jmschrei

Use for any task involving the tangermeme library — post-training analysis of genomic sequence-to-function (S2F) deep learning models. Triggers on predictions, DeepLIFT/SHAP attributions, marginalization/ablation/spacing of motifs, saturation mutagenesis (ISM), variant effect scoring, sequence design, seqlet calling, loading loci/FASTA/bigWig/MEME/VCF, or wrapping a PyTorch genomic model for these analyses. This is a router skill — read the relevant file under references/ for details and footguns before writing tangermeme code.

Train, evaluate, and use Cherimoya sequence-to-function genomic models with the `cherimoya` command-line tools or Python API. Use when a user wants to run the end-to-end pipeline, use a trained model to do downstream tasks, or troubleshoot a run. Designed for users who may be new to Cherimoya or to sequence modeling: ask clarifying questions whenever an input is ambiguous or missing, pick reasonable defaults, and explain in plain language what was chosen and why.