Core Insights - KRAS is one of the most mutated cancer driver genes, traditionally considered "undruggable" due to its smooth surface and high affinity for GTP/GDP, but recent advancements in targeting specific mutations like KRAS G12C have shown some progress [1] - Insilico Medicine (03696) is developing a pan-KRAS inhibitor strategy that targets multiple key mutations, with the oral small molecule ISM6166 showing promise for treating various KRAS-driven solid tumors such as lung, pancreatic, colorectal, and gastric cancers [1] - ISM6166 has demonstrated significant tumor suppression and regression effects in preclinical studies while maintaining high selectivity and favorable pharmacokinetic properties, indicating a balanced drug-like profile [1] Efficacy Data - In lung cancer models, ISM6166 achieved an 86.2% tumor growth inhibition rate (TGI) at a dose of 10 mg/kg and a 55.1% tumor regression at 30 mg/kg [2] - In gastric cancer models, ISM6166 showed even more pronounced anti-tumor efficacy, with a TGI of 99.5% at 5 mg/kg and up to 65.8% tumor regression at higher doses [2] Selectivity and Pharmacokinetics - ISM6166 maintains high selectivity for other RAS family proteins, which is crucial for reducing off-target toxicity and potential side effects [4] - The compound has shown good plasma clearance rates and acceptable oral bioavailability across four preclinical species, supporting its potential as a best-in-class oral therapy [4] Research Background - This is not the first time Insilico Medicine has leveraged its AI capabilities in the "undruggable" space; in 2025, the company was recognized in the Nature Biotechnology's top ten research advancements for its KRAS-related studies, which combined quantum and classical computing methods for small molecule design [4]

Core Insights - KRAS is one of the most mutated cancer driver genes, traditionally considered "undruggable" due to its smooth surface and high affinity for GTP/GDP, but recent advancements in targeting specific mutations like KRAS G12C have shown some progress [1] - Insilico Medicine's ISM6166 aims to address the limitations of existing KRAS inhibitors by targeting multiple key mutations and is expected to cover various KRAS-driven solid tumors such as lung, pancreatic, colorectal, and gastric cancers [1] - ISM6166 has demonstrated significant tumor suppression and regression effects in preclinical studies while maintaining high selectivity and favorable pharmacokinetic properties, indicating a balanced drug-like profile [1] Drug Efficacy - In lung cancer models, ISM6166 achieved an 86.2% tumor growth inhibition rate (TGI) at a dose of 10 mg/kg and a 55.1% tumor regression at 30 mg/kg [2] - In gastric cancer models, ISM6166 showed even more pronounced anti-tumor efficacy, with a TGI of 99.5% at 5 mg/kg and up to 65.8% tumor regression at higher doses [2] Selectivity and Pharmacokinetics - ISM6166 maintains high selectivity for other RAS family proteins, which is crucial for reducing off-target toxicity and potential side effects [4] - The compound has shown good plasma clearance rates and acceptable oral bioavailability across four preclinical species, supporting its potential as a best-in-class oral therapy [4] Research Background - This is not the first time Insilico Medicine has leveraged its AI capabilities in the "undruggable" space; in 2025, the company was recognized in Nature Biotechnology's top ten research advancements for its KRAS-related studies, which combined quantum and classical computing methods for small molecule design [4]

