Pub Date : 2012-10-04DOI: 10.1109/BIBM.2012.6392701
Hao Jiang, W. Ching
Driven by the challenge of integrating large amount of experimental data obtained from biological research, computational biology and bioinformatics are growing rapidly. Machine learning methods, especially kernel methods with Support Vector Machines (SVMs) are very popular tools. In the perspective of kernel matrix, a technique namely Eigen-matrix translation has been introduced for protein data classification. The Eigen-matrix translation strategy owns a lot of nice properties while the nature of which needs further exploration. We propose that its importance lies in the dimension reduction of predictor attributes within the data set. This can therefore serve as a novel perspective for future research in dimension reduction problems.
{"title":"The role of Eigen-matrix translation in classification of biological datasets","authors":"Hao Jiang, W. Ching","doi":"10.1109/BIBM.2012.6392701","DOIUrl":"https://doi.org/10.1109/BIBM.2012.6392701","url":null,"abstract":"Driven by the challenge of integrating large amount of experimental data obtained from biological research, computational biology and bioinformatics are growing rapidly. Machine learning methods, especially kernel methods with Support Vector Machines (SVMs) are very popular tools. In the perspective of kernel matrix, a technique namely Eigen-matrix translation has been introduced for protein data classification. The Eigen-matrix translation strategy owns a lot of nice properties while the nature of which needs further exploration. We propose that its importance lies in the dimension reduction of predictor attributes within the data set. This can therefore serve as a novel perspective for future research in dimension reduction problems.","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84352083","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 : 2012-10-04DOI: 10.1109/BIBM.2012.6392704
I. Gkigkitzis, Xin-Hua Hu
The aim of this report is to provide a mathematical model of the mechanism for making binary fate decisions about cell death or survival, during and after type II photodynamic therapy (PDT) treatment, and to supply the logical design for this decision mechanism as an application of rate distortion theory to the biochemical processing of information by the physical system of a cell. Based on system biology models of the molecular interactions involved in the PDT processes previously established, and regarding a cellular decision-making system as a noisy communication channel, we use rate distortion theory to design a time dependent three dimensional Blahut-Arimoto algorithm where the input is a stimulus vector composed of the time dependent concentrations of three PDT related cell death signaling molecules and a cell fate decision as output. The molecular concentrations are determined by a group of rate equations. The output is the cell decision with a probability of cell survival or death. The optimality of the cell decision strategy is assessed by the cell survival probability, which might be modified to account for heterogeneous cell resistance to therapy.
{"title":"A model of cellular decision making in photodynamic therapy of cancer","authors":"I. Gkigkitzis, Xin-Hua Hu","doi":"10.1109/BIBM.2012.6392704","DOIUrl":"https://doi.org/10.1109/BIBM.2012.6392704","url":null,"abstract":"The aim of this report is to provide a mathematical model of the mechanism for making binary fate decisions about cell death or survival, during and after type II photodynamic therapy (PDT) treatment, and to supply the logical design for this decision mechanism as an application of rate distortion theory to the biochemical processing of information by the physical system of a cell. Based on system biology models of the molecular interactions involved in the PDT processes previously established, and regarding a cellular decision-making system as a noisy communication channel, we use rate distortion theory to design a time dependent three dimensional Blahut-Arimoto algorithm where the input is a stimulus vector composed of the time dependent concentrations of three PDT related cell death signaling molecules and a cell fate decision as output. The molecular concentrations are determined by a group of rate equations. The output is the cell decision with a probability of cell survival or death. The optimality of the cell decision strategy is assessed by the cell survival probability, which might be modified to account for heterogeneous cell resistance to therapy.","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85444328","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 : 2012-10-04DOI: 10.1109/BIBM.2012.6392629
Ruobing Chen, K. Scheinberg, B. Chen
We describe an optimization-based method that seeks the superposition of ligand binding cavities that maximizes their overlapping volume. Our method, called DFO-VASP, iteratively uses Boolean set operations to evaluate overlapping volume in intermediate superpositions while searching for the maximal one. Our results verify that the superpositions identified are biologically relevant, and demonstrate that DFO-VASP generally discovers cavity superpositions with similar or occasionally larger overlapping volume than those of superpositions generated with existing means.
