Protein Design Campaign

Turn an ongoing binder-design effort into reproducible candidate decisions and an honestly described experimental or competition submission. Preserve the user's chosen models, infrastructure and goals; this skill does not grant permission to upload unpublished designs, publish a repository or accept terms.

Establish the current decision

For an existing campaign, read its latest status, manifests, executed results and failure records before launching jobs. Distinguish a completed process from an active one; an old PID or a queued browser file is not proof of ongoing computation or submission.

Record target isoform/species, assay construct and termini, intended epitope, glycosylation assumptions, molecule class, designable positions, and objective direction. Explicitly distinguish stronger binding at acidic pH from binding at neutral pH with acidic release. They are different objectives, not interchangeable consequences of adding histidine.

For competitions, verify the live challenge, account track, deadlines, novelty definition and molecule formats. Convert the deadline with an explicit UTC offset; AoE means UTC−12. Keep current competition limits in the campaign record, not as permanent defaults in this skill.

Choose the next informative computation

1. Resolve execution or input defects before generating more designs. Missing atoms, misidentified glycans or incomplete pKa inventories invalidate downstream scores.
2. Test known positive controls through the same preparation and scoring pipeline. If a known binder fails, diagnose the pipeline before treating the cutoff as a candidate veto. Keep the original result and any revised criterion separate.
3. Spend compute on distinct uncertainty: foldability, complex pose, receptor/glycan compatibility, protonation mechanism, or cross-species compatibility. More seeds assess sampling but do not supply another model family.
4. When models disagree, compare constructs, component retention, protonation conventions and coordinate preparation. Do not average unrelated units into an apparent consensus.
5. Keep an experimental route visible: matched SPR/BLI or an equivalent binding assay at the specified pHs, with receptor species and construct controls. Computation cannot establish an assay detection threshold.