Practical Introduction to Data Science Methods, Using AI and Generative AI

Data science involves the application of statistical and AI techniques on numerical, text and image data to rapidly gain useful scientific insights.  Data science platforms involve several functions, such as data engineering, data analyses, and insight generation and reporting. This course introduces these functions and presents them as part of an integrated workflow. The workflow is not always linear, and the use of these functions is often iterative within science projects. The course presents a both simplified and actionable description of the functions, including practical first steps for non-technical scientists looking to get started. Case examples are provided with public data, which attendees can replicate in their own time.

Attendees will learn from an instructor who has both built and led teams building data science environments. The course requires only a basic understanding of data and science. No coding knowledge is required. Practitioners with expertise in one of the functions are encouraged to attend and learn how to combine their knowledge with other functions.

Who Should Attend?

• Bench scientists
• Computational scientists
• Team leaders and project managers
• Students, postdocs, and faculty

Learning Objectives

• Acquire big picture industry and technology trends – for the use of AI and Generative AI in early drug discovery, including expectations and risks.
• Learn about the key building blocks for today’s data science environment – including the analysis of structured data, image data, and text publications.
• Understand the practical trade-offs (benefits and challenges) of using commercial software, open-source software, large-language models, and public datasets.
• Learn simple, actionable methods for attendees to set up their own data science environments – leveraging the right tools to solve the scientific problems that they are working on.

Course Topics

• Industry and technology trends for the use of AI and Generative AI in early drug discovery – including expectations and risks.
• Fundamentals of the building blocks in a data science environment: Data – Data Engineering – Data Analyses – Insights Generation & Reporting.
• AI and Machine Learning options for analyzing structured data, text data, and image data.
• Practical steps to creating one’s own data science environment – using open-source and vendor provided tools and datasets.  This will include a discussion on the trade-offs of Build vs Buy.
• A data science example using public data, with a framework for attendees to take away and replicate.

Interested in the course but can’t make it on this date? This course is also available on demand!

Instructors

Raminderpal Singh
20/15 Visioneers

Raminderpal Singh, Ph.D., is a recognized visionary in the implementation of AI & GenAI across technology and science-focused industries. He has over 30 years of global experience leading and advising teams, helping early to mid-stage companies achieve breakthroughs through the effective use of computational modelling. Singh is currently the Global Head of AI and GenAI Practice at 20/15 Visioneers. He also founded and leads the HitchhikersAI.org open-source community. He is also a co-Founder of Incubate Bio – a techbio providing a service to life sciences companies who are looking to accelerate their research and lower their wet lab costs through in silico modelling. Singh has extensive experience building businesses in both Europe and the US. As a business executive at IBM Research in New York, he led the go-to-market for IBM Watson Genomics Analytics. He was also Vice President and Head of the Microbiome Division at Eagle Genomics Ltd, in Cambridge. Singh earned his Ph.D. in semiconductor modelling in 1997. He has published several papers and two books and has twelve issued patents. In 2003, he was selected by EE Times as one of the top 13 most influential people in the semiconductor industry.