Bio Saga Blog - A Chronicle of Life Sciences & Informatics

Python Text Processing with NTLK 2.0 Cookbook - Ebook Free Download

C SHALS is the premier annual event focused on the use of semantic technologies in the pharmaceutical industry, including hospitals/healthcare institutions and academic research labs. Rather than a Semantic Web conference, CSHALS focuses on specific applications of semantic technologies. Attendees will gain a better understanding of where the field is headed and be prepared to advance with the field. Themes of past CSHALS conferences: Clinical Information Management Discovery Information Integration Integrated Healthcare and Semantics in Electronic Health Records Translational Medicine / Safety Search and Document Management/Business Intelligence/Text Mining Text Mining/ Information Extraction For further details visit   Share |

Courtesy: Dr Raghava &  Bioclues PubDNA Finder is an online repository to link PubMed Central manuscripts to the sequences of nucleic acids appearing in them. It extends the search capabilities provided by PubMed Central by enabling researchers to perform advanced searches involving sequences of nucleic acids. This includes, among other features, (1) searching for papers mentioning one or more specific sequences of nucleic acids and (2) retrieving the genetic sequences appearing in different articles. These additional query capabilities are provided by a searchable index that was created by using the full text of the 176672 papers available at PubMed Central at the time of writing and the sequences of nucleic acids appearing in them. To automatically  extract the genetic sequences occurring in each paper an original method has been developed. The database is updated monthly by automatically connecting to the PubMed Central FTP site to retrieve and index...

Lockheed Martin is working with researchers at Johns Hopkins University and medical informatics firm Sage Analytica to mine a "unique" set of medical records with the aim of integrating clinical and genomic data for prostate cancer research. The researchers are using Lockheed Martin's rule-based natural language processing platform, called ClinRead, to extract phenotypic descriptors from a set of clinical records tracking 33 men with metastatic prostate cancer for over 15 years before they succumbed to the disease. (Read Full Article)

Indian Life Sciences Informatics Company, Molecular Connections announced today, that their XTractor Premium platform now has more that 503,985 " Expert " annotated biomedical facts from literature and is the fastest growing knowledgebase currently. XTractor Premium platform is Fast Becoming the definitive Semantic Knowledge discovery & Expert curated Knowledgebase for Life Science Researchers. The XTractor Premium Knowledgebase in addition to more than 503,985 relationships on proteins, drugs, biological process and diseases has advanced semantic search, concept linking analytics for effective knowledge discovery and modeling. XTractor Premium provides Precision based mining of the most relevant facts. Compared to natural language processing engines, manual annotation approach reduces false positives rate by 12-35%. XTractor premium serves as a platform to stay current with weekly updates from PubMed. Provides “Topic Tracking” with email alerts on spe...

"There does appear to be a distinction between the way curation is used in the bio-sciences, and elsewhere. In particular, the term "curated database" tends to mean a manually constructed database that links literature to data, curated by experts who provide authority (eg see the Wikipedia definition of Biocurator ). The earliest mention of the term "curated database" I can find is in the abstract (and only in the abstract) of Larsen et al (1993)." Chris Rusbridge Digital Curation Blog Since these database are hand curated by experts (manually curated), they always promise a accuracy & quality better than uncurated or NLP based databases. While NLP based databases follow a automated curation provide quick updates and tend to be large in terms of the quantum of data. While they may trade off in accuracy due to their automated curation process. While platforms like XTractor Premium follow a unique approach by trying to adopt the best of both worlds. A ...

Biomedical Data mining happens to be a long-standing problem in scientific research. Scientists are constantly in search of newer and innovative means to mine biomedical data. Be a part of the XTractor community. XTractor is the first of its kind - Literature alert service , that provides manually curated and annotated sentences for the Keywords of user preference. XTractor maps the extracted entities (genes, processes, drugs, diseases etc) to multiple ontologies and enables customized report generation. With XTractor the sentences are categorized into biological significant relationships and it also provides the user with the ability to create his own database for a set of Key terms. Also the user could change the Keywords of preference from time to time, with changing research needs. The categorized sentences could then be tagged and shared across multiple users. Thus XTractor proves to be a platform for getting real-time highly accurate data along with the ability to Share and ...

