Keith Cheveralls

Software engineer

San Francisco, CA kchev.io 0000-0002-4157-6087 https://github.com/keithchev

Streamlining microscopy datasets by enriching for in-focus frames

Feridun Mert Celebi, Keith Cheveralls, Seemay Chou, Tara Essock-Burns, and Galo Garcia III

Published: Nov 17, 2023

We distilled label-free microscopy data by comparing and implementing feature-detection algorithms. Sobel and Laplacian methods outperformed pixel intensity variance in accuracy.

Connections

Supplements (1): Code v1.0 - GitHub

Automated classification of time-course imaging data applied to nematode embryogenesis

Prachee Avasthi, Feridun Mert Celebi, Keith Cheveralls, Seemay Chou, Ilya Kolb, and David Q. Matus

Published: Dec 02, 2023

Machine learning is a powerful tool for classifying images in a time series, such as the developmental stages of embryos. We built a classifier using only bright-field microscopy images to infer nematode embryonic stages at high throughput.

Connections

Supplements (2): Code v1.0 - GitHub • Data- Time-course images of nematode embryos - Zenodo

ProteinCartography: Comparing proteins with structure-based maps for interactive exploration

Prachee Avasthi, Brae M. Bigge, Feridun Mert Celebi, Keith Cheveralls, Jase Gehring, Erin McGeever, Gilad Mishne, Atanas Radkov, and 1 more

Published: Sep 29, 2023

The ProteinCartography pipeline identifies proteins related to a query protein using sequence- and structure-based searches, compares all protein structures, and creates a navigable map that can be used to look at protein relationships and make hypotheses about function.

Connections

Supplements (3): ProteinCartography v0.5.0 - GitHub • ProteinCartography v0.4.2 - GitHub • Data - Zenodo

Label-free neuroimaging in mice captures sensory activity in response to tactile stimuli and acute pain

Adair L. Borges, Seemay Chou, Ilya Kolb, Ryan Lane, David G. Mets, and Kira E. Poskanzer

Published: Jul 26, 2024

Sensory disorders are clinically common, debilitating conditions. But mouse behavioral models are often insufficient. We demonstrate that label-free, minimally-invasive brain imaging in mice could be a promising avenue for sensory research or drug discovery efforts.

Connections

Supplements (2): Code v1.0.1 - GitHub • Imaging data - Zenodo

Using protein language models to predict coding and non-coding transcripts with plm-utils

Adair L. Borges, Feridun Mert Celebi, Keith Cheveralls, and Taylor Reiter

Published: Aug 08, 2024

We explored the use of embeddings from protein language models to distinguish between genuine and putative coding open reading frames (ORFs). We found that an embeddings-based approach (shared as a small Python package called plm-utils) improves identification of short ORFs.

Connections

Supplements (2): Code v1.0.0 - GitHub • Evaluation and training code - GitHub

Predicting bioactive peptides from transcriptome assemblies with the peptigate workflow

Adair L. Borges, Feridun Mert Celebi, Keith Cheveralls, Seemay Chou, Taylor Reiter, and Emily C.P. Weiss

Published: Aug 08, 2024

Peptigate predicts bioactive peptides from transcriptomes. It integrates existing tools to predict sORF-encoded peptides, cleavage peptides, and RiPPs, then annotates them for bioactivity and other properties. We welcome feedback on expanding its capabilities.

Connections

Supplements (2): Code v1.0.0 - GitHub • Evaluation code and data v1.0 - GitHub

A high-throughput imaging approach to track and quantify single-cell swimming

Tara Essock-Burns, Ryan Lane, and David G. Mets

Published: Nov 06, 2024

Live imaging of swimming cells can yield insight into an organism’s viability and responses to environmental stimuli. We developed a microscopy workflow and image analysis pipeline, SwimTracker, to track motility phenotypes from swimming cells in high throughput.

Connections

Supplements (2): Code v1.1 - GitHub • Data - BioImage Archive