An Artificial Intelligence Characterised Functional Ingredient, Derived from Rice, Inhibits TNF-α and Significantly Improves Physical Strength in an Inflammaging Population.
Source check: Source checked. Not independent scientific confirmation.
Finding: An ensemble of ten neural networks predicted anti-inflammatory rice peptides, which were identified in a rice peptide hydrolysate and tested in vitro. A 12-week pilot randomized 40 older adults (30 rice NPN, 10 placebo); its primary digestive-discomfort endpoint was not met, while secondary physical-performance and biomarker outcomes favored treatment. Small sample, compliance/timing confounding, and the ingredient-versus-isolated-peptide distinction limit inference.
Technology: Trained neural-network ensemble for peptide bioactivity prediction
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
- AI contribution
- A ten-model neural-network ensemble predicted anti-inflammatory peptides from food proteomes and helped characterize peptides detected in rice NPN; peptide and ingredient effects were then tested by mass spectrometry, cell assays, and a human pilot. The AI prediction itself did not establish clinical effect.
- Test and result
- Eight predicted peptides were synthesized; seven reduced TNF-α secretion in stimulated THP-1 assays. A 12-week pilot randomized 40 older adults (rice NPN 30, placebo 10). The digestive-discomfort primary endpoint was not met; secondary chair-stand/SPPB results favored treatment. Figure captions report at least 27/10 and 28/10 analyzed for those outcomes, respectively.
- Limitation / still unknown
- The pilot was small and randomized 30:10; the primary subjective endpoint was not met, and authors noted compliance and Christmas-period measurement as confounders. The clinical intervention was a rice peptide hydrolysate, so effects cannot be assigned to individual AI-predicted peptides. Clinical efficacy and generalizability need confirmation.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://doi.org/10.3390/foods9091147
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 18 Nov 2026. Review scope: Publisher Methods on peptide prediction and pilot design; peptide Results, human Results and outcome-specific figure-caption denominators..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 3/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.