Pub Date : 2021-10-25DOI: 10.1109/BIBE52308.2021.9635284
V. Simić, M. Milošević, I. Šaveljić, B. Milićević, N. Filipovic, M. Kojic
In this report we present basic steps in the 3D reconstruction process of DICOM images and application of our finite element (FE) numerical procedure for loose coupling solid-fluid interaction, to simulate a complete heartbeat cycle for a realistic model of the left heart side. Passive mechanical stresses are calculated using an orthotropic material model based on the experimental investigation of passive material properties of the myocardium, while active stresses are calculated using the Hunter material model. The basic equations for solid mechanics, fluid dynamics, and muscle activation are summarized and model applicability is illustrated on a complex realistic model which includes a left atrium, ventricle, mitral and aortic valves (which serve as fluid domain) coupled with solid wall with realistic fiber directions.
{"title":"3D reconstruction and computational modeling of solid-fluid interaction in realistic heart model","authors":"V. Simić, M. Milošević, I. Šaveljić, B. Milićević, N. Filipovic, M. Kojic","doi":"10.1109/BIBE52308.2021.9635284","DOIUrl":"https://doi.org/10.1109/BIBE52308.2021.9635284","url":null,"abstract":"In this report we present basic steps in the 3D reconstruction process of DICOM images and application of our finite element (FE) numerical procedure for loose coupling solid-fluid interaction, to simulate a complete heartbeat cycle for a realistic model of the left heart side. Passive mechanical stresses are calculated using an orthotropic material model based on the experimental investigation of passive material properties of the myocardium, while active stresses are calculated using the Hunter material model. The basic equations for solid mechanics, fluid dynamics, and muscle activation are summarized and model applicability is illustrated on a complex realistic model which includes a left atrium, ventricle, mitral and aortic valves (which serve as fluid domain) coupled with solid wall with realistic fiber directions.","PeriodicalId":343724,"journal":{"name":"2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124322710","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 : 2021-10-25DOI: 10.1109/BIBE52308.2021.9635346
Vasileios Skaramagkas, Emmanouil Ktistakis, D. Manousos, N. Tachos, E. Kazantzaki, E. Tripoliti, D. Fotiadis, M. Tsiknakis
In the last years, many studies have been investigating emotional arousal and valence. Most of them have focused on the use of physiological signals such as EEG or EMG, cardiovascular measures or skin conductance. However, eye related features have proven to be very helpful and easy to use metrics, especially pupil size and blink activity. The aim of this study is to predict emotional arousal and valence levels which are induced during emotionally charged situations from eye related features. For this reason, we performed an experimental study where the participants watched emotion-eliciting videos and self-assessed their emotions, while their eye movements were being recorded. In this work, several classifiers such as KNN, SVM, Naive Bayes, Trees and Ensemble methods were trained and tested. Finally, emotional arousal and valence levels were predicted with 85 and 91% efficiency, respectively.
{"title":"A machine learning approach to predict emotional arousal and valence from gaze extracted features","authors":"Vasileios Skaramagkas, Emmanouil Ktistakis, D. Manousos, N. Tachos, E. Kazantzaki, E. Tripoliti, D. Fotiadis, M. Tsiknakis","doi":"10.1109/BIBE52308.2021.9635346","DOIUrl":"https://doi.org/10.1109/BIBE52308.2021.9635346","url":null,"abstract":"In the last years, many studies have been investigating emotional arousal and valence. Most of them have focused on the use of physiological signals such as EEG or EMG, cardiovascular measures or skin conductance. However, eye related features have proven to be very helpful and easy to use metrics, especially pupil size and blink activity. The aim of this study is to predict emotional arousal and valence levels which are induced during emotionally charged situations from eye related features. For this reason, we performed an experimental study where the participants watched emotion-eliciting videos and self-assessed their emotions, while their eye movements were being recorded. In this work, several classifiers such as KNN, SVM, Naive Bayes, Trees and Ensemble methods were trained and tested. Finally, emotional arousal and valence levels were predicted with 85 and 91% efficiency, respectively.","PeriodicalId":343724,"journal":{"name":"2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124003253","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 : 2021-10-25DOI: 10.1109/BIBE52308.2021.9635199
Nicoletta Prentzas, Marios Pitsiali, E. Kyriacou, Andrew N. Nicolaides, A. Kakas, C. Pattichis
The current adoption of Medical Artificial Intelligence (AI) solutions in clinical practice suggest that despite its undeniable potential AI is not achieving this potential. A major barrier to its adoption is the lack of transparency and interpretability, and the inability of the system to explain its results. Explainable AI (XAI) is an emerging field in AI that aims to address these barriers, with the development of new or modified algorithms to enable transparency, provide explanations in a way that humans can understand and foster trust. Numerous XAI techniques have been proposed in the literature, commonly classified as model-agnostic or model-specific. In this study, we examine the application of four model-agnostic XAI techniques (LIME, SHAP, ANCHORS, inTrees) to an XGBoost classifier trained on real-life medical data for the prediction of high-risk asymptomatic carotid plaques based on ultrasound image analysis. We present and compare local explanations for selected observations in the test set. We also present global explanations generated from these techniques that explain the behavior of the entire model. Additionally, we assess the quality of the explanations, using suggested properties in the literature. Finally, we discuss the results of this comparative study and suggest directions for future work.
