Seqanswers Leaderboard Ad

Collapse

Announcement

Collapse
No announcement yet.
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • AI-Driven Analysis of Tumor Genetics Enhances Chemotherapy Prediction

    Click image for larger version  Name:	Low-Res_national-cancer-institute-jdfn7Z03Qa4-unsplash.jpg Views:	0 Size:	178.1 KB ID:	325404
    Cervical cancer, shown here at the cellular level, frequently resists treatment. The researchers’ machine learning algorithm could help scientists better understand why this and other forms of cancer resist chemotherapy. (Image Credit: National Cancer Institute​)




    In a recent article published in Cancer Discovery, a team from the University of California San Diego School of Medicine reported on the development of a machine learning algorithm designed to predict cancer resistance to chemotherapy. This research addresses a critical challenge in oncology: anticipating when cancer will resist treatment.

    Understanding Cancer Resistance Through AI
    The study focuses on the role of a tumor's genetic makeup in determining its response to chemotherapy, particularly drugs targeting DNA replication in cancer cells. The complexity of the mutations within tumors has historically made predicting drug resistance difficult. However, the newly developed algorithm surmounts this challenge by examining how various genetic mutations collectively affect a tumor’s reaction to chemotherapy agents.

    The team tested this model specifically on cervical cancer tumors, assessing their responses to cisplatin. The model could not only pinpoint tumors most likely to resist treatment but also identify key elements of the molecular machinery that drive this resistance.

    Insights from the Researchers
    Dr. Trey Ideker, a professor in the Department of Medicine at UC San Diego, emphasized the importance of understanding a broad spectrum of mutations. "Clinicians were previously aware of a few individual mutations that are associated with treatment resistance, but these isolated mutations tended to lack significant predictive value. The reason is that a much larger number of mutations can shape a tumor's treatment response than previously appreciated," Ideker explained. He added, "Artificial intelligence bridges that gap in our understanding, enabling us to analyze a complex array of thousands of mutations at once."

    A significant hurdle in comprehending drug effects on tumors lies in the inherent sophistication of the DNA replication process, which is frequently targeted by cancer medications. “Hundreds of proteins work together in complex arrangements to replicate DNA," Ideker stated. "Mutations in any one part of this system can change how the entire tumor responds to chemotherapy.”

    The Machine Learning Approach
    The research team used a standard set of 718 genes, typically employed in clinical genetic testing for cancer, as the initial data input for their algorithm. After training the model with publicly available drug response data, it identified 41 molecular assemblies where genetic alterations influence drug efficacy.

    Ideker highlighted the network-based nature of cancer and the limitations of previous models. "Rather than focusing on a single gene or protein, our model evaluates the broader biochemical networks vital for cancer survival," he said.

    Testing and Transparency of the Model
    When applied to cervical cancer, the model accurately identified tumors likely to respond positively to treatment and those prone to resistance. Importantly, the model also offers insights into its decision-making process by pinpointing the protein assemblies driving treatment resistance.

    "Unraveling an AI model's decision-making process is crucial, sometimes as important as the prediction itself," Ideker remarked. He sees the model's transparency as a significant strength, building trust in the AI system and identifying potential new targets for chemotherapy.

    This AI-driven approach not only enhances the prediction of chemotherapy outcomes but also opens avenues for developing new treatment strategies. While optimistic about the broad applications of their model, the researchers maintain a cautious approach, focusing on the practical and immediate benefits of this technology in enhancing current cancer treatments.

    Original Publication
    Xiaoyu Zhao, Akshat Singhal, Sungjoon Park, JungHo Kong, Robin Bachelder, Trey Ideker; Cancer mutations converge on a collection of protein assemblies to predict resistance to replication stress. Cancer Discov 2024; https://doi.org/10.1158/2159-8290.CD-23-0641

Latest Articles

Collapse

  • seqadmin
    Exploring the Dynamics of the Tumor Microenvironment
    by seqadmin




    The complexity of cancer is clearly demonstrated in the diverse ecosystem of the tumor microenvironment (TME). The TME is made up of numerous cell types and its development begins with the changes that happen during oncogenesis. “Genomic mutations, copy number changes, epigenetic alterations, and alternative gene expression occur to varying degrees within the affected tumor cells,” explained Andrea O’Hara, Ph.D., Strategic Technical Specialist at Azenta. “As...
    07-08-2024, 03:19 PM
  • seqadmin
    Exploring Human Diversity Through Large-Scale Omics
    by seqadmin


    In 2003, researchers from the Human Genome Project (HGP) announced the most comprehensive genome to date1. Although the genome wasn’t fully completed until nearly 20 years later2, numerous large-scale projects, such as the International HapMap Project and 1000 Genomes Project, continued the HGP's work, capturing extensive variation and genomic diversity within humans. Recently, newer initiatives have significantly increased in scale and expanded beyond genomics, offering a more detailed...
    06-25-2024, 06:43 AM

ad_right_rmr

Collapse

News

Collapse

Topics Statistics Last Post
Started by seqadmin, Today, 11:09 AM
0 responses
14 views
0 likes
Last Post seqadmin  
Started by seqadmin, 07-19-2024, 07:20 AM
0 responses
146 views
0 likes
Last Post seqadmin  
Started by seqadmin, 07-16-2024, 05:49 AM
0 responses
120 views
0 likes
Last Post seqadmin  
Started by seqadmin, 07-15-2024, 06:53 AM
0 responses
111 views
0 likes
Last Post seqadmin  
Working...
X