Related Experiment Video
Updated: Jan 2, 2026
Using Human Differentially Expressed Gene Lists to Perform Downstream Pathway Enrichment Analysis and Target Prioritization
Published on: October 3, 2025
Identification of Targetable Pathways in Oral Cancer Patients via Random Forest and Chemical Informatics
John Schomberg1,2,3
1CHOC Children's, Orange, CA, USA.
Abstract:
Treatment of head and neck cancer has been slow to change with epidermal growth factor receptor (EGFR) inhibitors, PD1 inhibitors, and taxane-/plant-alkaloid-derived chemotherapies being the only therapies approved by the U.S. Food and Drug Administration (FDA) in the last 10 years for the treatment of head and neck cancers. Head and neck cancer is a relatively rare cancer compared to breast or lung cancers. However, it is possible that existing therapies for more common solid tumors or for the treatment of other diseases could also prove effective against oral cancers. Many therapies have molecular targets that could be appropriate in oral cancer as well as the cancer in which the drug gained initial FDA approval. Also, there may be targets in oral cancer for which existing FDA-approved drugs could be applied. This study describes informatics methods that use machine learning to identify influential gene targets in patients receiving platinum-based chemotherapy, non-platinum-based chemotherapy, and genes influential in both groups of patients. This analysis yielded 6 small molecules that had a high Tanimoto similarity (>50%) to ligands binding genes shown to be highly influential in determining treatment response in oral cancer patients. In addition to influencing treatment response, these genes were also found to act as gene hubs connected to more than 100 other genes in pathways enriched with genes determined to be influential in treatment response by a random forest classifier with 20 000 trees trying 320 variables at each tree node. This analysis validates the use of multiple informatics methods to identify small molecules that have a greater likelihood of efficacy in a given cancer of interest.
Insights
This study used machine learning to find new small molecule treatments for head and neck cancers by identifying key genes. Six promising molecules were identified, offering potential for improved oral cancer therapy.
Area of Science:
- Oncology
- Bioinformatics
- Computational Chemistry
Background:
- Head and neck cancer treatment has seen limited FDA-approved therapies in the past decade.
- Existing drugs for other cancers may hold potential for oral cancer treatment due to shared molecular targets.
- Identifying novel therapeutic targets is crucial for advancing head and neck cancer care.
Purpose of the Study:
- To employ informatics and machine learning to pinpoint influential gene targets in head and neck cancer patients undergoing chemotherapy.
- To identify potential small molecule drugs with high efficacy for oral cancer based on influential gene targets.
- To validate the use of computational methods for discovering new cancer therapies.
Main Methods:
- Utilized machine learning, specifically a random forest classifier, to identify influential genes in patients receiving platinum-based and non-platinum-based chemotherapy.
- Analyzed gene networks to find influential genes acting as hubs within pathways related to treatment response.
- Applied Tanimoto similarity analysis to identify small molecules targeting influential genes.
Main Results:
- Identified influential genes in head and neck cancer patients, differentiating responses to various chemotherapies.
- Discovered 6 small molecules exhibiting high Tanimoto similarity (>50%) to ligands of influential genes.
- Found that influential genes act as critical hubs, connecting to over 100 other genes in relevant pathways.
Conclusions:
- Informatics methods, including machine learning, are effective in identifying potential therapeutic small molecules for head and neck cancers.
- The identified small molecules show promise for future development as targeted therapies for oral cancer.
- This approach validates the use of computational strategies to accelerate the discovery of novel cancer treatments.
Related Concept Videos
02:57Targeted Cancer Therapies
There are several types of targeted therapies against...
02:50Combination Therapies and Personalized Medicine
The combination of the drug acetazolamide and sulforaphane is a good example of combination therapy to treat cancer. The cells in the interior of a large tumor often die due to the hypoxic and...