Pub Date : 2009-06-11DOI: 10.1109/ICBBE.2009.5162853
Sijiang Xiong, Bei-ping Zhang, Xiaoyuan Jia, B. Xiao, Maoyun He
The feasibility of producing hydrogen-riched fuel gas from wet sewage sludge was assessed in this paper, which consist in carrying out the pyrolysis of dewatered residual activated sludge as it is produced in the wastewater treatment plant with a moisture content of above 70%, without subjecting it to any previous thermal drying process. In order to establish the most favorable conditions for the production of hydrogen-riched fuel gas, the effects of moisture content, heating rate and temperature were analyzed. It was found that the natural moisture of the sludge was converted into steam at high temperature, which can take part in the partial gasification of the sludge, leading to an increase in the gas production and the yield of hydrogen. In addition, pyrolyzing wet sludge at high temperature with high heating rates could maximize the gas yield productivity and raise its quality as a fuel and as a source of hydrogen or syngas as well. In this process, the drying, pyrolysis and gasification of wet sewage sludge were completed in a single thermal process, and resulting in a considerable amount of gases with potential value as fuels due to the relatively high calorific values they contain.
{"title":"Feasibility Study on the Pyrolysis Production for Hydrogen-Riched Fuel Gas from the Wet Sewage Sludge","authors":"Sijiang Xiong, Bei-ping Zhang, Xiaoyuan Jia, B. Xiao, Maoyun He","doi":"10.1109/ICBBE.2009.5162853","DOIUrl":"https://doi.org/10.1109/ICBBE.2009.5162853","url":null,"abstract":"The feasibility of producing hydrogen-riched fuel gas from wet sewage sludge was assessed in this paper, which consist in carrying out the pyrolysis of dewatered residual activated sludge as it is produced in the wastewater treatment plant with a moisture content of above 70%, without subjecting it to any previous thermal drying process. In order to establish the most favorable conditions for the production of hydrogen-riched fuel gas, the effects of moisture content, heating rate and temperature were analyzed. It was found that the natural moisture of the sludge was converted into steam at high temperature, which can take part in the partial gasification of the sludge, leading to an increase in the gas production and the yield of hydrogen. In addition, pyrolyzing wet sludge at high temperature with high heating rates could maximize the gas yield productivity and raise its quality as a fuel and as a source of hydrogen or syngas as well. In this process, the drying, pyrolysis and gasification of wet sewage sludge were completed in a single thermal process, and resulting in a considerable amount of gases with potential value as fuels due to the relatively high calorific values they contain.","PeriodicalId":6430,"journal":{"name":"2009 3rd International Conference on Bioinformatics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74051428","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 : 2009-06-11DOI: 10.1109/ICBBE.2009.5162459
Haitao Wang
To improve the blood compatibility of polyethersulfone (PES) membrane, sulfonated polyethersulfone (SPES) was synthesized through an electrophilic substitution reaction and PES/SPES blending membranes were prepared. The characterization of the SPES was studied by FTIR. The water adsorption and water contact angle experiments show that the hydrophilicity of PES/SPES blend membrane was improved as for the sulfonate group existing in the SPES. Moreover, PES/SPES blend membrane could effectively reduce bovine serum albumin adsorption and prolong the blood coagulation time compared with the PES membrane. Overall results of this study demonstrated that blending SPES would be beneficial to improve the blood compatibility of PES membranes. Keywords-PES;SPES; Blood compatibility;blending
{"title":"Blending Sulfonated Polyethersulfone to Improve the Blood Compatibility of Polyethersulfone Membrane","authors":"Haitao Wang","doi":"10.1109/ICBBE.2009.5162459","DOIUrl":"https://doi.org/10.1109/ICBBE.2009.5162459","url":null,"abstract":"To improve the blood compatibility of polyethersulfone (PES) membrane, sulfonated polyethersulfone (SPES) was synthesized through an electrophilic substitution reaction and PES/SPES blending membranes were prepared. The characterization of the SPES was studied by FTIR. The water adsorption and water contact angle experiments show that the hydrophilicity of PES/SPES blend membrane was improved as for the sulfonate group existing in the SPES. Moreover, PES/SPES blend membrane could effectively reduce bovine serum albumin adsorption and prolong the blood coagulation time compared with the PES membrane. Overall results of this study demonstrated that blending SPES would be beneficial to improve the blood compatibility of PES membranes. Keywords-PES;SPES; Blood compatibility;blending","PeriodicalId":6430,"journal":{"name":"2009 3rd International Conference on Bioinformatics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74169860","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 : 2009-06-11DOI: 10.1109/ICBBE.2009.5162909
Haipeng Yu, Yixing Liu, Jun Wu
This study examined the effects of contact with wood- based materials and other reference materials on the living human body using the physiological indexes from heart rate variability (HRV) and non-invasive dynamic blood pressure (DBP) measurements. The changes of sympathetic and parasympathetic in autonomous nervous system were separately analyzed at time domain and frequency domain. The results showed that the activity of the sympathetic nervous system evidently changed with the thermal conduction of materials. It can be concluded that contacting with wood-based materials has little influence on the balance of the autonomous nervous system, and the parasympathetic could be quickly recovered. Subjective survey by SD method showed that the tactility of wood-based materials with smaller thermal conductivity was moderate and people preferred this kind of materials to others.
