results of two student competitions at Innopolis University and performs agent evolution to verify the existence of a rich strategy space for the game.","PeriodicalId":163387,"journal":{"name":"2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134196005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-13DOI: 10.1109/CIBCB49929.2021.9562855
Fatemeh Zaremehrjardi, Athar Omidi, Cristina D. Sciortino, Ryan E. R. Reid, Ryan Lukeman, J. Hughes, O. Soufan
The COVID-19 pandemic, caused by the SARS-CoV-2 virus, led to a global health crisis, with more than 157 million cases confirmed infected by May 2021. Effective medication is desperately needed. Predicting drug-target interaction (DTI) is an important step to discover novel uses of chemical structures. Here, we develop a pipeline to predict novel DTIs based on the proteins of the coronavirus. Different datasets (human/SARS-CoV-2 Protein-Protein interaction (PPI), Drug-Drug similarity (DD sim), and DTIs) are used and combined. After mapping all datasets onto a heterogeneous graph, path-related features are extracted. We then applied various machine learning (ML) algorithms to model our dataset and predict novel DTIs among unlabeled pairs. Possible drugs identified by the models with a high frequency are reported. In addition, evidence of the efficiency of the predicted medicines by the models against COVID-19 are presented. The proposed model can then be generalized to contain other features that provide a context to predict medicine for different diseases.
{"title":"Discovering Missing Edges in Drug-Protein Networks: Repurposing Drugs for SARS-CoV-2","authors":"Fatemeh Zaremehrjardi, Athar Omidi, Cristina D. Sciortino, Ryan E. R. Reid, Ryan Lukeman, J. Hughes, O. Soufan","doi":"10.1109/CIBCB49929.2021.9562855","DOIUrl":"https://doi.org/10.1109/CIBCB49929.2021.9562855","url":null,"abstract":"The COVID-19 pandemic, caused by the SARS-CoV-2 virus, led to a global health crisis, with more than 157 million cases confirmed infected by May 2021. Effective medication is desperately needed. Predicting drug-target interaction (DTI) is an important step to discover novel uses of chemical structures. Here, we develop a pipeline to predict novel DTIs based on the proteins of the coronavirus. Different datasets (human/SARS-CoV-2 Protein-Protein interaction (PPI), Drug-Drug similarity (DD sim), and DTIs) are used and combined. After mapping all datasets onto a heterogeneous graph, path-related features are extracted. We then applied various machine learning (ML) algorithms to model our dataset and predict novel DTIs among unlabeled pairs. Possible drugs identified by the models with a high frequency are reported. In addition, evidence of the efficiency of the predicted medicines by the models against COVID-19 are presented. The proposed model can then be generalized to contain other features that provide a context to predict medicine for different diseases.","PeriodicalId":163387,"journal":{"name":"2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","volume":"220 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124366395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-13DOI: 10.1109/CIBCB49929.2021.9562819
Batuhan Bardak, Mehmet Tan
Drug representations have played an important role in cheminformatics. However, in the healthcare domain, drug representations have been underused relative to the rest of Electronic Health Record (EHR) data, due to the complexity of high dimensional drug representations and the lack of proper pipeline that will allow to convert clinical drugs to their representations. Time-varying vital signs, laboratory measurements, and related time-series signals are commonly used to predict clinical outcomes. In this work, we demonstrated that using clinical drug representations in addition to other clinical features has significant potential to increase the performance of mortality and length of stay (LOS) models. We evaluate the two different drug representation methods (Extended -Connectivity Fingerprint- ECFP and SMILES-Transformer embedding) on clinical outcome predictions. The results have shown that the proposed multimodal approach achieves substantial enhancement on clinical tasks over baseline models. U sing clinical drug representations as additional features improve the LOS prediction for Area Under the Receiver Operating Characteristics (AUROC) around %6 and for Area Under Precision-Recall Curve (AUPRC) by around % 5. Furthermore, for the mortality prediction task, there is an improvement of around % 2 over the time series baseline in terms of AUROC and %3.5 in terms of AUPRC. The code for the proposed method is available at https://github.com/tanlab/MIMIC-III-Clinical-Drug-Representations.
{"title":"Using Clinical Drug Representations for Improving Mortality and Length of Stay Predictions","authors":"Batuhan Bardak, Mehmet Tan","doi":"10.1109/CIBCB49929.2021.9562819","DOIUrl":"https://doi.org/10.1109/CIBCB49929.2021.9562819","url":null,"abstract":"Drug representations have played an important role in cheminformatics. However, in the healthcare domain, drug representations have been underused relative to the rest of Electronic Health Record (EHR) data, due to the complexity of high dimensional drug representations and the lack of proper pipeline that will allow to convert clinical drugs to their representations. Time-varying vital signs, laboratory measurements, and related time-series signals are commonly used to predict clinical outcomes. In this work, we demonstrated that using clinical drug representations in addition to other clinical features has significant potential to increase the performance of mortality and length of stay (LOS) models. We evaluate the two different drug representation methods (Extended -Connectivity Fingerprint- ECFP and SMILES-Transformer embedding) on clinical outcome predictions. The results have shown that the proposed multimodal approach achieves substantial enhancement on clinical tasks over baseline models. U sing clinical drug representations as additional features improve the LOS prediction for Area Under the Receiver Operating Characteristics (AUROC) around %6 and for Area Under Precision-Recall Curve (AUPRC) by around % 5. Furthermore, for the mortality prediction task, there is an improvement of around % 2 over the time series baseline in terms of AUROC and %3.5 in terms of AUPRC. The code for the proposed method is available at https://github.com/tanlab/MIMIC-III-Clinical-Drug-Representations.","PeriodicalId":163387,"journal":{"name":"2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122912902","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：