Computer Scientist

POSTED: April 6, 2022
BUSINESS: AsedaSciences


AsedaSciences is engaged in the development of cell-based screening technologies.
AsedaSciences conducts phenotypic screening on chemical compounds using human cell lines
to ascertain their multiparametric biological effects. The data gathered is used to define the
potential risk of compound failure due to toxic effects and to identify potential mechanisms of
action. Additionally, AsedaSciences develops phenotypic data management for third-party
screens and offers data interrogation and visualization services compatible with a broad range of
phenotypic assays. The company employs sophisticated bioinformatics and statistical methods
to provide clients with biological risk assessments of test compounds and assist them in
prioritizing compound selection for progression within their R&D programs.

The Computer Scientist's primary responsibility will be to contribute to the development of data
processing and machine learning (ML) pipelines for analyzing AsedaSciences' proprietary data
and third-party results. They will use data handling, extraction, dimension reduction, and
automated interpretation techniques to process, evaluate, and interpret information from various
phenotypic assays. They will collaborate with AsedaSciences' scientists, external consultants,
and university researchers to develop novel and relevant analytical and machine learning-driven
predictive methodologies. These methods will integrate high-quality biological data, chemical
properties, and associated metadata to develop predictive decision-making tools for scientists
working in the pharmaceutical, industrial, and agricultural chemical markets. The ideal candidate
will have exceptional statistical and programming skills, with a preference for those with a strong
background in the bioanalytical domain, with an emphasis on single-cell analysis tools.


  • Perform exploratory analysis and build creative visualizations using biological data
  • Collaborate with biologists and medicinal chemists to define the data processing goals for
    designated project areas
  • Plan and schedule daily computing and reporting activities
  • Rapidly develop models and methods for quality control, analysis, classification, and
    prediction using existing open-source tools
  • Co-develop web-based data visualization and interaction tools usable by biologists, medicinal
    chemists and pharmacologists
  • Suggest and design biological experiments in collaboration with AsedaSciences staff
    biologists to answer data-driven questions, verify and validate data analysis and machine
    learning strategies

Minimum Requirements:

  • PhD or Master’s degree with a major and at least 5 years’ experience in statistics, computer
    science, mathematics/applied mathematics, engineering and either physics, computational
    biology or other quantitative field
  • Strong background in machine learning, regression analysis, feature extraction, feature
    discovery and selection, optimization, exploratory data analysis, data mining, and pattern
  • Experience with tools such as: GLMs, MCMC, dimensionality reduction (PCA, ICA, NMF,
    manifold learning, kernel PCA, spectral unmixing), feature selection, unsupervised and
    supervised learning (Neural Networks, Deep Learning, SVM, Decision Trees, etc.)
  • Proficiency in data analysis and visualization using R and Python (scikit-learn, NumPy, SciPy)
  • Experience with web-based graphical user interface for R data analysis and reporting (Shiny)
  • Documented experience in the development and implementation of machine learning
    techniques in R, Python, and Java
  • Experience with C/C++ and object-oriented programming techniques
  • Experience working with version control systems
  • Basic cell biology and biochemistry knowledge is required in order to comprehend underlying
    scientific problems and to facilitate effective communication with scientific collaborators and
    AsedaSciences' staff scientists.
  • Basic understanding of single-cell analysis techniques preferred (flow cytometry, high-content
    screening, automated microscopy) and common data processing practices in those fields
  • Familiarity with SQL (MySQL, PostgreSQL)
  • Familiarity with unstructured databases (e.g., MongoDB)
  • Experience with AWS tools preferred
  • General knowledge of Linux operating system and Linux system administration
    • Unix/Linux scripting skills (bash, Perl, awk, sed, etc.)
  • Demonstrated ability to work effectively and independently in a team environment
  • Strong desire to work in a growing startup with a willingness to acquire specialized domain
    knowledge in the area of single-cell analysis
  • Scientific curiosity and self-motivation
  • Minimum of three references for validation of technical skills and experience
  • Excellent problem solving and troubleshooting skills
  • Strong (oral and written) communication and presentation skills
  • Self-motivated and excited by opportunities to gain new skills and knowledge
  • Ability to explain complex data processing methods and communicate analytical results to
    both technical and non-technical audiences.


Interested candidates should send a resume to 

  • Job Listings

Kurz Purdue Technology Center, 1281 Win Hentschel Blvd., West Lafayette, IN 47906, 765-588-3470

© 2020 Purdue Research Foundation | Maintained by Purdue Research Foundation

Trouble with this page? Please contact Purdue Research Foundation by Phone, 765-588-3470, or FAX, 765-463-3501.