{"title":"HRV and DBP in Monitoring the Short-Term Effect of Wood-Based Materials on Human Physiologic System","authors":"Haipeng Yu, Yixing Liu, Jun Wu","doi":"10.1109/ICBBE.2009.5162909","DOIUrl":"https://doi.org/10.1109/ICBBE.2009.5162909","url":null,"abstract":"This study examined the effects of contact with wood- based materials and other reference materials on the living human body using the physiological indexes from heart rate variability (HRV) and non-invasive dynamic blood pressure (DBP) measurements. The changes of sympathetic and parasympathetic in autonomous nervous system were separately analyzed at time domain and frequency domain. The results showed that the activity of the sympathetic nervous system evidently changed with the thermal conduction of materials. It can be concluded that contacting with wood-based materials has little influence on the balance of the autonomous nervous system, and the parasympathetic could be quickly recovered. Subjective survey by SD method showed that the tactility of wood-based materials with smaller thermal conductivity was moderate and people preferred this kind of materials to others.","PeriodicalId":6430,"journal":{"name":"2009 3rd International Conference on Bioinformatics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74195236","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 : 2009-06-11DOI: 10.1109/ICBBE.2009.5162171
G. Cheng, Shan Xu, Ruifang Wang, Z. Wu, Fei-juan Zhang, Xiang-feng Huang
In a full-scale test, zeolite enhanced the biological nitrification, but the nitrate of returning mixed-flow in the anaerobic process inhibited the release of the polyphosphate accumulation microorganisms and had little effect on the phosphorus removal in the biological A/O process. It was suggested that we use the method of chemical phosphorus removal in the process. Aluminium and ferric salts had a good effect on chemical phosphorus removal, and had no correlation with locations. When adding Al 2 (SO 4 ) 3 ldr18H 2 O, the molar ratio of the TP and Al at 1:1.5, the rate of phosphorus removal was more than 85%. When adding FeSO 4 ldr12H 2 O, the molar ratio of the TP and Fe at 1:1, the rate of phosphorus removal was more than 80%. When adding 20 mg/L FeSO 4 ldr12H 2 O and 30 mg/L Al 2 (SO 4 ) 3 ldr18H 2 O in the anaerobic process, the mixed phosphorus removal agent could remove nearly 90% of phosphorus in a biological A/O process enhanced by zeolite. At the same time, the content of phosphorus could reach the effluent discharge standard.
