An Introduction to Cheminformatics

By: Katana Graph

April 15, 2022

An Introduction to Cheminformatics

Cheminformatics is the merging of physical chemistry theory with computational techniques. The term can apply to industrial chemical research, environmental science, and pharmacology, but its primary domain is in the drug discovery process and related activities where chemical processes are integral to real-world life science solutions. One common use in drug discovery research is in the field of combinatorial chemistry, where thousands of chemical structures are generated simultaneously to be screened as drug candidates.

Graph technology and mathematical modeling can work together to let us study chemical phenomena using graph-theoretical representations of molecules. This provides insights from these phenomena much faster than was possible in the past. The underlying principle of this field of study is that similar molecules generally have similar properties, and typical cheminformatics models use pattern recognition approaches to predict biochemical attributes.

The ability to study the structure of molecules as well as chemical interactions provides researchers with clues to the design of new molecules and Novel Chemical Entities (NCE). In the therapeutics field, cheminformatics allows us to predict critical ADMET properties – chemical absorption, distribution, metabolism, excretion, and toxicity – in the human body.

Graph neural network variants like Graph Convolutional Networks are proving especially productive in this field, enabling techniques such as the learning of vector representations of molecules and submodular function maximization. Graph abilities such as node, edge, and vector classification, in combination with convolutional prediction of node features based on neighboring nodes’ attributes, allow AI to interpret a thorough understanding of molecular compounds and to produce models based on that understanding.

Several algorithms developed for molecular research are available to identify and track particular routes or molecular structures, mutagenesis, and similar attributes. The potential for innovation using deep learning and AI is an exciting area that is being actively explored by scholars and scientists. To learn more about cheminformatics in the therapeutics field and the sort of problems graph intelligence is being used to solve with the Katana Graph Intelligence Platform, check out the Therapeutics Data Commons website, about which we’ll say more in the next post in this series.

Whether structured or unstructured data, Katana Graph can greatly improve the insights and opportunities uncovered from your organization’s data. Click to schedule a meeting.

share

Newsletter Sign Up

The Way Forward: Graph Computing Conquers Life Sciences, AI, and ML

Graph computing, which is much more than simply utilizing a graph database, and graph AI is capable.

Read More
An Introduction to Network Medicine Using Graphs

In this new era of Big Data, we can leverage the abundance of large Omics datasets: high-throughput.

Read More
The Graph Computing Differentiator for Life Sciences

Few industries are as data-intensive — and as highly regulated — as life sciences. Organizations in.

Read More

View All Resources

Let’s Talk

Turn Your Unmanageable
Data Into Answers

Find out how Katana Graph can help provide the foundation for your future of data-driven innovation.

Contact Sales