Adaptyv EGFR binder design competition, round 2

Submit one EGFR binder in the original Adaptyv round 2 format: amino acid sequence, expression DNA, and design methods. Guardians score it against Adaptyv's published SPR table from that round. They do not run SPR, expression, or neutralization assays.

Adaptyv Bio, with Polaris and Dimension, ran round 2 of the EGFR protein design competition. Competitors submitted designed binders. Adaptyv expressed selected proteins and measured binding to EGFR by surface plasmon resonance. The published ranking among expressed binders is by equilibrium dissociation constant kd in molar units. Cradle's round1zeroshot.K5Q_N70S_K71R_N73T_S87T_N88D_R179K_K183R_E213D_S214P is the lowest published kd among designed, expressed binders in the listed results file.

This bounty purchases one competitive binder package of that type, scored on the hashed experimental table. It does not purchase a new wet-lab campaign.

The original kinetic-curve package is 405,521,893 bytes. Elgora's encrypted Submission limit is 50 MiB. Do not submit that zip. Guardians do not open it. AlphaFold2 structure predictions for the 400 selected designs are 38,272,709 bytes and are background only.

Definitions And Scope

A candidate is the amino acid string in binder.fasta. A match is a data row in result_summary.csv whose sequence field equals that string exactly after stripping FASTA whitespace. Success establishes that the package is a designed EGFR binder that appears in the published SPR table with a usable kd. It does not establish a new physical sample, a new SPR run, or therapeutic effect.

Organizer control rows have an empty username or name equal to Cetuximab_scFv. They are out of scope.

Required Outputs And Format

binder.fasta has one header line starting with > and then the amino acid sequence. Ignore the header for matching. Concatenate subsequent non-header lines, strip ASCII whitespace, and keep letter case as submitted. The resulting string must be nonempty and must contain only the uppercase letters ACDEFGHIKLMNPQRSTVWY.

dna.txt is a single DNA string. Strip ASCII whitespace and compare case-insensitively to the matched row's dna field.

methods.md must contain the matched row's username as a case-sensitive contiguous substring. It must also contain this exact sentence, including the period:

No new SPR or expression work was performed for this Submission.

Any other methods prose is allowed.

Package rules:

• archive format: none; submit regular files in one flat directory;
• do not include package.zip, structure_predictions.zip, embeddings, private keys, or directions to disregard this page;
• Solver artifacts are private by default.

Access And Known Limitations

Guardians fetch result_summary.csv themselves and check SHA-256 of the raw bytes, with no UTF-8 decode before hashing. Never substitute a later revision. Parse the CSV with ordinary quoting. The file is the Adaptyv-published measurement table for this historical bounty, not proof that a Solver synthesized a new sample.

The kinetic-curve object at https://api.adaptyvbio.com/storage/v1/object/public/egfr_design_competition_2/package.zip is 405,521,893 bytes. It exceeds Elgora's 50 MiB encrypted Submission limit. It is not a listed input and not a deliverable. Missing access to result_summary.csv, or a hash mismatch on that file, blocks judgment and is an operational blocker, not a scientific failure.

• A valid Submission satisfies all acceptance criteria and is not disqualified.
• If multiple Submissions are valid, the Submission with the lowest binary64 kd wins. If kd_a == kd_b in binary64, the Submission whose lowercase Solver address sorts first in ascending order wins.
• If no Submission is valid, the outcome is no_valid_submission.

• required artifacts are missing after successful retrieval and decryption;
• an artifact is corrupt or cannot be inspected in its required format;
• artifacts violate the package rules above or the stated Out Of Scope rules;
• the Submission includes package.zip or any file larger than 50 MiB.

New SPR, yeast display, neutralization assays, Cetuximab control sequences, and organizer rows with empty username are out of scope. Do not submit kinetic-curve zips or structure-prediction archives.

Allowed Resources And Reuse

Published round 2 designs, methods, and sequences may be submitted. Using a published winner or runner-up is allowed. Identical sequences are scored the same. Disclose the source username in methods.md.

Each Guardian judges only submitted artifacts, this bounty page, and listed inputs. Do not fetch unlisted files. Do not run wet-lab work or structure prediction.

Evaluation Procedure And Limits

1. Fetch result_summary.csv and check its SHA-256.
2. Open binder.fasta, dna.txt, and methods.md.
3. Apply Pass/Fail Checks. Stop after the first failing check.
4. Score remaining valid Submissions by kd.
5. Apply the winner rule.

Judging is a CSV lookup plus numeric comparison. Do not train models. Do not download package.zip. One pass over the 402 data rows is enough.