{"title":"A Full-Scale Study On Phosphorus Removal From Biological A/O Process Enhanced by Zeolite","authors":"G. Cheng, Shan Xu, Ruifang Wang, Z. Wu, Fei-juan Zhang, Xiang-feng Huang","doi":"10.1109/ICBBE.2009.5162171","DOIUrl":"https://doi.org/10.1109/ICBBE.2009.5162171","url":null,"abstract":"In a full-scale test, zeolite enhanced the biological nitrification, but the nitrate of returning mixed-flow in the anaerobic process inhibited the release of the polyphosphate accumulation microorganisms and had little effect on the phosphorus removal in the biological A/O process. It was suggested that we use the method of chemical phosphorus removal in the process. Aluminium and ferric salts had a good effect on chemical phosphorus removal, and had no correlation with locations. When adding Al 2 (SO 4 ) 3 ldr18H 2 O, the molar ratio of the TP and Al at 1:1.5, the rate of phosphorus removal was more than 85%. When adding FeSO 4 ldr12H 2 O, the molar ratio of the TP and Fe at 1:1, the rate of phosphorus removal was more than 80%. When adding 20 mg/L FeSO 4 ldr12H 2 O and 30 mg/L Al 2 (SO 4 ) 3 ldr18H 2 O in the anaerobic process, the mixed phosphorus removal agent could remove nearly 90% of phosphorus in a biological A/O process enhanced by zeolite. At the same time, the content of phosphorus could reach the effluent discharge standard.","PeriodicalId":6430,"journal":{"name":"2009 3rd International Conference on Bioinformatics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74215233","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 : 2009-06-11DOI: 10.1109/ICBBE.2009.5163562
Guanghui Ding, Mihua Shao, Jing Zhang
Based on quantum chemical descriptors and topological descriptors, temperature-dependent predictive models for vapor pressures (P) of oxygen-containing polycyclic aromatic hydrocarbons (OPAHs) were developed following a variable selecetion procedure. The cross-validated Q 2 cum of the final model, 0.930, shows that the model has good predictive ability and robustness. In view of difficulties to measurements of P of OPAHs, the model could be used to estimate P values at different temperatures. The main factors influencing logP values of OPAHs, from important to less important, are hydrogen bond force, intermolecular dispersive interactions, electrostatic interactions, temperature and entropic factor.
{"title":"Temperature Dependent Predictive Models for Vapor Pressures of Oxygen-Containing Polycyclic Aromatic Hydrocarbons","authors":"Guanghui Ding, Mihua Shao, Jing Zhang","doi":"10.1109/ICBBE.2009.5163562","DOIUrl":"https://doi.org/10.1109/ICBBE.2009.5163562","url":null,"abstract":"Based on quantum chemical descriptors and topological descriptors, temperature-dependent predictive models for vapor pressures (P) of oxygen-containing polycyclic aromatic hydrocarbons (OPAHs) were developed following a variable selecetion procedure. The cross-validated Q 2 cum of the final model, 0.930, shows that the model has good predictive ability and robustness. In view of difficulties to measurements of P of OPAHs, the model could be used to estimate P values at different temperatures. The main factors influencing logP values of OPAHs, from important to less important, are hydrogen bond force, intermolecular dispersive interactions, electrostatic interactions, temperature and entropic factor.","PeriodicalId":6430,"journal":{"name":"2009 3rd International Conference on Bioinformatics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74254806","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 : 2009-06-11DOI: 10.1109/ICBBE.2009.5162167
N. Joglekar, R. Veljanovski, A. Zayegh, Jatin Mitra
This paper presents the design of a novel controller for a reconfigurable filter for the front end of an optical blood Oxygen sensor. The reconfigurability of the filter is dependant on the magnitude of the diode's current and is implemented with a feed forward loop from the ADC output. A relation between the output of the diode and the noise in the signal is proven in this paper. The reconfigurable filter enables a considerable amount of saving in power consumption and processing units and is a step towards implementing a portable and efficient blood gas analyzer for a point of care solution.
{"title":"A Design Proposal of a Reconfigurable Filter for an Optical Blood Oxygen Analyzer","authors":"N. Joglekar, R. Veljanovski, A. Zayegh, Jatin Mitra","doi":"10.1109/ICBBE.2009.5162167","DOIUrl":"https://doi.org/10.1109/ICBBE.2009.5162167","url":null,"abstract":"This paper presents the design of a novel controller for a reconfigurable filter for the front end of an optical blood Oxygen sensor. The reconfigurability of the filter is dependant on the magnitude of the diode's current and is implemented with a feed forward loop from the ADC output. A relation between the output of the diode and the noise in the signal is proven in this paper. The reconfigurable filter enables a considerable amount of saving in power consumption and processing units and is a step towards implementing a portable and efficient blood gas analyzer for a point of care solution.","PeriodicalId":6430,"journal":{"name":"2009 3rd International Conference on Bioinformatics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74567982","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}
Protein function determination is one of the most important issues in biology research. In this paper, a new method, which is based on logistic regression method, is introduced to predict protein function from protein-protein interaction data. In the proposed method, associations among different functions are taken into account by representing a protein using all the functional annotations of its interaction protein partners. We apply our method to a constructed data set for yeast based upon protein function classifications of FunCat scheme and upon the interaction networks collected from BioGrid. The results obtained by 3-fold cross-validation test show that the proposed method can obtain desirable results for protein function prediction and outperforms some existing approaches based on protein-protein interaction data.