{"title":"Model Agnostic Explainability Techniques in Ultrasound Image Analysis","authors":"Nicoletta Prentzas, Marios Pitsiali, E. Kyriacou, Andrew N. Nicolaides, A. Kakas, C. Pattichis","doi":"10.1109/BIBE52308.2021.9635199","DOIUrl":"https://doi.org/10.1109/BIBE52308.2021.9635199","url":null,"abstract":"The current adoption of Medical Artificial Intelligence (AI) solutions in clinical practice suggest that despite its undeniable potential AI is not achieving this potential. A major barrier to its adoption is the lack of transparency and interpretability, and the inability of the system to explain its results. Explainable AI (XAI) is an emerging field in AI that aims to address these barriers, with the development of new or modified algorithms to enable transparency, provide explanations in a way that humans can understand and foster trust. Numerous XAI techniques have been proposed in the literature, commonly classified as model-agnostic or model-specific. In this study, we examine the application of four model-agnostic XAI techniques (LIME, SHAP, ANCHORS, inTrees) to an XGBoost classifier trained on real-life medical data for the prediction of high-risk asymptomatic carotid plaques based on ultrasound image analysis. We present and compare local explanations for selected observations in the test set. We also present global explanations generated from these techniques that explain the behavior of the entire model. Additionally, we assess the quality of the explanations, using suggested properties in the literature. Finally, we discuss the results of this comparative study and suggest directions for future work.","PeriodicalId":343724,"journal":{"name":"2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126158350","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 : 2021-10-25DOI: 10.1109/BIBE52308.2021.9635403
Rémi Segretain, Laurent Trilling, N. Glade, Sergiu Ivanov
Intuition tells us that highly complex structure should be strongly correlated with highly complex behavior. In this work, we show that, while complex behavior does require complex structure, the converse is not necessarily true. Indeed, structural complexity can be also used to implement robust behavior, or even a variety of different relatively simple behaviors. To obtain these results, we explored the spaces of sign Boolean networks (SBNs) containing 2, 3, and 4 nodes, and we used complexity measures introduced in our previous work to study the relationship between structural and behavioral complexities of these networks.
{"title":"Who Plays Complex Music? On the Correlations Between Structural and Behavioral Complexity Measures in Sign Boolean Networks","authors":"Rémi Segretain, Laurent Trilling, N. Glade, Sergiu Ivanov","doi":"10.1109/BIBE52308.2021.9635403","DOIUrl":"https://doi.org/10.1109/BIBE52308.2021.9635403","url":null,"abstract":"Intuition tells us that highly complex structure should be strongly correlated with highly complex behavior. In this work, we show that, while complex behavior does require complex structure, the converse is not necessarily true. Indeed, structural complexity can be also used to implement robust behavior, or even a variety of different relatively simple behaviors. To obtain these results, we explored the spaces of sign Boolean networks (SBNs) containing 2, 3, and 4 nodes, and we used complexity measures introduced in our previous work to study the relationship between structural and behavioral complexities of these networks.","PeriodicalId":343724,"journal":{"name":"2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131232990","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 : 2021-10-25DOI: 10.1109/BIBE52308.2021.9635280
A. Rakic, D. Dimić, J. Markovic, D. Milenkovic, Z. Marković
The isonicotinohydrazide moiety is a common structural motif of the biologically active compounds with pronounced therapeutic effects. Four isonicotinohydrazide analogs were investigated to elucidate the importance of various substituents on the predicted biological activity. The structures of these compounds were optimized at the M06-2X16-311++G(d, p) level of theory based on the crystallographic structures. The intermolecular interactions governing the stability of these compounds were analyzed by the Natural Bond Orbital theory. The molecular docking studies towards Cyclin-Dependent Kinase 2 (CDK2) were performed and the specific interactions of present substituents were described. The absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties of these compounds were predicted by the SWISSADME and Prediction of Toxicity (ProTox-II) webservers. The ecotoxicity study also showed that these compounds might be potentially toxic towards fish, daphnia, and green algae. The similarity in toxicity and reactivity of these compounds is a consequence of the present substituents.
