Skip to content
#protein folding Dataset Open access

Reliability boundaries of protein language-model zero-shot variant scores: unified-score author-review research release

Oct 2026 · Zenodo (CERN European Organization for Nuclear Research)

Abstract

Reliability boundaries of protein language-model zero-shot variant scores: unified-score author-review research release Version: 2026.10.02-author-review. Scientific submission HOLD. Publication of this research artifact does not constitute journal submission, acceptance or independent scientific clearance. Scientific scope: A protein-language-model reliability-boundary atlas with 4,677 identified clinical variant scores across 20 genes. Current discrimination, five-fold out-of-fold calibration and saved identity-grouped refitting records use the same recovered score version. Nonclinical and historical gnomAD/antibody summaries remain explicitly separated. Included files: Current Article and readable SI, full figure/table sources and locked snapshots, 4,677 saved row scores, 4,677 OOF predictions, 5,000 saved refit metric records, reference identity hashes/lengths, scoring and analysis code, no-inference verifier, upstream notices and checksums. Reproduction boundary: The default standard-library verifier checks score identities, AUROC, OOF metrics/bins and saved refit summaries without model forwards, new calibrator fits or network access. Full matching reference sequences, original clinical input files and official model weights are upstream prerequisites and are not bundled. Unrecorded source release/access dates are not invented. Remaining limitations: Author-review/HOLD: no external, gene-disjoint or position-disjoint clinical validation. Historical gnomAD was not newly rescored; archived antibody interval identities remain unresolved. Public availability and byte identity do not attest independent scientific clearance. Public source: https://github.com/PeterPonyu/a3-plm-boundary-atlas, tag author-review-2026-10-02. README, DATA_SOURCES.md, THIRD_PARTY_NOTICES.md and the exact release manifest accompany the ZIP. SHA-256 identities bind the current Article/SI and payload; historical source-capsule contracts remain provenance only. Rights: author-owned code is MIT licensed; author-written text, tables and author-generated result aggregates are CC BY 4.0, to the extent of author rights. Third-party data, labels, source-image portions, structures, method implementations, weights, software and fonts retain upstream conditions and are not relicensed by this record.

View source

Similar papers

#computer vision Review Open access May 2015

A survey study on major technical barriers affecting the decision to adopt cloud services

The comparison of adopter and non-adopter sample reveals three potential adoption inhibitor, security, data privacy, and portability, which underlines the importance of the technical and security perspectives for research investigating the adoption of technology.

Nattakarn Phaphoom, Xiaofeng Wang, S. Samuel et al. · 111 citations · ⚡8
#computer vision Open access Feb 2018

Lean Internal Startups for Software Product Innovation in Large Companies: Enablers and Inhibitors

This study investigates how Lean internal startup facilitates software product innovation in large companies and identifies its enablers and inhibitors, and shows the potential of the method-in-action framework to investigate the Lean startup approach in non-startup context.

Henry Edison, Nina M. Smørsgård, Xiaofeng Wang et al. · 78 citations · ⚡6
#computer vision Book Open access Jul 2015

Understanding the affect of developers: theoretical background and guidelines for psychoempirical software engineering

This paper highlights the challenges to conduct proper affect-related studies with psychology, provides a comprehensive literature review in affect theory, and proposes guidelines for conducting psychoempirical software engineering.

D. Graziotin, Xiaofeng Wang, P. Abrahamsson · 56 citations · ⚡4
#machine learning Open access May 2017

What Influences the Speed of Prototyping? An Empirical Investigation of Twenty Software Startups

This study conducts a multiple case study on twenty European software startups and proposes a prototype-centric learning model in early stage software startups, and identifies factors that occur as barriers but also facilitators for prototyping in earlystage software startups.

Anh Nguyen-Duc, Xiaofeng Wang, P. Abrahamsson · 44 citations · ⚡5
#protein folding Open access Sep 2026

Programmable design of functional proteins from natural language

Pinal, a 16-billion-parameter foundation model that produces protein candidates from natural-language functional descriptions, supports natural language as a high-level interface for candidate generation in protein design, enabling programmable exploration with reduced reliance on manually specified structural or seque...

Fengyuan Dai, Shiyang You, Yudian Zhu et al. · 31 citations · ⚡3

Related blog posts

Google DeepMind Blog Sep 30, 2026

Introducing SynthID Bio

Proof of concept for watermarking AI-generated proteins while preserving biological function.

MIT News · Artificial Intelligence Aug 27, 2026

Looking beyond natural sequences

A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.