image: Ready for the future of Pharma.ai? Register here.
Credit: Insilico Medicine
A recent Nature Medicine publication by Insilico Medicine and its collaborators marks the first clinical-stage proof of concept (POC) for AI-enabled drug discovery, where Rentosertib (known as ISM001-055) demonstrated not only favorable safety profiles, but also potential to reverse the deadly process of pulmonary fibrosis in the “gold standard” of treatment effectiveness evaluation – a Phase IIa clinical trial named GENESIS-IPF. More importantly, Rentosertib boasts not only novel target and molecule structure, both empowered by Insilico’s proprietary Pharma.ai platform, but also an accelerated development process with more than 60% time saved from project initiation to preclinical candidate (PCC) nomination against the traditional method.
Since Insilico' s founding in 2014, the Pharma.ai platform has been through continuous expansion and optimization, all recorded and shared through update webinar series. In March 2025, Insilico’s newly announced Pharma.ai quarterly launch attracted interest from more than 300 professionals across various fields encompassing the whole life cycle of drug discovery, including medical research, biotech, pharma, and healthcare institutions.
Today, Insilico Medicine (“Insilico”), the clinical-stage generative artificial intelligence (AI)-driven drug discovery company, announces its upcoming Summer Pharma.ai Updates webinar, scheduled for 10 a.m. ET on July 10. During the webinar, Founder and CEO Alex Zhavoronkov, PhD, will provide the latest company developments and introduce new features and applications of Insilico’s AI software suite, with a particular focus on the latest advancements in Biology42 and Chemistry42 through product demos, in-depth explanations, and real-world use cases. Ready for the future of Pharma.ai? Register here.
Biology42：Enhancements for Antibody Design and Omics Data Analysis
On the biology side, Generative Biologics has continued to strengthen its capabilities in biomolecule design with the introduction of new 3D-based generative models for antibodies. These models support framework selection and enable more precise and reliable generation of antibody structures. The updated contact calculation feature now allows users to analyze interactions between generated binders and target proteins directly within the platform, improving the binder selection procedure. Additionally, we now support template-based screening for peptides, and users can fetch structural information directly from the RCSB Protein Data Bank, helping streamline and simplify the overall workflow.
As for PandaOmics, the omics data analysis tool for target and biomarker identification, latest updates include several powerful enhancements designed to improve usability, security, and data interpretation. Researchers can now duplicate default projects with a single click, creating editable versions preloaded with expertly curated comparisons to accelerate discovery. For enterprise-level security and scalability, PandaOmics now supports Virtual Private Cloud (VPC) deployment and advanced Single Sign-On (SSO) integration with identity providers like Okta. The new Multi-Entry Gene Support feature enables analysis of multiple molecular entities per gene—such as isoforms or transcripts—enhancing granularity in differential expression analysis. Finally, knowledge graphs, which reveal key biological relationships, can now be exported as high-quality PNG or editable PDF files for seamless inclusion in publications and presentations.
Chemistry42: Advancements in Foundation Models and Generative Chemistry AI for Next-Generation Drug Design
On the chemistry front, the spotlight is on the Nach01 foundation model, now available via AWS Marketplace. By integrating natural language processing (NLP), chemical data intelligence, and molecular point-cloud encoding, Nach01 creates a powerful tool for prediction and generation tasks using both 2D and 3D molecular data. The result is a versatile approach to drug design, with performance surpassing widely recognized benchmark tests.
In parallel, Chemistry42—the comprehensive generative chemistry platform—has received a major update with enhancements to its Alchemistry engine. The latest version accelerates relative binding free energy (RBFE) calculations by up to threefold while delivering improved output quality. Additionally, users can now analyze protein-ligand molecular dynamics directly within the platform, streamlining workflows and offering deeper insights into molecular interactions. Furthermore, the upgraded Alchemistry module demonstrates greater robustness, handling ligand poses with low structural overlap and enabling perturbations across alternative binding pockets and binding modes.
By integrating advanced AI and automation technologies, Insilico Medicine has demonstrated significant efficiency improvements in practical applications, setting a benchmark for AI-driven drug research and development. Compared to the typical 2.5–4 years required in traditional drug discovery, Insilico’s 22 nominated candidate drugs from 2021 to 2024 took only 12–18 months on average to progress from project initiation to nomination of preclinical candidates (PCCs), with each project requiring synthesis and testing of only about 60–200 molecules. The success rate from PCC to IND-enabling stage reached 100%.
About Insilico Medicine
Insilico Medicine, a leading and global AI-driven biotech company, utilizes its proprietary Pharma.AI platform and cutting-stage automated laboratory to accelerate drug discovery and advance innovations in life sciences research. By integrating AI and automation technologies and deep in-house drug discovery capabilities, Insilico is delivering innovative drug solutions for unmet needs including fibrosis, oncology, immunology, pain, and obesity and metabolic disorders. Additionally, Insilico is extending the reach of Pharma.AI across diverse industries, such as advanced materials, agriculture, nutritional products and veterinary medicine.
For more information, please visit www.insilico.com.