Reproducible code and supporting data for "Developability-gated virtual screening of de novo anti-VEGF-A miniprotein binders"
Year: 2026
Type: software
Abstract: Code and data snapshot for the manuscript "Developability-gated virtual screening of de novo anti-VEGF-A miniprotein binders". What changed in v1.2 Corrected the author's institutional affiliation to its official English name, "College of Pharmacy, Dali University", throughout the repository (README, LICENSE, CODE_AUTHORS.md, UPLOAD_GUIDE.md and the script headers). Removed a stale ", multi-model" from the cited manuscript title so that the title in this repository matches the paper verbatim. Added .zenodo.json, so the archived record now carries the author name, ORCID (0009-0006-6442-4250), both affiliations, the MIT licence and keywords instead of inheriting the creator name and licence from the GitHub account. Corrected two documentation errors in UPLOAD_GUIDE.md: Zenodo metadata remains editable after publication (only the files and the PID are immutable), and citations should use the version DOI rather than the concept DOI. Contents code/ - the design, ranking and figure-generation pipeline (RFdiffusion -> ProteinMPNN -> ESMFold -> Boltz-1 -> MM-GBSA). data/ - representative structures and the per-seed energy tables. results/ - the derived tables behind the manuscript figures. Repro scripts for the three-deposit DOI workflow (zenodo_upload.py, backfill_dois.py). The raw model outputs and the APR-Score / CCS recovery record are deposited separately on Zenodo; both DOIs are listed in results_manifest.md. Licence: MIT for the code; the tables and structures under data/ are released under CC-BY-4.0. Funding: Yunnan Provincial Department of Education, Grant No. 2026J0890.
Author: Yang, Sitao
Institution: Dali University
Language: English
Subfield: Drug Discovery
Domain: Life Sciences
Open Access status: green
OpenAlex ID: W7213916859