Unlocking the Potential of AI: Development of BRAF Inhibitors for Ameloblastomas

SANTANA, LUCAS A.M.; TORRES, GINA D.R.; , RAJIV G. GOPALSAMY; , VIRGÍNIA K.S. SILVA; , JANAÍNA A. DANTAS; , FELIPE R. DE MATOS; , CARLOS EDUARDO P. REPEKE; BORGES, LYSANDRO P.

doi:10.1590/0001-3765202520250442

Ameloblastoma is a benign odontogenic tumor characterized by a slow growth rate but notable for its locally aggressive behavior and high recurrence rate (Effiom et al. 2018). Studies have highlighted recurrent somatic mutations in the mitogen-activated protein kinase (MAPK) pathway, particularly the BRAFV600E mutation, in ameloblastomas (Anbinselvam et al. 2024). This same mutation is observed in other malignancies, such as melanoma and thyroid cancer, where targeted therapies using BRAF inhibitors have demonstrated remarkable clinical efficacy (Chen et al. 2023).

In this context, we discuss the potential application of artificial intelligence (AI) in predicting and developing novel BRAF inhibitors for ameloblastoma treatment. AI has revolutionized healthcare by advancing disease diagnosis, clinical decision-making, medical imaging, and drug discovery (Hillary et al. 2024). The drug development process is inherently complex, requiring extensive time, resources, and rigorous preclinical and clinical testing to ensure safety and efficacy (Yang & Kar 2023). However, AI, particularly machine learning, enables the integration and analysis of large datasets, accelerating problem-solving and facilitating breakthroughs in drug discovery (Yang & Kar 2023). For ameloblastomas, AI-driven methods could offer a more personalized treatment strategy, particularly for tumors containing the BRAFV600E mutation.

BRAF-positive tumors often exhibit aggressive behavior, an increased risk of recurrence, and resistance to apoptosis (Fregnani et al. 2017). While some studies suggest that the BRAFV600E mutation does not significantly affect the progression of ameloblastomas, early reports on BRAF inhibitors, such as dabrafenib and vemurafenib, have shown promising results (Ebeling et al. 2023, Martins-de-Barros et al. 2024).

Resistance to BRAF inhibitors is often driven by genetic and non-genetic mechanisms, including the formation of BRAF homodimers, hyperactivation of MEK within the MAPK pathway, and activation of alternative signaling pathways such as PI3K/AKT (Proietti et al. 2020). Furthermore, the loss of the tumor suppressor PTEN has been linked to resistance mechanisms (Proietti et al. 2020). These alterations underscore the need for innovative therapeutic strategies, such as combination therapies (e.g., BRAF inhibitors with MEK inhibitors), next-generation BRAF inhibitors, and novel immunotherapy approaches (Zhong et al. 2022).

Alternatively, AI could play a pivotal role in addressing these challenges. Tools like AlphaFold, a neural network-based model for protein structure prediction, have already demonstrated remarkable accuracy in predicting protein folding from amino acid sequences (Yang et al. 2023). This technology has shown potential in peptide based drug discovery, offering critical insights into novel compounds’ physicochemical properties and toxicity profiles (Gupta et al. 2021). By leveraging AI-driven platforms, researchers can accelerate the design of next-generation BRAF inhibitors tailored to ameloblastomas, potentially overcoming resistance mechanisms and enhancing clinical outcomes. Through murine models, these drugs can be preliminarily evaluated for their safety and efficacy in a therapeutic context (Guo et al. 2024).

In conclusion, developing AI-designed BRAF inhibitors offers a novel avenue for improving the treatment of ameloblastomas. Future studies should prioritize validating these approaches, exploring combination therapies, and incorporating AI into clinical workflows to enhance therapeutic efficacy and minimize resistance. The synergy between AI, oncology, and pharmacology holds the potential to transform the management of ameloblastomas and other challenging tumors, ultimately improving patient care and outcomes.