Core Insights - The focus of cancer drug development is shifting towards targeting "undruggable" targets, moving from traditional optimization of mature targets to innovative strategies that aim to overcome long-standing challenges in drug development [1][16][29] Target: MYC - MYC has been considered a classic "undruggable" target due to its dynamic protein structure and lack of stable binding pockets, making traditional small molecules ineffective [1][16] - The mini-protein therapy OMO-103 has shown promising early activity signals in human studies, with manageable safety profiles and no dose-limiting toxicities observed, particularly in advanced solid tumors [2][17] - A targeted degradation approach using VHL E3 ligase recruitment has demonstrated the ability to dose-dependently clear endogenous MYC protein, showing biological activity in breast and prostate cancer models [2][17] Target: KRAS - KRAS is recognized as one of the most representative "undruggable" targets in oncology, with drug development hindered by its unique molecular biology [3][18] - The KRAS G12C inhibitors sotorasib and adagrasib have received FDA approval, marking a shift towards broader precision interventions [3][18] - The RAS(ON) tri-complex inhibitor zoldonrasib has shown a 61% objective response rate in previously treated non-small cell lung cancer patients, indicating effective pharmacological control over the KRAS G12D mutation [3][18][20] Target: MTAP - MTAP deficiency presents a unique challenge, as it is not a traditional oncogenic driver but is prevalent in various tumors, leading to a lack of clear drug development pathways [6][21] - The PRMT5 inhibitor AMG193 has shown selective inhibition of tumor cells with MTAP deficiency, demonstrating initial anti-tumor activity in late-stage solid tumor patients [6][21][22] - Other candidates like MRTX1719 and TNG462 are in early clinical studies to further validate the synthetic lethality strategy associated with MTAP deficiency [6][22] Target: TP53 - TP53 mutations are widespread in human cancers, complicating traditional inhibitor strategies due to the loss of tumor suppressor function [7][23] - MDM2 inhibitors aim to restore p53 function by relieving its inhibition, with early studies confirming the activation of the p53 pathway and tumor growth suppression [7][23][25] - Small molecule correction strategies targeting mutant TP53 have shown preliminary clinical response signals, indicating potential for restoring p53 function [7][25] Target: WNT/β-catenin Pathway - The WNT/β-catenin pathway is essential for physiological processes but poses safety challenges in therapeutic development due to its role in embryonic development and tissue homeostasis [8][11][26] - The PORCN inhibitor zamaporvint has shown clinical benefit in combination with PD-1 inhibitors in specific colorectal cancer patients, achieving a disease control rate of 57.1% [8][11][26] - Downstream regulatory strategies, such as β-catenin–TBL1 complex inhibitors, are being explored for their potential to selectively modulate tumor activity while maintaining normal physiological functions [8][11][27]

Core Viewpoint - Targeted protein degradation represents a significant advancement in treating diseases previously deemed untreatable, particularly for traditionally "undruggable" targets such as transcription factors and scaffold proteins [2][6]. Group 1: Development of New Screening Methods - A novel high-throughput screening platform named DEFUSE (DE ath FUS ion E scaper) has been developed to identify small molecule protein degraders, enabling efficient degradation of oncoprotein SKP2 [3][10]. - The DEFUSE platform utilizes a fusion of target proteins with a rapidly activated death protein, allowing for a visual representation of cell survival or death based on the presence of degradation compounds [6][8]. Group 2: Discovery of New Degraders - The research team identified a small molecule, SKPer1, which specifically promotes the degradation of the oncogenic protein SKP2 and selectively kills SKP2-expressing cancer cells [8][10]. - SKPer1 functions as a novel molecular glue degrader, recruiting SKP2 to the ubiquitin ligase STUB 1, facilitating its ubiquitination and subsequent degradation [8][10]. Group 3: Implications for Cancer Treatment - SKPer1 demonstrated significant tumor-suppressive effects in vivo and exhibited good safety profiles, indicating its potential as a therapeutic agent [10]. - The study suggests that a 10-amino acid sequence derived from SKP2 can serve as a universal degradation tag, allowing other target proteins fused with this tag to be recruited for degradation by SKPer1 [10].

Core Viewpoint - Intrinsically disordered proteins (IDPs) and intrinsically disordered regions (IDRs) represent about 60% of the human proteome and are crucial for various cellular functions and disease progression. Recent advancements in artificial intelligence (AI) have enabled the design of specific binding agents for these previously considered "undruggable" targets, unlocking new therapeutic possibilities [1][2][20]. Group 1: Importance of IDPs and IDRs - IDPs and IDRs play significant roles in cellular signaling, stress responses, and disease progression, making them valuable targets for clinical diagnostics and drug development [2][8]. - Traditional drug design struggles with IDPs due to their lack of stable structure, which complicates the development of targeted therapies [6][7]. Group 2: AI Breakthroughs in Drug Design - The research led by David Baker's team utilized generative AI to design proteins that can accurately bind to IDPs and IDRs, achieving atomic-level precision [2][11]. - The AI model, RFdiffusion, allows for dynamic matching without pre-setting structures, enabling the generation of binding proteins that can adapt to the flexible nature of IDPs [11][12]. Group 3: Experimental Results and Applications - The studies published in Nature and Science demonstrated the successful design of binding proteins for various IDPs, with binding affinities ranging from 3 to 100 nanomolar [15][18]. - These binding proteins have shown potential in therapeutic applications, such as inhibiting amyloid fiber formation related to type 2 diabetes and disrupting stress granule formation in neurodegenerative diseases [16][18]. Group 4: Future Implications - The new design strategies developed could lead to innovative treatment methods and diagnostic tools for diseases associated with IDPs and IDRs, marking a significant advancement in precision medicine [20][24]. - The complementary strategies of RFdiffusion and logos provide a robust framework for targeting both structured and unstructured protein regions, enhancing the versatility of drug design [21][22].