{"title":"Toxicity, structural analysis, and molecular docking studies of selected isonicotinohydrazide analogs","authors":"A. Rakic, D. Dimić, J. Markovic, D. Milenkovic, Z. Marković","doi":"10.1109/BIBE52308.2021.9635280","DOIUrl":"https://doi.org/10.1109/BIBE52308.2021.9635280","url":null,"abstract":"The isonicotinohydrazide moiety is a common structural motif of the biologically active compounds with pronounced therapeutic effects. Four isonicotinohydrazide analogs were investigated to elucidate the importance of various substituents on the predicted biological activity. The structures of these compounds were optimized at the M06-2X16-311++G(d, p) level of theory based on the crystallographic structures. The intermolecular interactions governing the stability of these compounds were analyzed by the Natural Bond Orbital theory. The molecular docking studies towards Cyclin-Dependent Kinase 2 (CDK2) were performed and the specific interactions of present substituents were described. The absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties of these compounds were predicted by the SWISSADME and Prediction of Toxicity (ProTox-II) webservers. The ecotoxicity study also showed that these compounds might be potentially toxic towards fish, daphnia, and green algae. The similarity in toxicity and reactivity of these compounds is a consequence of the present substituents.","PeriodicalId":343724,"journal":{"name":"2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131249007","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 : 2021-10-25DOI: 10.1109/BIBE52308.2021.9635313
Maja Savić, A. M. Samanovic, N. Draginic, M. Andjic, M. Nikolić, V. Jakovljevic, S. Bolevich
Taraxacum officinale Weber (Asteraceae), known as dandelion, is used for medicinal purposes due to its antioxidant as well as hypolipemic, anticoagulation, diuretic, antitumor, anti-inflammatory and hepatoprotective properties. Therefore, the aim of our study was to examine the effects of a two-week application of dandelion root extract on the oxidative status in rats. Every morning, for 15 days, the animals received a fresh infusion of dandelion, and it was previously measured and recorded how much they drank the previous day. After treatment, rats were sacrificed and blood samples were collected from a jugular vein to test the systemic redox state. In rats treated with dandelion extract, there was a significant increase of prooxidant markers, lipid peroxidation index (TBARS) and hydrogen peroxide (H2O2) compared to the control group. After two weeks of application of fresh dandelion extract, changes in the level of prooxidative parameters were noticed. Levels of H2O2, NO and TBARS increased, while there was a significant decrease in the levels of superoxide anionic radical as the most toxic free radical. On the basis of the obtained results, we can assume that dandelion is successful in treating conditions and diseases caused by an increased amount of superoxide anionic radical. On the other hand, dandelion extract treatment increased the level of reduced glutathione in rats, but significantly reduced the activity of superoxide dismutase and catalase. Further research and studies are needed to identify all bioactive compounds present in dandelion as well as a more detailed examination of the effects of dandelion on oxidation status.
