Insilico Medicine Selects AI Designed Obesity Drug Candidate ISM1354

Sep 30, 2026
Insilico Medicine selected ISM1354 as a preclinical small molecule candidate targeting GIPR for potential treatment of obesity and related conditions.

Insilico Medicine selected ISM1354 as a preclinical small molecule candidate targeting GIPR for potential treatment of obesity and related conditions. The company announced the selection in a press release.

Insilico used its Chemistry42 platform to generate and optimize molecules for potency, selectivity, and safety. The process included a drug induced liver injury prediction model, affinity ranking, and repeated testing with experimental feedback.

In preclinical studies, ISM1354 showed oral bioavailability of 75% to 104% across mice, rats, dogs, and monkeys. Insilico said the compound produced at least 18 fold greater plasma exposure than a clinical stage benchmark at the same dose and showed weaker inhibition of the OATP1B1 transporter.

The compound had minimal effects on human and monkey liver cell viability at concentrations up to 200 micromolar. A monkey toxicology assessment found no significant toxicity and indicated an estimated safety margin of about 45 fold, supporting further toxicology studies.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Life AI Weekly or Daily AI Brief.

Also, consider following us on social media:

Healthcare & Life Sciences AI AI Brief AI Brief (X)
Free newsletter

Life AI Weekly

Weekly coverage of AI applications in healthcare, drug development, biotechnology research, and genomics breakthroughs.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.