4 papers
An autoencoder outperforms two transformers on prediction of gene expression from chromatin accessibility
Jesse G. Meyer
Models that predict RNA abundance from chromatin accessibility are rarely compared under the same features, targets and metrics. We built one benchmark on 126,604 paired single-nuc…
From Articles to Code: On-Demand Generation of Core Algorithms from Scientific Publications
Cameron S. Movassaghi, Amanda Momenzadeh, Jesse G. Meyer
Maintaining software packages imposes significant costs due to dependency management, bug fixes, and versioning. We show that rich method descriptions in scientific publications ca…
Single-Cell Proteomics Using Mass Spectrometry
Amanda Momenzadeh, Jesse G. Meyer
Single-cell proteomics (SCP) is transforming our understanding of biological complexity by shifting from bulk proteomics, where signals are averaged over thousands of cells, to the…
AttentionSmithy: A Modular Framework for Rapid Transformer Development and Customization
Caleb Cranney, Jesse G. Meyer
Transformer architectures have transformed AI applications but remain complex to customize for domain experts lacking low-level implementation expertise. We introduce AttentionSmit…