Data Scientist - Computational Biology

Department:  Bioinformatics                                                                             

Reports to: Director of Bioinformatics                                   

The Opportunity:


Passionate to put your data science/machine learning/Computational biology skills to give hope to the cancer patients of today and tomorrow?


Headquartered in Pittsburgh, Helomics is a division of Predictive Oncology Inc. Our mission is to improve outcomes for current and future cancer patients using a knowledge and AI-driven approach. We leverage our proprietary tumor profiling platform, a vast historical knowledgebase of 150,000 de-identified patient drug response profiles, together with proven AI to deliver more precisely targeted therapies for patients. For clinicians and their patients, we provide a proprietary clinically validated tumor profiling test to help oncologists individualize the treatment of GYN cancer patients with current therapies. For our pharmaceutical partners, we improve the efficiency and cost-effectiveness of the discovery of new therapies, using a unique AI-driven, patient-centric approach.

Position Scope and Focus

  • Play a key role in a dynamic team developing an AI-driven approach to patient-centric drug discovery and precision medicine

  • This is a challenging role, where you will have responsibility for your own projects, their successes, and failures, so you will need to be a quick learner and able to manage your time effectively to work in our highly Agile environment

  • You will work with a wide variety of data from genomic and transcriptomic data through tissue and cell images to clinical data

  • You will use your skills to build machine learning and bioinformatic approaches to this data to build AI-driven platforms that help clinicians better treat patients with current therapies as well as improve the discovery of new therapies

  • You will need to be good at problem-solving and able to rise to a challenge as much of the work we do has no clear solution – yet.


Required Education & Experience

  • Masters or Ph.D in data science, machine learning, computational biology or equivalent practical experience, together with a degree or equivalent experience in computer science or bioinformatics

  • Excellent programming skills in Python, R and SQL

  • Practical experience of developing, training, testing and validating both deep and classical machine learning models using public frameworks scikit-learn, tensorflow, pyTorch on omics data

  • Practical experience of analysis and visualization of multi-omic data sets using R and Python

  • Experience of cloud compute infrastructure, scheduling of compute workloads and tools such as SparkR, pySpark etc

  • Self-motivated and able to work as part of a team within a results-oriented culture

  • Able to communicate effectively with all levels, both internal and external to Helomics


Additional Skills and Experience

  • Experience with cloud-based compute environments and high performance compute environments

  • Familiarity with graph-based databases, Neo4j, graph data modelling a plus

  • Familiarity with Agile software development practices

  • Work experience or familiarity with healthcare or drug discovery processes and data

If you meet the requirements and are seeking a dynamic, challenging atmosphere, with the opportunity to make a difference to help oncologists and their patients, email your resume to with the words

“Datascientist-computational biology 2021” in the subject of the email.