Identifying Relevant Data for a Biological Database: Handcrafted Rules versus Machine Learning

Sehgal, Aditya Kumar; Das, Sanmay; Noto, Keith; Saier, Milton H.; Elkan, Charles

doi:10.1109/tcbb.2009.83

Cited by 11 publications

(6 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We have: Incorporated an improved administration page, built-in semi-automatic machine learning tools ( 11 ) and user contributions, allowing protein history tracking, see Wakabayashi et al ( 10 ). Updated software to BLAST 2.2.27.…”

Section: Recent Technical Improvements (2011–13)mentioning

confidence: 99%

The Transporter Classification Database

et al. 2013

View full text Add to dashboard Cite

The Transporter Classification Database (TCDB; http://www.tcdb.org) serves as a common reference point for transport protein research. The database contains more than 10 000 non-redundant proteins that represent all currently recognized families of transmembrane molecular transport systems. Proteins in TCDB are organized in a five level hierarchical system, where the first two levels are the class and subclass, the second two are the family and subfamily, and the last one is the transport system. Superfamilies that contain multiple families are included as hyperlinks to the five tier TC hierarchy. TCDB includes proteins from all types of living organisms and is the only transporter classification system that is both universal and recognized by the International Union of Biochemistry and Molecular Biology. It has been expanded by manual curation, contains extensive text descriptions providing structural, functional, mechanistic and evolutionary information, is supported by unique software and is interconnected to many other relevant databases. TCDB is of increasing usefulness to the international scientific community and can serve as a model for the expansion of database technologies. This manuscript describes an update of the database descriptions previously featured in NAR database issues.

show abstract

Section: Recent Technical Improvements (2011–13)mentioning

confidence: 99%

The Transporter Classification Database

et al. 2013

View full text Add to dashboard Cite

show abstract

“…But the tree constructed may become too large and it has Oversensivity to training set. Practical machine learning approaches for identification of MEDLINE documents and Swiss-Prot/TrEMBL protein records have been described in [9]. This also involves incorporation of those into TCDB which is a biological repository for transport proteins.…”

Section: Literature Surveymentioning

confidence: 99%

String Kernel Approach for Efficient Extraction of Medical Relations

Vrinda¹,

Venkatesan²

2015

IJCA

View full text Add to dashboard Cite

This paper presents a methodology for building an application that can classify healthcare information. It extracts informative sentences from medical papers that mentions about diseases and treatments, and then recognizes semantic relations that exist between the entities in the informative sentences. Support Vector Machine algorithm with String Kernel is used for relation identification. The proposed system avoids unnecessary information and gives the user disease and Treatment related sentences from medical pages. Evaluation results for this approach show that the proposed methodology obtains reliable results. The string kernel approach is also compared with naïve bayes approach and it was found that string kernel approach outperforms naïve bayes method for classification. This technique can be integrated with any medical management system to make good decisions and in patient management system by automatically mining the biomedical information from digital repositories. This system enables easy access to medical information in rural areas where there is a relative shortage of physicians. General TermsClassification, Machine learning.

show abstract

“…Whenever a con-causal relation between different data sources exists, but it is not clear how to design and parametrize a direct algorithm to exploit such relation, resorting to some machine learning technique is a natural choice. In fact, given a reasonable feature selection, learning techniques have proven to be often more effective in classification tasks than manually crafted solution that exploit a direct knowledge of the problem domain [3,30]. We decided to address the issue of blob-device association in terms of a non-probabilistic binary classification problem.…”

Section: Identification By Learningmentioning

confidence: 99%

Using multiple sensors for reliable markerless identification through supervised learning

Albarelli

Bergamasco

Celentano

et al. 2013

Machine Vision and Applications

View full text Add to dashboard Cite

In many interaction models involving an active surface, there is a need to identify the specific object that performs an action. This is the case, for instance, when interactive contents are selected through differently shaped physical objects, or when a two-way communication is sought as the result of a touch event. When the technological facility is based on image processing, fiducial markers become the weapon of choice in order to associate a tracked object to its identity. Such approach, however, requires a clear and unoccluded view of the marker itself, which is not always the case. We came across this kind of hurdle during the design of a very large multi-touch interactive table. In fact, the thickness of the glass and the printed surface, which were required for our system, produced both blurring and occlusion at a level such that markers were completely unreadable. To overcome these limitations we propose an identification approach based on SVM that exploits the correlation between the optical features of the blob, as seen by the camera, and the data coming from active sensors available on the physical object that interacts with the table. This way, the recognition has been cast into a classification problem that can be solved through a standard

show abstract

Identifying Relevant Data for a Biological Database: Handcrafted Rules versus Machine Learning

Cited by 11 publications

References 30 publications

The Transporter Classification Database

The Transporter Classification Database

String Kernel Approach for Efficient Extraction of Medical Relations

Using multiple sensors for reliable markerless identification through supervised learning

Contact Info

Product

Resources

About