Taylor Reiter

@efranzosa Thank you! This figure started as a diagram of the workflow that I made in Lucidchart (attached here). Then, Audrey Bell, a very talented science illustrator at Arcadia, worked her magic in Illustrator! research.arcadiascience.com/user/audrey-be…. @thecrispress also gave critical feedback.

@ReiterTaylor Nice work! May I ask how Fig. 1 from the manuscript was assembled? That's one of the cleanest-looking workflow diagrams I've seen.

Introducing peptigate (peptide+investigate), a workflow that predicts and annotates peptides from transcriptome assemblies. It predicts small ORF-encoded peptides, cleavage peptides, and ribosomally synthesized and posttranslationally modified peptides.🧵 github.com/Arcadia-Scienc…

Thank you to all of my colleagues @ArcadiaScience who helped put this project together – @emilycpierce, @seemaychou, @AdairLBorges, @mertcelebi_, @kchev, Audrey Bell, @thecrispress, and @RobertRoth57.

If you want to learn more about peptigate, read our pub or take a look at the GitHub repo. research.arcadiascience.com/pub/resource-p… github.com/Arcadia-Scienc…

Learn more about plm-utils by reading our pub, “Using protein language models to predict coding and noncoding transcripts,” or see the GitHub repository. research.arcadiascience.com/pub/resource-p… github.com/Arcadia-Scienc…

This was a combined effort between many scientists @ArcadiaScience. @Gilad had the initial idea to use ESM embeddings to improve prediction accuracy, while @kchev implemented the code and performed some of the validation.

Have you ever wondered whether a transcript is coding or noncoding? Or whether a predicted open reading frame encodes a functional protein? We recently had this question for very short open reading frames (sORFs). Enter the Python package plmutils 🧵 research.arcadiascience.com/pub/resource-p…