{"title":"Aligning ligand binding cavities by optimizing superposed volume","authors":"Ruobing Chen, K. Scheinberg, B. Chen","doi":"10.1109/BIBM.2012.6392629","DOIUrl":"https://doi.org/10.1109/BIBM.2012.6392629","url":null,"abstract":"We describe an optimization-based method that seeks the superposition of ligand binding cavities that maximizes their overlapping volume. Our method, called DFO-VASP, iteratively uses Boolean set operations to evaluate overlapping volume in intermediate superpositions while searching for the maximal one. Our results verify that the superpositions identified are biologically relevant, and demonstrate that DFO-VASP generally discovers cavity superpositions with similar or occasionally larger overlapping volume than those of superpositions generated with existing means.","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79847029","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 : 2012-10-04DOI: 10.1109/BIBMW.2012.6470276
Brian S. Olson, Amarda Shehu
The protein conformational space is characterized as a multi-dimensional funnel-like energy surface with conformations corresponding to the native state around the energy basin. The dimensionally and ruggedness of this energy surface are primary why computationally determining the biologically active or native state of a protein remains a difficult challenge. A common template among structure prediction protocols begins by sampling many local minima in the energy surface. Basin Hopping (BH) has emerged as a suitable framework for effectively sampling these coarse grained local minima. BH consists of a series structural perturbations followed by minimizations, forming a trajectory of local minima with the Metropolis criterion biasing it towards increasingly low-energy minima.
{"title":"Jumping low, jumping high: Controlling hopping in the protein energy surface","authors":"Brian S. Olson, Amarda Shehu","doi":"10.1109/BIBMW.2012.6470276","DOIUrl":"https://doi.org/10.1109/BIBMW.2012.6470276","url":null,"abstract":"The protein conformational space is characterized as a multi-dimensional funnel-like energy surface with conformations corresponding to the native state around the energy basin. The dimensionally and ruggedness of this energy surface are primary why computationally determining the biologically active or native state of a protein remains a difficult challenge. A common template among structure prediction protocols begins by sampling many local minima in the energy surface. Basin Hopping (BH) has emerged as a suitable framework for effectively sampling these coarse grained local minima. BH consists of a series structural perturbations followed by minimizations, forming a trajectory of local minima with the Metropolis criterion biasing it towards increasingly low-energy minima.","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83701364","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 : 2012-10-04DOI: 10.1109/BIBMW.2012.6470320
Xue-Qiang Zeng, Guozheng Li
As a high dimensional problem, analysis of microarray data sets is a challenging task, where many weakly relevant or redundant features hurt generalization performance of classifiers. The previous works used redundant feature detection methods to select discriminative compact gene set, which only considered the relationship among features, not the redundancy of classification ability among features. Here, we propose a novel algorithm named RESI (Redundant fEature Selection depending on Instance), which considers label information in the measure of feature subset redundancy. Experimental results on benchmark data sets show that RESI performs better than the previous state-of-arts algorithms on redundant feature selection methods like mRMR.
{"title":"A supervised solution for redundant feature detection depending on instances","authors":"Xue-Qiang Zeng, Guozheng Li","doi":"10.1109/BIBMW.2012.6470320","DOIUrl":"https://doi.org/10.1109/BIBMW.2012.6470320","url":null,"abstract":"As a high dimensional problem, analysis of microarray data sets is a challenging task, where many weakly relevant or redundant features hurt generalization performance of classifiers. The previous works used redundant feature detection methods to select discriminative compact gene set, which only considered the relationship among features, not the redundancy of classification ability among features. Here, we propose a novel algorithm named RESI (Redundant fEature Selection depending on Instance), which considers label information in the measure of feature subset redundancy. Experimental results on benchmark data sets show that RESI performs better than the previous state-of-arts algorithms on redundant feature selection methods like mRMR.","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75872028","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 : 2012-10-04DOI: 10.1109/BIBMW.2012.6470270
Yu Zhang, Xiuwen Liu, J. Dennis
Nucleosome is the basic unit of DNA in eukaryotic cells. As nucleosomes limit the accessibility of the wrapped DNA to transcription factors and other DNA-binding proteins, their positions play an essential role in regulations of gene activities. Experiments have indicated that DNA sequence strongly influences nucleosome positioning by enhancing or reducing their binding affinity to nucleosomes, therefore providing an intrinsic cell regulatory mechanism. While some sequence features are known to be nucleosome forming or nucleosome inhibiting, however, existing models have limited accuracy in predicting quantitatively nucleosomes occupancy (i.e., statistical nucleosome positioning) based on DNA sequence. In this paper, we propose new quantitative models for DNA sequence-based nucleosome-occupancy prediction based on dinucleotide-matching features, where the parameters are learned through regression algorithms. Experimental results on a genome-wide set of yeast dataset show that our models give more accurate predictions than existing models.
