Work

Natural-Product Models Learn What Databases Choose to Record: A Data-Governance Architecture for Structures, Spectra, Bioassays, Taxonomy, Provenance, and Negative Results

Year: 2026

Type: article

Abstract: Natural-product machine-learning models do not encounter molecules, spectra, organisms, or biological responses directly; they encounter database records produced through choices about what is deposited, normalized, linked, corrected, omitted, and retained. This article develops an original data-governance architecture for natural-product modeling that treats these choices as part of the inferential system rather than as background data-management operations. The analysis integrates structural i

Source: Specialty journal of Pharmacognosy Phytochemistry and Biotechnology

DOI: 10.51847/jujwjdusfg

Authors: Gabriel Costa, Lucas Ribeiro, Ricardo Alves, Mariana Lopes

Institutions: Universidade Federal de Minas Gerais, University of Coimbra, Universidade de São Paulo

Topic: Research Data Management Practices

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

OpenAlex ID: W7204997157

FWCI:

Cites: 35

Cited by:

Related to: