AI Independence for Life Science Practitioners
Develop a practical understanding of the AI landscape with an emphasis on its relevance to and the common use cases for the life sciences
This course is no longer available.
Explore other courses
Course overview
Develop into an independent AI practitioner!
Too often practitioners in the life sciences feel as though they are mostly or wholly dependent on data scientists or ML engineers to incorporate AI into their daily workflows and strategic research initiatives.
The reality is that impactful AI applications have been proven to consistently thrive at the intersection of strong subject matter expertise and the most basic of AI skills. This powerful confluence happens when practitioners are fully enabled to navigate and leverage existing AI resources, including: public data repositories; well-documented end-to-end projects on GitHub; and other publicly available and fee-based tools and pre-trained models that enable them to incorporate significant temporal and effort-based efficiencies into their AI-driven projects.
This course will enable life science practitioners with no prior experience in building AI-driven applications to leverage their subject matter expertise and existing capabilities around data and statistical models - in tandem with easily accessible support and resources - to design and execute their first AI project.
Who is this course for
01
Research scientists wanting to enhance their ability to analyze complex biological data, make good decisions, and accelerate their research.
02
Medical technicians looking to improve diagnostics and patient plans as well as improving patient safety.
03
Laboratory analysts needing to accelerate drug discovery, optimize processes, streamline quality control, and better support validation.
What you’ll get out of this course
Understand how AI has impacted the traditional data lifecycleÂ
Traditional data lifecycles have been number>data>intelligence. With enveloping of AI by data science, that lifecycle has become richer and a bit more interesting as data now tends to evolve form nascent states all the way to predictive and even generative states.
Master the basics of the AI lifecycle
In broadest terms, building AI requires two macro-level steps: 1. learn the rules, 2. apply the rules. Everything you need to learn about AI elaborates around those two steps. From there, we will break it down to a slightly more complex set of steps and activities that you
Develop a comprehensive understanding of the contemporary AI landscape
Evolve your understanding of AI from a rough familiarity of buzzwords to a mastery of AI models from simple linear regression to cutting edge generative AI models.
Explain how each major type of AI model is applicable to life sciences
Contextualizing your understanding of the most common AI models with well documented and carefully curated examples and common case studies from the life sciences will ease your transition into a savvy AI practitioner.
Develop a familiarity of the resources and best practices needed to start building and evolve your AI capabilities
The culture led by the advent of Web 3.0 has exponentially grown the proclivity for practitioners of all kinds to share their work – including source code and documentation. And in few sectors is this practice more prevalent than in the field of AI. You will walk away from
Course syllabus
26 lessons • 5 projects
Week 1
- đź“„
What is AI trying to achieve?
- đź“„
AI as the new programming paradigm in the era of Big Data
- đź“„
AI Macro-Level Phases: Learning the Rules, Applying the Rules
- đź“„
The practical steps of the AI lifecycle
- ✍️
Reflection Questions: Conceptualizing AI
Submit by Sep 12 - đź“„
The traditional data lifecycle
- đź“„
How AI changes everything about the data lifecycle
- đź“„
How fluid is the data lifecycle?
- ✍️
Applying the data lifecycle to the data you work with everyday
Submit by Sep 12 - đź“„
Linear Regression
- đź“„
Logistic Regression
- đź“„
Supervised vs Unsupervised Learning
- đź“„
Clustering Models
- đź“„
Deep learning models - CNNs & RNNs
- đź“„
Case Study: Malic Acid & Flavanoids
AI Fundamentals for Life Science
How AI has impacted the traditional data lifecycle
Common AI Models and the problem spaces they address
Deep learning models - CNNs & RNNs
No module content yet
Week 2
- đź“„
Mapping common life science activities to AI Models
- đź“„
Applying AI to the Drug Development Lifecycle
- đź“„
Accelerating and Approving Diagnostics with AI
- đź“„
Streamlining QC with AI
- ✍️
Upon further reflection..
Submit by Sep 12 - đź“„
Revisiting the phases of an AI project
- đź“„
Separating data science steps from ML steps
- đź“„
Guidelines for selecting an MVP of the best size and scope
- đź“„
Developing a comprehensive pre-project checklist
- đź“„
Assigning roles and resources to a project template
- ✍️
Completing a high-level work plan for your AI MVP
Submit by Sep 12 - đź“„
Data Source Repositories: Kaggle and UC Irvine ML Repository
- đź“„
Git at it! An introduction to navigating GitHub for benchmark projects
- đź“„
Come on get happy! The Hugging Face Hub
- đź“„
Entering the xfer portal: Using transfer learning to accelerate your project
- ✍️
Creating a resource acquisition plan for you and your team
Submit by Sep 12
Deeply contextualizing AI for the life sciences
Planning, exciting, and elaborating on your first AI MVP
Locating and applying the available resources for your AI Project
Bonus
Generative AI applications for the life sciences
No module content yet
Meet your instructor
Bryan D. Eldridge, M.Ed.
Bryan D. Eldridge, M.Ed.
Master Instructor
Bryan has worked with some of the largest pharmaceutical companies and biotech labs in the world to design and deliver training programs for drug researchers, microbiologists, product stability teams, pharmaceutical laboratory analysts, documentation specialists, and system validation specialists.
Course schedule
4-6 hours per week
Tuesdays & Thursdays
4:00pm - 5:30pm EST
90 minute lectures will be delivered from 4:00pm - 5:30pm Tuesdays and Thursdays.
May 7, 2022
Feel free to type out dates as your title as a way to communicate information about specific live sessions or other events.
Weekly projects
2 hours per week
Schedule items can also be used to convey commitments outside of specific time slots (like weekly projects or daily office hours).
Learning is better with cohorts
Active hands-on learning
This course builds on live workshops and hands-on projects
Interactive and project-based
You’ll be interacting with other learners through breakout rooms and project teams
Learn with a cohort of peers
Join a community of like-minded people who want to learn and grow alongside you