Extracting unrecognized gene relationships from the biomedical literature via matrix factorizations

Kim, Hyunsoo; Park, Haesun; Drake, Barry

doi:10.1186/1471-2105-8-s9-s6

Cited by 15 publications

(10 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The current state of data visualization revolves around the representation of data matrices—an ensemble of data points. For example, when data is sparse and slight information loss is not an issue, a common practice is to perform Principal Components Analysis (PCA) to extract three or fewer components and then graph the resulting data points in a three-dimensional scatterplot (Wold et al, 1987; Kim et al, 2007). Other methods have been developed for even larger data sets.…”

Section: Resultsmentioning

confidence: 99%

Plurigon: three dimensional visualization and classification of high-dimensionality data

et al. 2013

View full text Add to dashboard Cite

High-dimensionality data is rapidly becoming the norm for biomedical sciences and many other analytical disciplines. Not only is the collection and processing time for such data becoming problematic, but it has become increasingly difficult to form a comprehensive appreciation of high-dimensionality data. Though data analysis methods for coping with multivariate data are well-documented in technical fields such as computer science, little effort is currently being expended to condense data vectors that exist beyond the realm of physical space into an easily interpretable and aesthetic form. To address this important need, we have developed Plurigon, a data visualization and classification tool for the integration of high-dimensionality visualization algorithms with a user-friendly, interactive graphical interface. Unlike existing data visualization methods, which are focused on an ensemble of data points, Plurigon places a strong emphasis upon the visualization of a single data point and its determining characteristics. Multivariate data vectors are represented in the form of a deformed sphere with a distinct topology of hills, valleys, plateaus, peaks, and crevices. The gestalt structure of the resultant Plurigon object generates an easily-appreciable model. User interaction with the Plurigon is extensive; zoom, rotation, axial and vector display, feature extraction, and anaglyph stereoscopy are currently supported. With Plurigon and its ability to analyze high-complexity data, we hope to see a unification of biomedical and computational sciences as well as practical applications in a wide array of scientific disciplines. Increased accessibility to the analysis of high-dimensionality data may increase the number of new discoveries and breakthroughs, ranging from drug screening to disease diagnosis to medical literature mining.

show abstract

Section: Resultsmentioning

confidence: 99%

Plurigon: three dimensional visualization and classification of high-dimensionality data

et al. 2013

View full text Add to dashboard Cite

show abstract

“…Kim et al attempted to retrieve unrecognized gene relationships by using LSI along with Non-Negative Matrix Factorization (NMF), another matrix factorization method (Kim et al, 2007). Gene retrieval was evaluated on manually created test sets based on precision and recall, showing that LSI- and NMF-based methods vastly outperformed co-occurrence methods.…”

Section: Latent Links For Literature-based Biomedical Discoverymentioning

confidence: 99%

“…Second, LSI's ability to reduce dimensionality allows for a better visualization of high-dimensionality points that exceed the realm of physical space. For example, LSI can be used to reduce the number of dimensions in vector space to one, two, or three so that each point is graphable in three-dimensional space (Kim et al, 2007). A major disadvantage to this method is that three dimensions is typically not an optimal value for k , so information loss will be significant.…”

Section: Visualization Of High-dimensional Datamentioning

confidence: 99%

“…Conversely, a low k value suffers from the danger of discarding crucial, distinguishing concepts in the data. This problem can be ameliorated to a certain extent by optimizing the precision and recall of LSI retrieval with a priori knowledge (Dumais, 2004; Kim et al, 2007). Analysis of the variance captured by the current dimensions, similar to that of PCA, is another method frequently employed (Cangelosi and Goriely, 2007).…”

Section: Limitations Of Lsi-based Analysesmentioning

confidence: 99%

See 1 more Smart Citation

Effective use of latent semantic indexing and computational linguistics in biological and biomedical applications

et al. 2013

View full text Add to dashboard Cite

Text mining is rapidly becoming an essential technique for the annotation and analysis of large biological data sets. Biomedical literature currently increases at a rate of several thousand papers per week, making automated information retrieval methods the only feasible method of managing this expanding corpus. With the increasing prevalence of open-access journals and constant growth of publicly-available repositories of biomedical literature, literature mining has become much more effective with respect to the extraction of biomedically-relevant data. In recent years, text mining of popular databases such as MEDLINE has evolved from basic term-searches to more sophisticated natural language processing techniques, indexing and retrieval methods, structural analysis and integration of literature with associated metadata. In this review, we will focus on Latent Semantic Indexing (LSI), a computational linguistics technique increasingly used for a variety of biological purposes. It is noted for its ability to consistently outperform benchmark Boolean text searches and co-occurrence models at information retrieval and its power to extract indirect relationships within a data set. LSI has been used successfully to formulate new hypotheses, generate novel connections from existing data, and validate empirical data.

show abstract

“…There are many physical problems that the observations are formed by addition of non-negative components. Some of the examples include photon counting processes (Woolfe et al, 2011), gene relations (Kim et al, 2007), text mining (Park & Kim, 2006), and some computer vision applications (Lee & Seung, 1999).…”

Section: Non-negative Matrix Factorizationmentioning

confidence: 99%

Digitally adjusting chromogenic dye proportions in brightfield microscopy images

Bilgin

Rittscher

Filkins

et al. 2012

Journal of Microscopy

View full text Add to dashboard Cite

SummaryWe present an algorithm to adjust the contrast of individual dyes from colour (red-green-blue) images of dye mixtures. Our technique is based on first decomposing the colour image into individual dye components, then adjusting each of the dye components and finally mixing the individual dyes to generate colour images. Specifically in this paper, we digitally adjust the staining proportions of hematoxylin and eosin (H&E) chromogenic dyes in tissue images. We formulate the physical dye absorption process as a non-negative mixing equation, and solve the individual components using non-negative matrix factorisation (NMF). Our NMF formulation includes camera dark current in addition to the mixing proportions and the individual H and E components. The novelty of our approach is to adjust the dye proportions while preserving the color of nonlinear dye interactions, such as pigments and red blood cells. In this paper we present results for only H&E images, our technique can easily be extended to other staining techniques.

show abstract

Extracting unrecognized gene relationships from the biomedical literature via matrix factorizations

Cited by 15 publications

References 22 publications

Plurigon: three dimensional visualization and classification of high-dimensionality data

Plurigon: three dimensional visualization and classification of high-dimensionality data

Effective use of latent semantic indexing and computational linguistics in biological and biomedical applications

Digitally adjusting chromogenic dye proportions in brightfield microscopy images

Contact Info

Product

Resources

About