Skip to main content
Tessa NewsLink
Paste a health news link, or browse
Latest checks

Source study found

Story checked

Researchers use AI to identify early-stage inhibitors for antiviral therapy (opens in a new tab)

news-medical.net · 2026-10-19

Short answerEvidenceSource

Short answer

Needs review

Study found.

We found the study, but the claim check did not finish.

Share this check

Follow the evidence trail
1
2

NewsLink checks it

We found the study behind this story.

We found the study, but couldn't compare the story to it: the study's evidence could not be profiled.

Open claim evidence
3
Then inspect each claim

Evidence layer

Claim by claim

The source study was found, but the study's evidence could not be profiled, so these claims couldn't be checked.

Claim 1 of 5Not checkedResearchers at Korea University developed an artificial intelligence-guided strategy to discover molecules that inhibit deoxyhypusine synthase (DHPS), a human enzyme involved in eIF5A hypusination and viral replication.View evidenceHide evidence

Not checked

The source study was found, but this claim couldn't be checked against it.

Claim 2 of 5Not checkedThe researchers benchmarked 13 machine-learning models for predicting molecular binding scores and 10 methods for generating new molecules, using DHPS as a common target; Out-of-Fold Stacking performed best overall among the prediction models, while RL-Design had the highest predicted hit rate at 92.02% and 98.0% of its top-ranked molecules met a drug-likeness threshold.View evidenceHide evidence

As stated13 models, 10 generation methods, 92.02% predicted hit rate, 98.0% drug-likeness threshold pass rate

Not checked

The source study was found, but this claim couldn't be checked against it.

Claim 3 of 5Not checkedSix AI-selected fragments were experimentally tested, and all three predicted-active fragments inhibited DHPS while none of the three predicted-inactive fragments did; two active fragments had IC50 values of 31.2 and 49.1 μM.View evidenceHide evidence

As stated6 fragments; 3 active and 3 inactive; IC50 values of 31.2 and 49.1 μM

Not checked

The source study was found, but this claim couldn't be checked against it.

Claim 4 of 5Not checkedAn X-ray co-crystal structure provided structural evidence for binding of one AI-generated compound at the entrance of the DHPS substrate and NAD-binding pocket.View evidenceHide evidence

Not checked

The source study was found, but this claim couldn't be checked against it.

Claim 5 of 5Not checkedThe authors describe the hits as early-stage fragments rather than drug candidates and say further studies are needed to establish inhibition mechanisms, selectivity, cellular activity, toxicity, and performance in animal models.View evidenceHide evidence

Not checked

The source study was found, but this claim couldn't be checked against it.

Finally, the search trail

Method layer

NewsLink found the paper. Tessa takes you deeper.

NewsLink checks the story. Tessa is where you inspect the paper, authors, evidence, and research context.

Open the paper in Tessa

AI-guided De Novo design of DHPS inhibitors

Journal of Cheminformatics · 2026

Source record (opens in a new tab)

Why this one

Near certain

NewsLink found the paper. Tessa is where you inspect it deeply.

Papers considered

The selected paper, plus nearby candidates.

Crossref, Europe PMC, PubMed · 40 candidate papers

And 34 more candidates considered.