AI Science Tracker
EN

Random-forest screening helps identify kinase inhibitors with activity against two malaria targets

Stellenbosch University; University of Cape Town; GenAIRx · 15 Feb 2026 · medicine

Discovery

Random-forest screening helps identify kinase inhibitors with activity against two malaria targets

Source check: Source checked. Not independent scientific confirmation.

Finding: A random-forest classifier combined with molecular docking helped select five known kinase inhibitors for experimental evaluation. Afatinib and pexidartinib inhibited both synthetic hemozoin formation and the malaria parasite protein kinase G in vitro; their kinase IC 50 values were about 2.6 micromolar, and hemozoin-formation inhibition required much higher concentrations. The strongest compounds in the overall study came from a separate selection route based on chemical-space mapping and docking. These results identify laboratory starting points, not an effective malaria treatment.

Technology: Random-forest classifier

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

AI contribution
A random forest trained on 379 literature compounds and 1190 molecular fingerprint features predicted protein-kinase-G activity. Its probability threshold, applicability-domain filter and docking scores selected five purchased compounds; PCA enrichment and docking formed a separate route.
Test and result
Five purchased compounds belonged to the random-forest-plus-docking selection route, including one shared with the other route. Afatinib and pexidartinib each had protein-kinase-G IC 50 values around 2.6 micromolar and synthetic-hemozoin-formation IC 50 values of 230 and 140 micromolar, respectively.
Limitation / still unknown
These are in vitro enzyme and crystallization assays, not clinical efficacy or safety. The most promising overall compounds were selected without the random forest. The small test set does not establish one selection route as superior. PMC and Crossref record online publication on 15 February 2026 and an earlier issue date of 12 February; this entry uses the online date.
Evidence sources and annotation context

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

Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC12907745/ · https://doi.org/10.1002/cmdc.202500756

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: 21 Nov 2026. Review scope: Primary full-text Methods, compound-level selection table and assays, exact article-front DOI/title/PMCID, deposited date metadata and current PubMed publication-status metadata..

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.

Related catalog entries

Links use documented relationships where available, plus shared catalog context. A shared topic or model family does not establish a scientific dependency.