{"title":"Using Logistic Regression Method to Predict Protein Function from Protein-Protein Interaction Data","authors":"Qingshan Ni, Zheng-Zhi Wang, Qingjuan Han, Gangguo Li, Xiaomin Wang, Guangyun Wang","doi":"10.1109/ICBBE.2009.5163737","DOIUrl":"https://doi.org/10.1109/ICBBE.2009.5163737","url":null,"abstract":"Protein function determination is one of the most important issues in biology research. In this paper, a new method, which is based on logistic regression method, is introduced to predict protein function from protein-protein interaction data. In the proposed method, associations among different functions are taken into account by representing a protein using all the functional annotations of its interaction protein partners. We apply our method to a constructed data set for yeast based upon protein function classifications of FunCat scheme and upon the interaction networks collected from BioGrid. The results obtained by 3-fold cross-validation test show that the proposed method can obtain desirable results for protein function prediction and outperforms some existing approaches based on protein-protein interaction data.","PeriodicalId":6430,"journal":{"name":"2009 3rd International Conference on Bioinformatics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74798311","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 : 2009-06-11DOI: 10.1109/ICBBE.2009.5162262
Jun Yu Li, Li Xie, Fubo Luan, J. Sheng, Qi Zhou
The abiotic degradation of 3 nitroaromatic compounds (NACs) by steel converter slag(SCS) with Fe(II) was investigated in this study. Experimental results showed that in aqueous solutions of steel converter slag, Fe(II) readily reduce nitrobenzene (NB), p-chloronitrobenzene (P-ClNB) and 2, 4-dinitrotoluene (2, 4DNT) to the corresponding anilines. The initial kinetics of the reduction could be well described by pseudo-first-order dynamical equation. The HPLC results illustrated that the reduction of NACs mainly involved with the nitro groups with the reduction pathway of: nitro- rarr nitroso- rarr hydroxamino- rarr amino-. Our findings suggested that Fe(II) adsorbed on SCS surfaces may play an important role in abiotic reduction of aromatic pollutants in anoxic environment such as constructed wetland or saturated soil aquifer where SCS is used as substrate.
{"title":"Abiotic Degradation of Nitroaromatic Compounds by Steel Converter Slag with Fe(II)","authors":"Jun Yu Li, Li Xie, Fubo Luan, J. Sheng, Qi Zhou","doi":"10.1109/ICBBE.2009.5162262","DOIUrl":"https://doi.org/10.1109/ICBBE.2009.5162262","url":null,"abstract":"The abiotic degradation of 3 nitroaromatic compounds (NACs) by steel converter slag(SCS) with Fe(II) was investigated in this study. Experimental results showed that in aqueous solutions of steel converter slag, Fe(II) readily reduce nitrobenzene (NB), p-chloronitrobenzene (P-ClNB) and 2, 4-dinitrotoluene (2, 4DNT) to the corresponding anilines. The initial kinetics of the reduction could be well described by pseudo-first-order dynamical equation. The HPLC results illustrated that the reduction of NACs mainly involved with the nitro groups with the reduction pathway of: nitro- rarr nitroso- rarr hydroxamino- rarr amino-. Our findings suggested that Fe(II) adsorbed on SCS surfaces may play an important role in abiotic reduction of aromatic pollutants in anoxic environment such as constructed wetland or saturated soil aquifer where SCS is used as substrate.","PeriodicalId":6430,"journal":{"name":"2009 3rd International Conference on Bioinformatics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74828182","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 : 2009-06-11DOI: 10.1109/ICBBE.2009.5162539
Peng Xu, Shaozhi Wu, S. Asgari, M. Kasprowicz, M. Bergsneider, Xiao Hu
Changes of ICP waveform morphology are characterized with different patients' states like hypertension, hydrocephalus and traumatic brain injury etc. Morphological clustering and analysis of ICP pulse (MOCAIP) approach is recently developed to extract ICP morphology feature, in which hierarchical clustering is used to extract the dominated pulse. In this paper, we evaluate the feasibility of using principle component analysis (PCA) and independent component analysis (ICA) to extract dominated pulse. The comparative study among clustering, PCA and ICP based approaches shows that PCA approach may be an alternative of clustering approach to extract dominated pulse in a faster fashion when dataset is of large size.