{"title":"Effects of chronic administration of Taraxacum Officinale Weber extract on oxidative status in rats","authors":"Maja Savić, A. M. Samanovic, N. Draginic, M. Andjic, M. Nikolić, V. Jakovljevic, S. Bolevich","doi":"10.1109/BIBE52308.2021.9635313","DOIUrl":"https://doi.org/10.1109/BIBE52308.2021.9635313","url":null,"abstract":"Taraxacum officinale Weber (Asteraceae), known as dandelion, is used for medicinal purposes due to its antioxidant as well as hypolipemic, anticoagulation, diuretic, antitumor, anti-inflammatory and hepatoprotective properties. Therefore, the aim of our study was to examine the effects of a two-week application of dandelion root extract on the oxidative status in rats. Every morning, for 15 days, the animals received a fresh infusion of dandelion, and it was previously measured and recorded how much they drank the previous day. After treatment, rats were sacrificed and blood samples were collected from a jugular vein to test the systemic redox state. In rats treated with dandelion extract, there was a significant increase of prooxidant markers, lipid peroxidation index (TBARS) and hydrogen peroxide (H2O2) compared to the control group. After two weeks of application of fresh dandelion extract, changes in the level of prooxidative parameters were noticed. Levels of H2O2, NO and TBARS increased, while there was a significant decrease in the levels of superoxide anionic radical as the most toxic free radical. On the basis of the obtained results, we can assume that dandelion is successful in treating conditions and diseases caused by an increased amount of superoxide anionic radical. On the other hand, dandelion extract treatment increased the level of reduced glutathione in rats, but significantly reduced the activity of superoxide dismutase and catalase. Further research and studies are needed to identify all bioactive compounds present in dandelion as well as a more detailed examination of the effects of dandelion on oxidation status.","PeriodicalId":343724,"journal":{"name":"2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"155 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126736422","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 : 2021-10-25DOI: 10.1109/BIBE52308.2021.9635370
M. Pilou, Anastasios Skiadopoulos, P. Neofytou
Computational fluid particle dynamics techniques are employed to investigate particle adhesion on the vascular wall of a patient specific infrarenal abdominal aorta aneurysm (AAA). The particles are decorated with ligands that are assumed to interact with receptors expressed on the inflamed endothelium. In-house software is used for the generation of the computational grid from anonymous medical data, the calculation of the time-dependent flow field over a cardiac cycle, and the solution of the particle convection-diffusion equation. The effect of particle size and flow field on adhesion efficiency and location is investigated. It is found that for the 500nm particles high area average vascular deposition parameter (AAVDP) corresponds to areas of low Area average shear rate (AASR), whereas for the 50nm particles, AAVDP increases monotonically with AASR. In all cases, particles adhere predominately around the proximal and distal AAA necks and maximum deposition occurs at the areas of high flow residence time. Moreover, 50nm particles adhere diffusely on the vascular wall, whereas adhesion of 500nm particles is highly localized. For all particle diameters, however, the adhesion efficiency is almost negligible, as more than 99.9% of the released particles escape the AAA.
{"title":"Particle Adhesion on a Patient Specific Abdominal Aorta Aneurysm","authors":"M. Pilou, Anastasios Skiadopoulos, P. Neofytou","doi":"10.1109/BIBE52308.2021.9635370","DOIUrl":"https://doi.org/10.1109/BIBE52308.2021.9635370","url":null,"abstract":"Computational fluid particle dynamics techniques are employed to investigate particle adhesion on the vascular wall of a patient specific infrarenal abdominal aorta aneurysm (AAA). The particles are decorated with ligands that are assumed to interact with receptors expressed on the inflamed endothelium. In-house software is used for the generation of the computational grid from anonymous medical data, the calculation of the time-dependent flow field over a cardiac cycle, and the solution of the particle convection-diffusion equation. The effect of particle size and flow field on adhesion efficiency and location is investigated. It is found that for the 500nm particles high area average vascular deposition parameter (AAVDP) corresponds to areas of low Area average shear rate (AASR), whereas for the 50nm particles, AAVDP increases monotonically with AASR. In all cases, particles adhere predominately around the proximal and distal AAA necks and maximum deposition occurs at the areas of high flow residence time. Moreover, 50nm particles adhere diffusely on the vascular wall, whereas adhesion of 500nm particles is highly localized. For all particle diameters, however, the adhesion efficiency is almost negligible, as more than 99.9% of the released particles escape the AAA.","PeriodicalId":343724,"journal":{"name":"2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116619832","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 : 2021-10-25DOI: 10.1109/BIBE52308.2021.9635558
Kirstina B. Persson Vestersoe, M. Mohammadi, E. Kromann, L. Struijk
Complete tetraplegia causes paralysis from the neck down, resulting in a need for constant care and lack of doing activities of daily living by yourself. Exoskeletons have enabled some rehabilitation and movement of paralyzed limbs but are often prohibitively large and heavy. This project aimed to redesign the wrist of the tongue controlled EXOTIC exoskeleton, making it compact and light. The new design used tendon-based technology, removing the motor from the forearm as well as employing 3D print. A proof-of-concept for the new design was obtained through a case study with three subjects.
