AI Science Tracker

Using Bibliometric Analysis and Machine Learning to Identify Compounds Binding to Sialidase-1.

Collaborations Pharmaceuticals (United States) · 20 Jan 2021 · medicine

Discovery

Using Bibliometric Analysis and Machine Learning to Identify Compounds Binding to Sialidase-1.

Source check: Source checked. Not independent scientific confirmation.

Finding: A Bayesian model ranked three candidates for testing; microscale thermophoresis found sialidase-1 binding for sulfameter (Kd 2.15 ± 1.02 μM) and mexenone (8.88 ± 4.02 μM). Enzyme activity and chaperone function were not tested.

Technology: Bayesian classifier

Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.

AI contribution
Assay Central used ECFP6 descriptors and a Bayesian model trained on curated ChEMBL and BindingDB IC50 data to rank compounds; toxicity and CNS filters also informed candidate selection.
Test and result
Three selected compounds were tested by microscale thermophoresis in triplicate against 5 nM recombinant human sialidase-1; two bound, with reported Kd values of 2.15 ± 1.02 μM (sulfameter) and 8.88 ± 4.02 μM (mexenone).
Limitation / still unknown
The paper states that the target model used a small training set and limited chemical space. The study measured binding, not sialidase activity, cellular chaperoning, or disease benefit.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://doi.org/10.1021/acsomega.0c05591

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: Full PMC paper, including Methods, results and limitations..

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.

Open in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.