b***p
发帖数: 1398 | 1 【 以下文字转载自 JobHunting 讨论区 】
发信人: jianan (JiaNan), 信区: JobHunting
标 题: summer intern opportunity at GSK (philadelphi (转载)
发信站: BBS 未名空间站 (Wed Feb 15 17:23:10 2012, 美东)
发信人: jianan (JiaNan), 信区: Pharmaceutical
标 题: summer intern opportunity at GSK (philadelphia)
发信站: BBS 未名空间站 (Wed Feb 15 17:20:38 2012, 美东)
12-Week Summer Internship, Natural Language Processing and Text Mining
http://us.gsk.com/html/career/career-summer.html (search for requisition number: 73364)
GlaxoSmithKline (GSK) is a one of the world's largest pharmaceutical company
. We develop medicine and vaccines for both major disease areas including
asthma, cancer, virus and infections, mental health, diabetes and digestive
conditions. In addition, we are a leader in the important area of vaccines
and are developing new treatments for cancer. Now the Computational Biology
group, at Philadelphia R&D center, is recruiting an internship in Natural
Language Processing and Text Mining, for 2012 summer.
Basic qualifications:
• Master degree in Biomedical Informatics or Computer Science or
related discipline.
• The candidate should be available for a total of 12 weeks at
minimum. The start date is May 14, 2012 (can be flexible)
• Location will be at King of Prussia, PA
• The candidate must hold a legal status to work in US for the
above period of time
Preferred qualifications:
• Senior graduate student in a PhD program in Biomedical
Informatics or Computer Science or related discipline
• Sufficient experience with natural language processing, text
mining and various biomedical terminologies
• Practical programming skills in one or more of Java, Perl, and
Python
• The candidate should be an analytical and creative thinker with
efficient communication skills, both verbally and in writing
Details:
Comprehensive information about finished and ongoing clinical trials is
stored in either public database (clinicaltrial.gov) or internal commercial
database, including patient demographics, inclusion and exclusion criteria,
medications, targeted medical conditions, and clinical trial outcomes and
etc. These trial data eliminates the bias in scientific literatures and is
extremely valuable to decision making in both early drug discovery and
clinical development. Unfortunately as the data are mostly stored in the
format of irregular free text, its value is under explored. Desirable
candidate will apply Natural Language Processing (NLP) and text mining
approaches to deep mine these databases to identify therapeutic areas/
diseases which have clear clinical endpoint or which are easy and fast to
carry out. He or she will also be able to integrate such information with
other data sources including scientific literature and electronic health
records (EHR), to discover unmet medical needs with socio-economical benefit
and scientific maturity.
Please contact the hiring manager, Lixia Yao (L*********[email protected]) directly
with any inquiries. |
|
