Authors:

Adam G Weber

Date Created:

Not specified

Course Title:

Professor:

Not specified

About Paper:

Biocatalysis, the use of enzymes to catalyze reactions, provides a more specific, sustainable, and efficient method of chemical synthesis to manufacturers. There are approximately twenty thousand enzymatic reactions in our reaction databases and millions of enzymes sequences annotated to these transformations. To produce a desired target compound, human scientists rely on their experience and intuition to select the appropriate enzyme reaction chemistry and its corresponding enzyme sequence candidates. It is difficult for a small group of scientists to have an encyclopedic knowledge of enzyme reaction chemistry. Thus, tools are needed that can identify and suggest biocatalytic synthesis routes for target molecules in an unbiased fashion after considering the entire dataset of ~20,000 enzymatic transformations. This research focuses on the development of such a tool, called RDEnzyme. RDEnzyme utilizes AI/data science to suggest single step retrosynthetic pathways. It does this by identifying potentially evolvable reactions from the large corpus of known enzymatic reactions RHEA. The tool currently provides users with a ranked list of fifty proposed reactions along with scores to measure the reaction's complexity change and evolvability. Here, we employ this tool to plan synthetic routes towards medicinal compounds, some of which are in FDA's critical shortage list. The result plans set the stage for the development of biocatalytic routes that will lead to more efficient and sustainable manufacturing to alleviate current shortages. Keywords: Enzyme; Biocatalysis; Retrosynthesis; Data Science; Biological Engineering

Source:

Purdue University / 2024

Topics:

No topics listed

Co-authors:

Adam G Weber