Date: 19 Jan 2007
Subject: Pittsburgh, PA: (Senior) Scientist; Bioinformatics - Machine Learning - Statistics - Algorithm Development at Precision Therapeutics, Inc.
(Senior) Scientist; Bioinformatics - Machine Learning - Statistics - Algorithm Development
Position available full- or part-time as employment or consultant
Precision Therapeutics, Inc. is a bio-technology start-up company
located on the South Side of Pittsburgh just minutes away from
Carnegie Mellon University, the University of Pittsburgh, and the
University of Pittsburgh Medical Center (UPMC). PTI assists
oncologists in evaluating individualized cancer therapy options for
their patients. We are currently seeking a Bioinformatics/Machine
Learning/Statistics Scientist to join the Precision Therapeutics
Duties & Responsibilities:
The successful candidate will join a talented team of Technology and Biology professionals in the development of products designed to customize cancer therapy treatments on an individualized patient basis. The successful candidate must be highly organized; detail oriented and is an excellent communicator. The role will include:
- Responsibility for developing and implementing innovative cell-based and gene-based algorithms aimed to predict patient response to cancer therapy.
- Designing and implementing statistical models that will support medical management; identify previously unknown relationships among the data for analyses of trends; provide support to Informatics staff and other areas of the corporation.
- Defining effective statistical models (logistic and linear regression, neural network, cluster analysis, SVM, categorical data modeling and other relevant predictive statistical techniques).
- Employing model comparison and selection techniques (e.g. Lift/ROC curves) to identify best models.
- Analyze and mine multiple data sources to select statistically valid data samples; build, test and implement statistical models by investigating appropriate methods and algorithms.
- Evaluate analytical findings to ensure accurate interpretation of data and development of meaningful data mining results
- Identify/Create programming tools and technical solutions.
If you are seeking a dynamic, challenging atmosphere, that is never boring, with a chance to make a difference and help cancer patients, email your resume to
with the words
in the subject of the email.
- Masters, or PhD with a focus in Bioinformatics, Machine Learning, Mathematics, Engineering, Computational Biology and/or Statistics.
- Knowledge & Abilities
- Clinical trial design and data interpretation and analysis for innovative genomic studies
- Logical thinker able to break down complex projects into achievable tasks
- Ability to plan and manage strategic research projects.
- Ability to problem solve and prioritize work assignment
- Willingness to work in an ambiguous environment
- Effective interpersonal skills and ability to maintain effective working relationships with others
- Able to work independently or in small teams
- Quick learner
- Highly organized and detail oriented.
- Well-developed and effective communication skills: phone, email, documentation, and in-person
- Ability and enthusiasm for learning and mastering new domain areas outside of the candidate's focused area of expertise.
- Overall Attitude, Aptitude, Willingness to Learn and Achievement oriented approach and desire to get the job done right, whatever that takes.
- Technical Skills:
- Strong background in quantitative statistical analysis including model building and concepts, regression analysis, cluster analysis, discriminate analysis, factor analysis and multivariate statistics
- Skills in mathematics, statistics, and scientific analysis for application in a business environment.
- Prior experience in Algorithm Development
- Proficiencies in:
- SAS 9, S Plus or R
- PERL or Python
- SQL & Database Development
- Java, C, C++ or other scientific programming
- Spotfire Decisionsite
- Microsoft Office Tools - Excel (including Pivot Tables), Word, Project
- Preferred Skills:
- SQL, Oracle Database preferred, but other Relational databases considered
- machine learning and statistics experience;
- Demonstrated command of methods and software tools for machine learning and statistical analysis
- Participation in data analysis, data mining, statistical inference, particularly classification prediction using censored survival outcomes, and longitudinal, survival outcomes.
- In-depth exposure to a variety of data mining, regression, and machine learning algorithms
- Comfortable with a variety of statistical and biostatistical techniques, including both classical and Bayesian methods
- genomic data experience including:
- RNA/DNA diagnostic assays
- RNA expression analysis by microarray chips and Taqman
- SNP analysis
- Predictive genomic profiles
- Demonstrated command of methods and software tools for bioinformatics and analysis of microarray data
- Experience with basic bioinformatics tools (Blast, BLAT, sequence analysis algorithms, clustering tools) and bioinformatics resources, including UCSC genome browser, Entrez gene, GEO, and pathway analysis.