{"title":"Quantitative models for statistical nucleosome occupancy prediction","authors":"Yu Zhang, Xiuwen Liu, J. Dennis","doi":"10.1109/BIBMW.2012.6470270","DOIUrl":"https://doi.org/10.1109/BIBMW.2012.6470270","url":null,"abstract":"Nucleosome is the basic unit of DNA in eukaryotic cells. As nucleosomes limit the accessibility of the wrapped DNA to transcription factors and other DNA-binding proteins, their positions play an essential role in regulations of gene activities. Experiments have indicated that DNA sequence strongly influences nucleosome positioning by enhancing or reducing their binding affinity to nucleosomes, therefore providing an intrinsic cell regulatory mechanism. While some sequence features are known to be nucleosome forming or nucleosome inhibiting, however, existing models have limited accuracy in predicting quantitatively nucleosomes occupancy (i.e., statistical nucleosome positioning) based on DNA sequence. In this paper, we propose new quantitative models for DNA sequence-based nucleosome-occupancy prediction based on dinucleotide-matching features, where the parameters are learned through regression algorithms. Experimental results on a genome-wide set of yeast dataset show that our models give more accurate predictions than existing models.","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81396575","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 : 2012-10-04DOI: 10.1109/BIBMW.2012.6470298
Hailong Zhu, R. Rao, Luonan Chen
A crucial work of investigating the mechanisms of cancer development is to unraveling the dynamic nature of gene regulation during the disease process. However, reconstruction of dynamic gene regulatory network requires time-sequence samples of a biological process, which are not available for many bio-medical problems. In this paper, we propose a dynamic cascaded method to reconstruct dynamic gene networks from sample-based transcriptional data. Our method is based on two biologically plausible assumptions, which can characterise the dynamic and continuous nature of gene transcription. Our approach was successfully applied to reconstruct the dynamic gene networks of hepatocellular carcinoma (HCC) progression. The derived HCC networks were verified by functional analysis and network enrichment analysis.
{"title":"Reconstructing dynamic gene regulatory network for the development process of hepatocellular carcinoma","authors":"Hailong Zhu, R. Rao, Luonan Chen","doi":"10.1109/BIBMW.2012.6470298","DOIUrl":"https://doi.org/10.1109/BIBMW.2012.6470298","url":null,"abstract":"A crucial work of investigating the mechanisms of cancer development is to unraveling the dynamic nature of gene regulation during the disease process. However, reconstruction of dynamic gene regulatory network requires time-sequence samples of a biological process, which are not available for many bio-medical problems. In this paper, we propose a dynamic cascaded method to reconstruct dynamic gene networks from sample-based transcriptional data. Our method is based on two biologically plausible assumptions, which can characterise the dynamic and continuous nature of gene transcription. Our approach was successfully applied to reconstruct the dynamic gene networks of hepatocellular carcinoma (HCC) progression. The derived HCC networks were verified by functional analysis and network enrichment analysis.","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82426518","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 : 2012-10-04DOI: 10.1109/BIBMW.2012.6470351
Qingsheng Yang, Z. Gu, Zhenhua Xu, Quanxin Chen
This study is to explore the rule of acupoint heat-sensitization within patients who suffer Bell's palsy. Probe the rule of acupoint heat-sensitization within patients suffer Bell's palsy by recording the phenomenon and contrasting the frequency of acupoints, meridians, patterns of manifestation between healthy control volunteers and patients. We found that there was statistical difference between two groups on the frequency of acupoint heat-sensitization phenomenon (P<;0.01), but not among different types of TCM syndrome when compared on the occurrence rate, patterns of manifestation (the top five patterns: blended sense, diathermanous sense, thermolytic sense, orderly transmission along channels, enjoying the thermal sensation), distribution of meridians (the top five channels: meridian of FOOT-YANG MING, HAND-SHAO YANG, FOOT-SHAO YANG, HAND-TAI YANG, HAND-YANG MING) and distribution of acupuncture points (the five top points: YIFENG(SJ17), XIAGUAN(ST7), QUANLIAO(SL18), YANGBAI(GB14), HEGU(LM)) (P>0.05). Thus we conclude that the frequency of acupoint heat-sensitization phenomenon within Bell's palsy patients is higher than normal volunteers, and the difference of patterns of manifestation, distribution of acupoints and meridians are all associated with channels, but not with the TCM syndromes.