Blogging about curation in the past several issues have been discussed but here is something very critical. To thrive, the field that links biologists and their data urgently needs structure, recognition and support. Biocuration , the activity of organizing, representing and making biological information accessible to both humans and computers, has become an essential part of biological discovery and biomedical research. But curation increasingly lags behind data generation in funding, development and recognition. Three urgent actions to advance this key field. First, authors, journals and curators should immediately begin to work together to facilitate the exchange of data between journal publications and databases. Second, in the next five years, curators, researchers and university administrations should develop an accepted recognition structure to facilitate community-based curation efforts . Third, curators, researchers, academic institutions and funding agencies should, in the ...

Provision to change keywords with user’s changing research preferences in PUBMED data Be a part of the XTractor community. XTractor is the first of its kind - Literature alert service , that provides manually curated and annotated sentences for the Keywords of user preference. XTractor maps the extracted entities (genes, processes, drugs, diseases etc) to multiple ontologies and enables customized report generation. With XTractor the sentences are categorized into biological significant relationships and it also provides the user with the ability to create his own database for a set of Key terms. Also the user could change the Keywords of preference from time to time, with changing research needs. The categorized sentences could then be tagged and shared across multiple users. Thus XTractor proves to be a platform for getting real-time highly accurate data along with the ability to Share and collaborate. Sign up it's free, and takes less than a minute. Just click here: www.xt...

XTractor now has over Over 150 registered users from FDA , NIH , NCI , Astra Zeneca , Wyeth , MD Anderson Cancer Institute , Washington university , Scripps institute , Max Planck , Harvard Medical school and many more in less than 3 weeks !!! More than 600 annotated facts added everyday. A total of 25,000 facts added till date!!! Be a part of the XTractor community. XTractor is the first of its kind - Literature alert service , that provides manually curated and annotated sentences for the Keywords of user preference. XTractor maps the extracted entities (genes, processes, drugs, diseases etc) to multiple ontologies and enables customized report generation. With XTractor the sentences are categorized into biological significant relationships and it also provides the user with the ability to create his own database for a set of Key terms. Also the user could change the Keywords of preference from time to time, with changing research needs. The categorized sentences could the...

Bangalore, India — Indian Life Sciences Informatics Company, Molecular Connections announced today, the release of XTractor™, a first of its kind manually curated literature alert service. XTractor™ can be accessed free of charge by the scientific community world wide. XTractor™ acts as a literature alert service, which provides scientists with manually annotated scientific facts from literature. It enables researchers to be up-to-date with the latest scientific publications in the STM arena, as and when they are published. Once registered the scientists have the freedom to choose their keywords of choice and also set the frequency at which they wish to receive these alerts. Mining scientific literature to retrieve accurate hits or extract entity relationship has always been a long-standing problem in research. It is a daunting task to identify the right gene name or the right drug name and extract relations/association with diseases, processes; pathways etc accurately fo...

Previously blogging about Smart tools to track, analyze and visualize research discussed about the latest trends in literature abstraction, alert services and analysis tools. This time as a sequel check out one of the finest alert service using the web 2.0 technology. It is absolutely FREE! It is very simple, just visit the site www.xtractor.in and register. Almost immediately you are provided with a user-name and pw to access the alert service. Smart tools to track, analyze and visualize research II Talking about the development in the field of literature and scientific publication search. Looking beyond NLP some of the advancements and service models based on NLP and other advanced methods. Today to the user's delight there are quite a few companies and organization that provide services that absolutely make a scientist life easy! These services revolve around customized alert services for selected search terms, specific research area of interest even more so pertaining to a ...

Bangalore, India — Indian Life Sciences Informatics Company, Molecular Connections announced today, the release of XTractor™, a first of its kind manually curated literature alert service. XTractor™ can be accessed free of charge by the scientific community world wide. XTractor™ acts as a literature alert service, which provides scientists with manually annotated scientific facts from literature. It enables researchers to be up-to-date with the latest scientific publications in the STM arena, as and when they are published. Once registered the scientists have the freedom to choose their keywords of choice and also set the frequency at which they wish to receive these alerts. Mining scientific literature to retrieve accurate hits or extract entity relationship has always been a long-standing problem in research. It is a daunting task to identify the right gene name or the right drug name and extract relations/association with diseases, processes; pathways etc accurately ...

