Karyagyna A.S.,Russian Academy of Medical Sciences |
Vassiliev M.O.,Russian Academy of Medical Sciences |
Ershova A.S.,Russian Academy of Medical Sciences |
Nurtdinov R.N.,French Institute of Health and Medical Research |
Journal of Bioinformatics and Computational Biology | Year: 2010
Affymetrix microarrays measure gene expression based on the intensity of hybridization of a panel of oligonucleotide probes (probe set) with mRNA. The signals from all probes within a probe set are converted into a single measure that represents the expression value of a gene. This step diminishes the number of independently measured parameters and eliminates from consideration individual "good-working" probes. We propose a new feature selection algorithm (Probe Level Universal Search or PLUS algorithm) for probe-level analysis of gene expression datasets. The algorithm evaluates the intensities of perfect-match Affymetrix probes individually and selects probes that allow one to distinguish two given classes of samples. The algorithm was used to differentiate the samples according to their gender ("gender differentiation"). The universal gender differentiating set of 3′ Gene Affymetrix microarray probes was selected; the set consists of 38 probes from XIST gene of X-chromosome and 17 probes from five Y-chromosome genes: RPS4Y1, EIF1A, DDX3Y, JARID1D and USP9Y. The selection procedure based on the probes selected by PLUS algorithm differentiates the sex chromosome karyotype of the sample, reveals samples with incorrect gender labels and samples from patients with hereditary syndromes or cancer-associated chromosome abnormalities. © 2010 Imperial College Press.
News Article | March 3, 2015
Parascript today announced a partnership with OneTouchPoint, which is integrating the Parascript software platform as part of its business process outsourcing services. Together, they are focused on helping their clients achieve greater compliance, efficiency, and cost savings by streamlining processes and workflows. OneTouchPoint will leverage Parascript technologies to facilitate effective enterprise-wide information management. “Parascript has delivered phenomenal results for their clients, including the U.S. Postal Service and eight of the ten largest banks in the country. We look forward to providing Parascript software to meet our customers’ high-volume document processing needs,” said Jason Wienke, General Manager of Digital Services at OneTouchPoint. “This encompasses a wide range of activities from processing invoices, insurance claims, survey cards, explanation of benefits, applications, to checks and remittance documents.” Unstructured documents and data from disparate sources impact efficiencies in business processes at each level across almost every enterprise. Processing and accessing information from these sources can require extensive manual data entry and wasted time spent searching for hard-to-access documents. To meet this challenge for greater efficiencies, Parascript technology facilitates both backfile digital conversion projects and front-end document processing applications. OneTouchPoint clients are likely to see significant cost and productivity benefits by automating rote, labor-intensive data capture and data location activities, according to Wienke. “Our partnership with OneTouchPoint is precisely the type of strategic relationship that we look for in a partner because it leads to the most innovative and comprehensive enterprise content management solutions,” said Mark Gallagher, VP of Sales at Parascript. For more about this partnership, go to the OneTouchPoint press release. About Parascript, LLC Parascript automates data-intensive image and document processing activities, enabling organizations to increase efficiency and productivity at reduced cost. Parascript software processes any document with any data from any source with its easy-to-use, image-based analysis, classification, data location, and extraction technology. More than 100 billion documents for financial services, government organizations, and the healthcare and life sciences industry are analyzed annually by Parascript software. Our OEM and value-added reseller network partners integrate and distribute Parascript software in the US and across the world. Visit Parascript online at http://www.Parascript.com About OneTouchPoint OneTouchPoint aggregates the resources of industry-leading solution providers to deliver true, end-to-end document process outsourcing solutions, including digital conversion, enterprise content management and business process automation services. With offices and production facilities located throughout the U.S., OneTouchPoint has onsite or outsource capabilities focused on providing comprehensive business process services that address key applications throughout the enterprise, including accounts payable automation, mailroom automation, survey processing, customer onboarding, records management and invoice processing. OneTouchPoint is also a national provider of marketing, print, mail, distribution, fulfillment and eBusiness solutions. For more information, visit us online at http://www.1touchpointdigital.com
News Article | May 26, 2015