{"title":"Comparison of Different Approaches to ICP Dominated Pulse Extraction","authors":"Peng Xu, Shaozhi Wu, S. Asgari, M. Kasprowicz, M. Bergsneider, Xiao Hu","doi":"10.1109/ICBBE.2009.5162539","DOIUrl":"https://doi.org/10.1109/ICBBE.2009.5162539","url":null,"abstract":"Changes of ICP waveform morphology are characterized with different patients' states like hypertension, hydrocephalus and traumatic brain injury etc. Morphological clustering and analysis of ICP pulse (MOCAIP) approach is recently developed to extract ICP morphology feature, in which hierarchical clustering is used to extract the dominated pulse. In this paper, we evaluate the feasibility of using principle component analysis (PCA) and independent component analysis (ICA) to extract dominated pulse. The comparative study among clustering, PCA and ICP based approaches shows that PCA approach may be an alternative of clustering approach to extract dominated pulse in a faster fashion when dataset is of large size.","PeriodicalId":6430,"journal":{"name":"2009 3rd International Conference on Bioinformatics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78599300","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 : 2009-06-11DOI: 10.1109/ICBBE.2009.5162790
Chetan Kumar, Gang Li, A. Choudhary
Enzymes are proteins that catalyze bio-chemical reactions in different ways and play important roles in metabolic pathways. The exponential rise in sequences of new enzymes has necessitated developing methods that accurately predict their function. To address this problem, approaches that cluster enzymes based on their sequence and structural similarity have been applied, but are known to fail for dissimilar proteins that perform the same function. In this paper, we present a machine learning approach to accurately predict the main function class of enzymes based on a unique set of 73 sequence-derived features. Our features can be extracted using freely available online tools. We used different multi-class classifiers to categorize enzyme protein sequences into one of the NC-IUBMB defined six main function classes. Amongst the classifiers, Random Forest reported the best results with an overall accuracy of 88% and precision and recall in the range of 84% to 93% and 82% to 93% respectively. Our results compare favorably with existing methods, and in some cases report better performance. Random Forest has been proven to be a very efficient data mining algorithm. This paper is first in exploring their application to enzyme function prediction. The datasets can be accessed online at the location: http://cholera.ece.northwestern.edu/EnzyPredict.
{"title":"Enzyme Function Classification Using Protein Sequence Features and Random Forest","authors":"Chetan Kumar, Gang Li, A. Choudhary","doi":"10.1109/ICBBE.2009.5162790","DOIUrl":"https://doi.org/10.1109/ICBBE.2009.5162790","url":null,"abstract":"Enzymes are proteins that catalyze bio-chemical reactions in different ways and play important roles in metabolic pathways. The exponential rise in sequences of new enzymes has necessitated developing methods that accurately predict their function. To address this problem, approaches that cluster enzymes based on their sequence and structural similarity have been applied, but are known to fail for dissimilar proteins that perform the same function. In this paper, we present a machine learning approach to accurately predict the main function class of enzymes based on a unique set of 73 sequence-derived features. Our features can be extracted using freely available online tools. We used different multi-class classifiers to categorize enzyme protein sequences into one of the NC-IUBMB defined six main function classes. Amongst the classifiers, Random Forest reported the best results with an overall accuracy of 88% and precision and recall in the range of 84% to 93% and 82% to 93% respectively. Our results compare favorably with existing methods, and in some cases report better performance. Random Forest has been proven to be a very efficient data mining algorithm. This paper is first in exploring their application to enzyme function prediction. The datasets can be accessed online at the location: http://cholera.ece.northwestern.edu/EnzyPredict.","PeriodicalId":6430,"journal":{"name":"2009 3rd International Conference on Bioinformatics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78716028","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：