The first of its kind - SCIENTIFIC LITERATURE alert service which also provides manually annotated sentences for the keywords of YOUR preference Highly accurate , manually annotated sentences for given keywords. Daily scientific literature updates at your desktop along with extracted facts - manually curated. Provision to change keywords with your changing research preferences. Annotated sentences and abstracts get stored in your profile, as and when they get updated in PubMed. Classify and create your own datasets of annotated facts. Enhanced experiences of reading & analyzing literature. Access your profile / datasets from anytime, anywhere. Discover and Create newer relations from scientific facts classified by the XTractor™ Community. Tag your favorite abstracts and share them across other users. Much more faster and an Absolutely Free Service PRODUCT HIGHLIGHTS Abstract Summarization The XTractor™ system would provide extracted relations in addition to id...

Anyone who has ever built a website knows that maintaining it is a lot of work. There’s just making sure it hasn’t gone offline because the httpd daemon died. Constant monitoring for script kiddies and their SQL injections. Not to mention continually feeding it with fresh content, lest your audience become bored and desert. I’ve always thought it would be cool to build a site that could more or less look after itself. There’s a myriad of content management systems to choose from, most of which are somewhat hackable in whatever language they happen to be coded in. One of the more mature in this respect is Drupal - which is the engine behind Eureka! Science News . It’s a fully-automated science news portal, using a bunch of customised Drupal modules to aggregate, cluster, categorise and rank articles. First impressions are excellent. Coders will enjoy this post at Drupal explaining how it all works.

The International Conference in Trends for Scientific Information Professionals Habitual attendees say that "it is the meeting to which they go to spot the trends, as well as the meeting that provides unparalleled opportunities for networking" Trends and networking will be high on the Nice agenda in October 2008. The ICIC meeting covers trends in the field of scientific and professional information with an impressive line-up of significant figures in the information world. Among the topics that will be covered and discussed by the 22+ speakers are: Tools for Competitive Intelligence ( e.g., mining tools, visualisation tools, analysis tools, etc ) Challenges for the information community over the next five years Changes in the information environment for patents, innovation and intellectual property Trends in Search Engines and Information Retrieval ( also see ) Case Studies in Data and Content Integration

Already blogging on similar lines and the subject of Bring in data from the published literature in my earlier blog Smart tools to track, analyze and visualize research , here is another interesting experiment on similar lines: The experiment centres on Structured Digital Abstracts (SDA). SDA are extensions of the normal journal article abstracts that describe the relationship between two biological entities , mentioning the method used to study the relationship. Each sentence is preceded by one or more identifiers pointing to the corresponding database entries that contain the full details of the interaction e.g. protein A interacts with protein B, by method X . The aim of SDA is to assist data entry, text mining and literature searching by extracting the salient data from the article into simple sentences using a defined structure and controlled vocabularies. Gianni Cesareni, Editor of FEBS Letters explains: Many articles in biological journals describe relationships between ent...

Yes i am talking about the development in the field of literature search and scientific publication search. Looking beyond NLP some of the advancements and service models based on NLP and other advanced methods. Today to the user's delight there are quite a few companies and organization that provide services that absolutely make an scientist life easy! These services revolve around customized alert services for selected search terms, specific research area of interest even more so pertaining to a list of custom key-word and search terms that the service providers allow the user to choose form. The scientist can simply subscribe to such service, sit back and wait for daily updates. The updates are provided on a day to day basis at his desktop. He gets abstract summarization , full text summarization so that he need not actually go through the ordeal of reading through pages of scientific literature. Some once else does the job for him and just pick up the right things that he woul...

What is this? is this a new industry? or a old wine in a new bottle? may be the later is true, bioinformatics is more popularly known by this name in the industry circle these days! Well Life Sciences and Informatics can be any thing form anything form computational biology, all omes and omics, core bioinformatics to curation and literature mining , database creation, in the area of biology, chemistry , bio-chem space. Cheminformatics , insilico chemistry and insilico biology how best to describe the host of activities involved that companies do to serve their clients and earn revenues for their firms... There are number of companies in India and bangalore is the forefront as a major bio-cluster with 20 to 30 companies operation in this sphere. there are companies with the sole focus as informatics as business to name a few : Molecular Connections Pvt. Ltd. Jubilant Biosys Strand Life Sciences Ocimumbio (hyderbad) While IT companies which are also in to Life Sciences as one of thei...