Combining cutting edge computational and experimental methods for targeting KRAS mutations in non-small cell lung cancer
Year: 2026
Type: article
Abstract: Introduction Historically, KRAS mutations have been notoriously difficult to target despite their status as the most commonly mutated oncogene in the RAS gene family. However, pioneering work by Shokat and colleagues has led to the discovery of KRAS G12C-GDP mutant specific inhibitors, with two such inhibitors adagrasib and sotorasib now FDA approved for treatment of non-small cell lung cancer (NSCLC). Unfortunately, despite FDA approval, several patients did not achieve full treatment response. Further drug discovery is urgently needed to identify compounds capable of synergizing with available KRAS G12C inhibitors to prevent drug resistance, pan-KRAS inhibitors capable of binding multiple KRAS mutations, and KRAS-GTP inhibitors.Areas covered This review encompasses the development of the first KRAS G12C inhibitors through rational drug design, to recent advances in precision oncology utilizing artificial intelligence (AI) to identify compounds capable of targeting KRAS G12C, D, and V in-dividually, as well as pan-KRAS and SOS1 inhibitors. The literature search was made using PubMed and Google Scholar with keywords”KRAS G12C inhibitors,””NSCLC,””pan-KRAS inhibitors,””AI,” and”drug discovery” from 2013 to 2025.Expert opinion Recent studies support the view that integration of AI algorithms with experimental methods is a key aspect in stream-lining the drug discovery process and identifying molecules with greater structural diversity, less off target effects than traditional screening methods. Furthermore, the authors believe that AI will eventually become standardized in drug discovery and existing pipelines specific to KRAS mutant inhibitor design will be expanded for additional KRAS mutations as well as other aggressive driver oncogenes across multiple cancers.
Source: Expert Opinion on Drug Discovery
Institution: University at Buffalo, State University of New York
Language: English
Subfield: Molecular Biology
Domain: Life Sciences
Open Access status: green
Awards: G3791589606, G4045563614, G4733169064, G5382207646, PURPOSE:THE PURPOSE OF THIS PROJECT IS TO USE MACHINE LEARNING AND OTHER ADVANCED COMPUTATIONAL METHODS TO ACCELERATE THE THERAPEUTIC DRUG DISCOVERY PROCESS.ACTIVITIES TO BE PERFORMED:THE RESEARCHERS WILL ACQUIRE AND IMPLEMENT A HIGH-PERFORMANCE DATA ANALYTIC AND COMPUTING INFRASTRUCTURE AT THE UNIVERSITY AT BUFFALO (UB). THEY WILL USE THIS INFRASTRUCTURE TO APPLY THE COMPUTATIONAL ANALYSIS OF NOVEL DRUG OPPORTUNITIES (CANDO) PLATFORM TO DISCOVER AND DESIGN THERAPEUTIC DRUG THERAPIES TO TREAT A VARIETY OF HIGH PRIORITY DISEASES.EXPECTED OUTCOMES:THE PROJECT EXPECTS TO RAPIDLY IDENTIFY NOVEL COMPOUNDS WITH THE POTENTIAL TO BE USED AS THERAPEUTICS. IN ADDITION, THIS FACILITY WILL IMPROVE RESEARCH, TRAINING, AND EDUCATION ACTIVITIES AT UB.INTENDED BENEFICIARIES:THIS IS TO ACQUIRE A HIGH-PERFORMANCE DATA ANALYTIC INFRASTRUCTURE TO SUPPORT A COMPUTATIONAL DRUG DISCOVERY PLATFORM. THIS WILL LEAD TO COMMERCIALIZATION OF NEW DRUGS FOR PATIENT USE BENEFITING THE US PHARMACEUTICAL INDUSTRY, PUBLIC, AND RESEARCHERS INTERESTED IN DRUG DISCOVERY METHODS.SUBRECIPIENT ACTIVITIES:THE RECIPIENT DOES NOT INTEND TO SUB AWARD FUNDS., G9000068634, G9000263877, Buffalo Research Innovation in Genomic and Healthcare Technology Education (BRIGHT Education)
OpenAlex ID: W7155017840