Parascript, the industry innovator in advanced data location, extraction, and classification, today announced the next generation of document classification software. Parascript Document Classification 2.0 empowers business users to leverage auto-classification without programming experience. “We’re placing the power of document auto-classification in the hands of business users,” Mark Gallagher, Vice President of Sales, said. “On the one hand, you don’t have your team spending hours manually reviewing and organizing documents in the system. On the other hand, you don’t have to employ a team of programmers to auto-classify your documents. It’s advanced classification functionality that’s straightforward to use.” Parascript Document Classification 2.0 advances classification beyond batch classification, which is limited to organizing pre-defined sets of documents in an established order. Unlike other auto-classification solutions, Parascript Document Classification 2.0 provides the following unique benefits: High Accuracy Classification. Most classification software relies on one type of classification method over another, which limits the types of documents and how accurately they can be processed. Parascript drew upon its advanced data location and extraction techniques along with its state-of-the-art image analysis capabilities to develop Document Classification. It automatically applies multiple techniques including algorithms that process visual, text, or glyph-like elements such as signatures or logos in order to classify documents based upon all the available information. All of this allows results to be highly accurate with very low error rates. Discovery Via Auto-Classification. Large organizations have many different types of documents and need to avoid expending employee resources to identify all document types. When applying Parascript Document Classification, it’s not necessary to manually review repositories for samples. By document clustering, the software groups documents automatically without samples. Once samples are identified, it is no longer necessary to have examples of every document variant. For example with invoices, Parascript Document Classification can use a few samples, after which it can classify an invoice as an invoice and any variation of that invoice. Dynamic Organization and Ongoing Maintenance. Engaging the organization’s Subject Matter Experts (SMEs) to organize, classify, and maintain the taxonomies with ever-changing business rules are highly labor-intensive, ongoing activities that divert SMEs from their core tasks. Parascript Document Classification is automated and trainable. With a few samples, the software automatically learns the features of a particular document class. The software applies the rules so that users don’t have to, establishes the necessary metadata, and is rapidly trained to classify hundreds of different documents all in random order. Rapid Set-Up and Ease of Use. Organizations can be up and running with advanced classification capabilities in weeks not months. SMEs can use Parascript Document Classification without any programming or coding background. “For the first time, enterprises can affordably and effectively address their document organization workload,” Greg Council, VP of Marketing and Product Management said. “With Parascript Document Classification, enterprises gain a comprehensive understanding of their document data lakes so that business users no longer expend resources manually organizing and reorganizing documents. Document data can now be optimally used, governed, defined, and secured.” Auto-classification is included in the general availability of Parascript Document Classification 2.0 and also available as an option with FormXtra Capture 6.1. For more information about Classification 2.0, visit Parascript. About Parascript, LLC Parascript automates data-intensive image and document processing activities, enabling organizations to increase efficiency and productivity at reduced cost. Parascript software processes any document with any data from any source with its easy-to-use, image-based analysis, classification, data location, and extraction technology. More than 100 billion documents for financial services, government organizations, and the healthcare and life sciences industry are analyzed annually by Parascript software. Our OEM and value-added reseller network partners integrate and distribute Parascript software in the US and across the world. Visit Parascript online at http://www.Parascript.com
Parascript | Date: 2010-04-22
Methods and systems are disclosed to aid in the detection of areas of interest in an image. Multiple image recognition processes analyze the image and identify areas of interest. The identified areas of interest are compared to determine confidence values for each identified area of interest using a voting process. The confidence values may be used in determining areas of increased interest which are highlighted on the image. In embodiments, identified areas of interest meeting a certain threshold requirement are selected as areas of increased interest. In other embodiments, new areas of increased interest are created by combining areas of interest. Embodiments of the disclosed methods and system may be used to aid in the detection of cancer in mammogram images.
Parascript | Date: 2012-10-25
Computer software, namely, indicia recognition software for use in authenticating, tracking, managing and processing postal markings and postage payment indicia on parcels, letters, and flats.