{"title":"Tendon-based design of wrist joint for tongue-controlled exoskeleton - a case study","authors":"Kirstina B. Persson Vestersoe, M. Mohammadi, E. Kromann, L. Struijk","doi":"10.1109/BIBE52308.2021.9635558","DOIUrl":"https://doi.org/10.1109/BIBE52308.2021.9635558","url":null,"abstract":"Complete tetraplegia causes paralysis from the neck down, resulting in a need for constant care and lack of doing activities of daily living by yourself. Exoskeletons have enabled some rehabilitation and movement of paralyzed limbs but are often prohibitively large and heavy. This project aimed to redesign the wrist of the tongue controlled EXOTIC exoskeleton, making it compact and light. The new design used tendon-based technology, removing the motor from the forearm as well as employing 3D print. A proof-of-concept for the new design was obtained through a case study with three subjects.","PeriodicalId":343724,"journal":{"name":"2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121795724","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 : 2021-10-25DOI: 10.1109/BIBE52308.2021.9635292
Aviral Chharia, Apurva Narayan
The identification of B-cell epitopes that elicit an antigen-specific immune response is essential for a variety of immunodetection and immunotherapeutic applications, including the development of safe and high efficacy vaccines. Identifying diagnostically or therapeutically useful epitopes is a difficult, time-consuming, and resource-intensive procedure. In silico prediction of B-cell epitope has gained immense attention in recent years due to its low cost, fast results, and less labor-intensive method compared to NMR spectroscopy and 3D X-ray structural analysis of antibody-antigen complexes. However, one of the major problems that most established models confront is gathering huge volumes of data. Moreover, most models do not achieve high levels of accuracy. The current work is the first to propose the ‘Fuzzy’ approach to in silico B-cell epitope prediction. The effectiveness of the proposed approach is demonstrated on severely imbalanced and limited datasets through several experiments. The results show that using the proposed method enhances both accuracy and precision when compared to existing approaches. Further, the model is tested on the SARS-CoV-1 antigen-antibody PDB complex. The proposed approach outperforms state-of-the-art machine learning (ML) models trained on the same dataset. Results obtained indicate that applying the proposed method improves the prediction compared to the other approaches.
{"title":"A novel fuzzy approach towards in silico B-cell epitope identification inducing antigen-specific immune response for Vaccine Design","authors":"Aviral Chharia, Apurva Narayan","doi":"10.1109/BIBE52308.2021.9635292","DOIUrl":"https://doi.org/10.1109/BIBE52308.2021.9635292","url":null,"abstract":"The identification of B-cell epitopes that elicit an antigen-specific immune response is essential for a variety of immunodetection and immunotherapeutic applications, including the development of safe and high efficacy vaccines. Identifying diagnostically or therapeutically useful epitopes is a difficult, time-consuming, and resource-intensive procedure. In silico prediction of B-cell epitope has gained immense attention in recent years due to its low cost, fast results, and less labor-intensive method compared to NMR spectroscopy and 3D X-ray structural analysis of antibody-antigen complexes. However, one of the major problems that most established models confront is gathering huge volumes of data. Moreover, most models do not achieve high levels of accuracy. The current work is the first to propose the ‘Fuzzy’ approach to in silico B-cell epitope prediction. The effectiveness of the proposed approach is demonstrated on severely imbalanced and limited datasets through several experiments. The results show that using the proposed method enhances both accuracy and precision when compared to existing approaches. Further, the model is tested on the SARS-CoV-1 antigen-antibody PDB complex. The proposed approach outperforms state-of-the-art machine learning (ML) models trained on the same dataset. Results obtained indicate that applying the proposed method improves the prediction compared to the other approaches.","PeriodicalId":343724,"journal":{"name":"2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126979519","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 : 2021-10-25DOI: 10.1109/BIBE52308.2021.9635512
S. Raval, O. Erin, Xiaolong Liu, L. Mair, Will Pryor, Yotam Barnoy, I. Weinberg, A. Krieger, Y. Diaz-Mercado