Core Viewpoint - The article discusses the breakthrough in targeting intrinsically disordered proteins (IDPs) and intrinsically disordered regions (IDRs) using artificial intelligence (AI), specifically through the work of Professor David Baker and his team, which has made previously "undruggable" targets accessible for drug development [3][5][20]. Group 1: Research Breakthroughs - The research led by Professor David Baker utilizes generative AI to design proteins that can precisely bind to IDPs and IDRs, achieving atomic-level accuracy [3][5]. - The studies employed two complementary design strategies based on amino acid sequences, eliminating the need for structural information, thus enhancing the universality of drug discovery [7][22]. - The first study published in Science demonstrated the design of binding proteins for 43 diverse disordered protein targets, achieving tight binding for 39 of them, with affinities ranging from 100 picomolar to 100 nanomolar [14][20]. Group 2: Applications and Implications - The designed binding proteins show potential applications in various fields, including cancer treatment, disease diagnostics, and intervention in neurodegenerative diseases [14][20]. - Specific examples include a binding protein targeting enkephalin that successfully blocked pain signal transduction in human cells [14][21]. - The second study, available on bioRxiv, reported the design of binding proteins for various IDPs and IDRs, with affinities also in the range of 3-100 nanomolar [17][20]. Group 3: Methodology and Tools - The research utilized a protein design strategy called "logos," which created a library of binding pockets to recognize amino acid side chains, allowing for the assembly of binding proteins [9][11]. - The RFdiffusion model was employed to generate novel proteins that do not exist in nature, demonstrating its effectiveness in various therapeutic contexts [5][22]. - The strategies developed in these studies are now available online for researchers to use freely, promoting further exploration in the field [23][24].

Core Insights - Quantum physics, AI, and robotics drug and new materials development platform, CrystalTech (02228), has entered a strategic partnership worth billions with DoveTree LLC, founded by renowned chemist Gregory Verdine [1] - The agreement grants DoveTree exclusive global rights to multiple pipelines in oncology, autoimmune, and neurological diseases, with CrystalTech receiving a total of $100 million in upfront payments and potential milestone payments worth billions [1][10] Company Overview - Gregory Verdine is a pioneer in chemical biology and a successful entrepreneur, having founded over 12 biotech companies, with 7 going public and one being acquired [2][3] - Verdine's innovative "Stapled Peptides" technology has opened new pathways for targeting "undruggable" targets, creating a market valued in the billions [2][6] Financial Implications - CrystalTech will receive $51 million and $49 million in upfront payments within 10 and 180 days post-signing, respectively, along with potential milestone payments and royalties based on annual net sales [1][10] - The collaboration is expected to significantly enhance CrystalTech's financial returns and support ongoing R&D efforts [10] Market Potential - Verdine's work has led to the successful development of drugs targeting traditionally "undruggable" targets, generating over $30 billion in sales from three major drugs [6][8] - The partnership is seen as a model for combining U.S. intellectual property with Chinese efficiency, potentially unlocking a multi-billion dollar market for previously untargetable drug targets [10] Strategic Positioning - The collaboration elevates CrystalTech's status in the industry and may inspire further high-tech partnerships [10] - Verdine's extensive experience and network in the biotech sector, including roles with top venture capital firms, positions the partnership for success in the evolving landscape of drug development [9][10]