{"title":"Clinical research on rule of acupoint heat-sensitization within patients suffer Bell's palsy","authors":"Qingsheng Yang, Z. Gu, Zhenhua Xu, Quanxin Chen","doi":"10.1109/BIBMW.2012.6470351","DOIUrl":"https://doi.org/10.1109/BIBMW.2012.6470351","url":null,"abstract":"This study is to explore the rule of acupoint heat-sensitization within patients who suffer Bell's palsy. Probe the rule of acupoint heat-sensitization within patients suffer Bell's palsy by recording the phenomenon and contrasting the frequency of acupoints, meridians, patterns of manifestation between healthy control volunteers and patients. We found that there was statistical difference between two groups on the frequency of acupoint heat-sensitization phenomenon (P<;0.01), but not among different types of TCM syndrome when compared on the occurrence rate, patterns of manifestation (the top five patterns: blended sense, diathermanous sense, thermolytic sense, orderly transmission along channels, enjoying the thermal sensation), distribution of meridians (the top five channels: meridian of FOOT-YANG MING, HAND-SHAO YANG, FOOT-SHAO YANG, HAND-TAI YANG, HAND-YANG MING) and distribution of acupuncture points (the five top points: YIFENG(SJ17), XIAGUAN(ST7), QUANLIAO(SL18), YANGBAI(GB14), HEGU(LM)) (P>0.05). Thus we conclude that the frequency of acupoint heat-sensitization phenomenon within Bell's palsy patients is higher than normal volunteers, and the difference of patterns of manifestation, distribution of acupoints and meridians are all associated with channels, but not with the TCM syndromes.","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90338331","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 : 2012-10-04DOI: 10.1109/BIBM.2012.6392625
J. P. Cleveland, J. Rose
The effectiveness of de novo peptide sequencing algorithms depends on the quality of MS/MS spectra. Since most of the peaks in a spectrum are uninterpretable `noise' peaks it is necessary to carefully pre-filter the spectra to identify the `signal' peaks that likely correspond to b-/y-ions. Selecting the optimal set of peaks for candidate peptide generation is essential for obtaining accurate results. A careful balance must be maintained between the precision and recall of peaks that are selected for further processing and candidate peptide generation. If too many peaks are selected the search space will be too large and the problem becomes intractable. If too few peaks are selected cleavage sites will be missed, the resulting candidate peptides will have large gaps, and sequencing results will be poor. For this reason pre-filtering of MS/MS spectra and accurate selection of peaks for peptide candidate generation is essential to any de novo peptide sequencing algorithm. We present a novel neural network approach for the selection of b-/y-ions using known fragmentation characteristics, and leveraging neural network probability estimates of flanking and complementary ions. We show a significant improvement in precision and recall of peaks corresponding to b-/y-ions and a reduction in search space over approaches used by other de novo peptide sequencing algorithms.
{"title":"A neural network approach to the identification of b-/y-ions in MS/MS spectra","authors":"J. P. Cleveland, J. Rose","doi":"10.1109/BIBM.2012.6392625","DOIUrl":"https://doi.org/10.1109/BIBM.2012.6392625","url":null,"abstract":"The effectiveness of de novo peptide sequencing algorithms depends on the quality of MS/MS spectra. Since most of the peaks in a spectrum are uninterpretable `noise' peaks it is necessary to carefully pre-filter the spectra to identify the `signal' peaks that likely correspond to b-/y-ions. Selecting the optimal set of peaks for candidate peptide generation is essential for obtaining accurate results. A careful balance must be maintained between the precision and recall of peaks that are selected for further processing and candidate peptide generation. If too many peaks are selected the search space will be too large and the problem becomes intractable. If too few peaks are selected cleavage sites will be missed, the resulting candidate peptides will have large gaps, and sequencing results will be poor. For this reason pre-filtering of MS/MS spectra and accurate selection of peaks for peptide candidate generation is essential to any de novo peptide sequencing algorithm. We present a novel neural network approach for the selection of b-/y-ions using known fragmentation characteristics, and leveraging neural network probability estimates of flanking and complementary ions. We show a significant improvement in precision and recall of peaks corresponding to b-/y-ions and a reduction in search space over approaches used by other de novo peptide sequencing algorithms.","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87531277","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 : 2012-10-04DOI: 10.1109/BIBM.2012.6392698
Shuguang Wang, M. Hauskrecht
In this paper, we present a new approach that lets us extract, and represent relations among terms (concepts) in the documents and uses these relations to support various document analysis applications. Our approach works by building a graph of local co-occurrence relations among terms that are extracted directly from text and by defining a global similarity metric among these terms and sets of terms using the graph and its connectivity. We demonstrate the benefit of the approach on the problem of MeSH keyword annotation of documents based on their abstracts.
{"title":"Keyword annotation of biomedicai documents with graph-based similarity methods","authors":"Shuguang Wang, M. Hauskrecht","doi":"10.1109/BIBM.2012.6392698","DOIUrl":"https://doi.org/10.1109/BIBM.2012.6392698","url":null,"abstract":"In this paper, we present a new approach that lets us extract, and represent relations among terms (concepts) in the documents and uses these relations to support various document analysis applications. Our approach works by building a graph of local co-occurrence relations among terms that are extracted directly from text and by defining a global similarity metric among these terms and sets of terms using the graph and its connectivity. We demonstrate the benefit of the approach on the problem of MeSH keyword annotation of documents based on their abstracts.","PeriodicalId":6392,"journal":{"name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83649422","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：