Search
Close this search box.

Prot2Prot: a deep learning model for rapid, photorealistic macromolecular visualization

Author(s)

Jacob D. Durrant

Sources

Journal of Computer-Aided Molecular Design (2022) 36:677–686 https://doi.org/10.1007/s10822-022-00471-4

Molecular visualization is a cornerstone of structural biology, providing insights into the form and function of biomolecules that are difficult to achieve any other way. Scientific analysis, publication, education, and outreach often benefit from photorealistic molecular depictions using advanced computer-graphics programs. The article reports developing and applying a deep-learning model called Prot2Prot that quickly imitates photorealistic visualization styles, giving a much simpler, easy-to-generate molecular representation. The resulting images are often indistinguishable from images rendered using industry-standard 3D graphics programs. Still, they can be created in a fraction of the time, even when running in a web browser. Prot2Prot is the first example of image-to-image translation applied to macromolecular visualization.
prot2prot.jpg
Prot2Prot is available free of charge, released under the terms of the Apache License, Version 2.0. Users can access a Prot2Prot-powered web app without registration at http://durrantlab.com/prot2prot.

Latest news

In biological systems, vascular networks play a pivotal role in regulating the chemical compositions of...

Amylose, a linear polymer comprised of α-1,4-linked glucopyranose units, is renowned for its propensity to...

Algae play an important ecological role as oxygen producers and carbon sequesters and are the...

Streptococcus gordonii is a Gram-positive bacterial species that typically colonizes the human oral cavity, but...