Interactive Python Notebook Modules for Chemoinformatics in Medicinal Chemistry
-
Babak Mahjour [1] ; Andrew McGrath [1] ; Andrew Outlaw [1] ; Ruheng Zhao [1] ; Charles Zhang [1] ; Tim Cernak [1]
-
[1] University of Michigan–Ann Arbor
University of Michigan–Ann Arbor
City of Ann Arbor, Estados Unidos
-
- Localización: Journal of chemical education, ISSN 0021-9584, Vol. 100, Nº 12, 2023, págs. 4895-4902
- Idioma: inglés
- Texto completo no disponible (Saber más ...)
-
Resumen
Data science is becoming a mainstay in research. Despite this, very few STEM graduates matriculate with basic formal training in programming. The current lesson plan was developed to introduce undergraduates studying chemistry or biology to chemoinformatics and data science in medicinal chemistry. The objective of this lesson plan is to introduce students to common techniques used in analyzing medicinal chemistry data sets, such as visualizing chemical space, filtering to molecules that observe the Lipinski rules of drug-likeness, and principal component analysis. The content provided in this lesson plan is intended to serve as a tutorial-based reference for aspiring researchers. The lesson plan is split into two three-hour class sessions, each with an introductory slide deck, Python notebook consisting of several modules, and lab report template. During this activity, students learned to parse medicinal chemistry data sets with Python, perform simple machine learning analyses, and develop interactive graphs. During each session, students complete the Python notebook protocol and fill out a lab report template after a short lecture. By the end of the lesson plan, students were able to generate and manipulate various plots of chemical space and they reported having increased confidence in their understanding of chemistry, Python, and data science.
