Build a protein property prediction AI model - BC-619

Project type: Research
Desired discipline(s): Engineering - biomedical, Engineering, Engineering - chemical / biological, Biology, Life Sciences, Computer science, Mathematical Sciences, Statistics / Actuarial sciences, Chemistry, Natural Sciences
Company: AI Dynamics
Project Length: 4 to 6 months
Preferred start date: 09/01/2021
Language requirement: English
Location(s): United States; Canada; Japan; Canada; Canada
No. of positions: 4
Desired education level: Master'sPhD
Open to applicants registered at an institution outside of Canada: Yes

About the company: 

AI Dynamics was formed in 2015 on the belief that businesses, regardless of size, should have access to affordable AI solutions. 

Our trusted AI platform, allows every enterprise to expand AI capabilities across the organization while providing data security and management capabilities. In addition, NeoPulse can be deployed on any on-premise device, cloud or IoT environment.

We care deeply about building products that cater to our customer's needs and UX/UI design is paramount. 

Describe the project.: 

Goal of the project is to build AI models that can predict protein properties. You will:

- Gather data from public data sources, format and organize.
- Summarize data using simple statistics.
- Assist designing in silico experiments to solve the problems using machine learning.
- Assist interpreting machine learning results in the context of biology.
- Participate in scientific discussions and communicate analysis results with the team. 

Required expertise/skills: 

- Currently pursuing master’s or Ph.D. degree in computational biology, bioinformatics, cheminformatics or equivalent field.
- Basic knowledge of biology and statistics.
- Proficient in computational programming language, R and/or Python.
- Familiar with Unix and/or shell scripting.
- Familiar with public biological databases such as PDB, TCGA, STRING etc is a big plus.
- Knowledge and experience in protein science, chemical informatics, and/or gene expression data is a plus.