Exerting forces and torques instantaneously on rigid magnetic bodies with no physical connection is an attractive feature of magnetic robotics. This demonstrates great potential for manipulating tools that are externally controlled through the use of magnetic fields in minimally invasive surgeries. The magnetic field can be controlled by the application of currents to electromagnets positioned around the surgical site, and the necessary currents for a specific desired manipulation can be derived from magnetic field models. However, the magnetic field generated by electromagnetic coils are highly nonlinear, especially in the vicinity of the magnetic field sources, which complicates the modeling process. While simple dipole models provide a good approximation for these fields far away from the electromagnets, these models tend to be highly inaccurate near the sources. Magnetic surgical applications benefit from models which accurately describe fields and gradients both near and far from the field source. Particularly, since forces and torques decay inversely proportionally with the cube of the distance to the coil, inaccurate modeling near the coil makes large regions near the coil unfit for applications requiring precisely predicted motion. Estimation errors near coils generate inaccuracies in field models that significantly reduce control performance for rigid magnetic bodies. In order to tackle this problem, we utilize Zernike basis functions to analytically represent the nonlinear magnetic field distribution more accurately. The accuracy of the controller is tested experimentally by driving a magnetic surgical suture needle with a length of 22 mm in the MagnetoSuture™ system along a lemniscate trajectory. The magnetic needle's tip position and the needle orientation, autonomously controlled by the proposed controller, shows RMS tracking error of 2.35 mm using typical dipole models and 1.71 mm for the Zernike fitting approach, a 27% improvement in tracking error. This suggests that the use of Zernike basis functions to capture the nonlinearities of the magnetic field may assist in implementing fast and precise autonomous control strategies for magnetic suture needles.
{"title":"Magnetic Model Calibration for Tetherless Surgical Needle Manipulation using Zernike Polynomial Fitting","authors":"S. Raval, O. Erin, Xiaolong Liu, L. Mair, Will Pryor, Yotam Barnoy, I. Weinberg, A. Krieger, Y. Diaz-Mercado","doi":"10.1109/BIBE52308.2021.9635512","DOIUrl":"https://doi.org/10.1109/BIBE52308.2021.9635512","url":null,"abstract":"Exerting forces and torques instantaneously on rigid magnetic bodies with no physical connection is an attractive feature of magnetic robotics. This demonstrates great potential for manipulating tools that are externally controlled through the use of magnetic fields in minimally invasive surgeries. The magnetic field can be controlled by the application of currents to electromagnets positioned around the surgical site, and the necessary currents for a specific desired manipulation can be derived from magnetic field models. However, the magnetic field generated by electromagnetic coils are highly nonlinear, especially in the vicinity of the magnetic field sources, which complicates the modeling process. While simple dipole models provide a good approximation for these fields far away from the electromagnets, these models tend to be highly inaccurate near the sources. Magnetic surgical applications benefit from models which accurately describe fields and gradients both near and far from the field source. Particularly, since forces and torques decay inversely proportionally with the cube of the distance to the coil, inaccurate modeling near the coil makes large regions near the coil unfit for applications requiring precisely predicted motion. Estimation errors near coils generate inaccuracies in field models that significantly reduce control performance for rigid magnetic bodies. In order to tackle this problem, we utilize Zernike basis functions to analytically represent the nonlinear magnetic field distribution more accurately. The accuracy of the controller is tested experimentally by driving a magnetic surgical suture needle with a length of 22 mm in the MagnetoSuture™ system along a lemniscate trajectory. The magnetic needle's tip position and the needle orientation, autonomously controlled by the proposed controller, shows RMS tracking error of 2.35 mm using typical dipole models and 1.71 mm for the Zernike fitting approach, a 27% improvement in tracking error. This suggests that the use of Zernike basis functions to capture the nonlinearities of the magnetic field may assist in implementing fast and precise autonomous control strategies for magnetic suture needles.","PeriodicalId":343724,"journal":{"name":"2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132782967","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：