← ClaudeAtlas

bioreason-predictionslisted

Work with BioReason-Pro predictions and reasoning traces for protein function. Use when: comparing BioReason outputs against curated reviews, converting web exports to YAML, reviewing reasoning trace quality, or running the SFT/RL comparison. Triggers: "bioreason", "GO-GPT predictions", "reasoning trace review", "bioreason comparison", "SFT vs RL".
ai4curation/ai-gene-review · ★ 20 · AI & Automation · score 74
Install: claude install-skill ai4curation/ai-gene-review
# BioReason-Pro-RL Predictions ## About BioReason-Pro-RL is a pipeline for producing functional summaries of genes, along with reasoning traces, and other raw material (including high recall function predictions) - Web app: app.bioreason.net (model toggle top-left). Default: RL. - Paper: doi:10.64898/2026.03.19.712954 We store these in: `{GENE}-deep-research-bioreason-{rl,sft}.md` We are primarily interested in the higher precision RL results rather than just Supervised Fine Tuning (SFT) ## Structure of a bioreason report A bioreason report is structured as a markdown doc in these parts: * Metadata (organism and sequence) * Thinking/Reasoning trace -- the models exposed internal trace of thoughts as to why it arrived at its conclusions * Functional summary -- a consise summary of what the function of the gene is * Other details * Uniprot summary (imported) * Interpro domains (from running it as part of pipeline) * GO Terms (upstream ESM autoregressive transformer predictions -- high recall, low precision) We are generally NOT interested in the GO terms in this report. We know in advance these over-predict, they are just their to show provenance of the reasoner. ## File naming | File | Content | |------|---------| | `{GENE}-deep-research-bioreason-{rl,sft}.md` | Raw RL web export (provenance) | | `{GENE}-gogpt-leaf-predictions.yaml` | GO-GPT leaf terms as PredictionReview YAML (renamed from bioreason-rl-predictions.yaml) | | `{GENE}-bioreas