References

ANBINSELVAM A, AKINSHIPO AO, ADISA AO, EFFIOM OA, ZHU X, ADEBIYI KE, AROTIBA GT & AKINTOYE SO. 2024. Comparison of diagnostic methods for detection of BRAFV600E mutation in ameloblastoma. J Oral Pathol Med 53(1): 79-87.
CHEN D ET AL. 2023. Papillary thyroid cancer organoids harboring BRAFV600E mutation reveal potentially beneficial effects of BRAF inhibitor-based combination therapies. J Transl Med 21(1): 9.
EBELING M, SCHEURER M, SAKKAS A, PIETZKA S, SCHRAMM A & WILDE F. 2023. BRAF inhibitors in BRAF V600E-mutated ameloblastoma: systematic review of rare cases in the literature. Med Oncol 40(6): 163.
EFFIOM OA, OGUNDANA OM, AKINSHIPO AO & AKINTOYE SO. 2018. Ameloblastoma: current etiopathological concepts and management. Oral Dis 24(3): 307-316.
FREGNANI ER, PEREZ DE, PAES DE ALMEIDA O, FONSECA FP, SOARES FA, CASTRO-JUNIOR G & ALVES FA. 2017. BRAF-V600E expression correlates with ameloblastoma aggressiveness. Histopathology 70(3): 473-484.
GUO H, XU X, ZHANG J, DU Y, YANG X, HE Z, ZHAO L, LIANG T & GUO L. 2024. The Pivotal Role of Preclinical Animal Models in Anti-Cancer Drug Discovery and Personalized Cancer Therapy Strategies. Pharmaceuticals (Basel) 17(8): 1048.
GUPTA R, SRIVASTAVA D, SAHU M, TIWARI S, AMBASTA RK & KUMAR P. 2021. Artificial intelligence to deep learning: machine intelligence approach for drug discovery. Mol Divers 25(3): 1315-1360.
HILLARY VE ET AL. 2024. The impact of generative artificial intelligence (AI) on the development of personalized pharmaceuticals and the future of precision medicine. EXCLI J 23: 1459-1462.
MARTINS-DE-BARROS AV, DA COSTA ARAÚJO FA, FARO TF, DE AQUINO AAT, BARBOSA NETO AG, DA SILVA HAM, DE LIMA ELS, MUNIZ MTC, DE OLIVEIRA E SILVA ED & DE VASCONCELOS CARVALHO M. 2024. BRAF p.V600E Mutational Status Does Not Correlate with Biological Behavior in Conventional Ameloblastomas: A Disease-Free Survival Analysis. Head Neck Pathol 18(1): 23.
PROIETTI I ET AL. 2020. Mechanisms of Acquired BRAF Inhibitor Resistance in Melanoma: A Systematic Review. Cancers (Basel). 29; 12(10): 2801. doi:10.3390/cancers12102801.
YANG S & KAR S. 2023. Application of artificial intelligence and machine learning in early detection of adverse drug reactions (ADRs) and drug-induced toxicity. Artif Intel Chem 1(2): 100011.
YANG Z, ZENG X, ZHAO Y & CHEN R. 2023. AlphaFold2 and its applications in the fields of biology and medicine. Signal Transduct Target Ther 8(1): 115.
ZHONG J, YAN W, WANG C, LIU W, LIN X, ZOU Z, SUN W & CHEN Y. 2022. BRAF Inhibitor Resistance in Melanoma: Mechanisms and Alternative Therapeutic Strategies. Curr Treat Options Oncol 23(11): 1503-1521.

Publication Dates

Publication in this collection
20 Oct 2025
Date of issue
2025

History

Received
22 Apr 2025
Accepted
4 July 2025

This is an open-access article distributed under the terms of the Creative Commons Attribution License

[1] ANBINSELVAM A, AKINSHIPO AO, ADISA AO, EFFIOM OA, ZHU X, ADEBIYI KE, AROTIBA GT & AKINTOYE SO. 2024. Comparison of diagnostic methods for detection of BRAFV600E mutation in ameloblastoma. J Oral Pathol Med 53(1): 79-87.

[2] CHEN D ET AL. 2023. Papillary thyroid cancer organoids harboring BRAFV600E mutation reveal potentially beneficial effects of BRAF inhibitor-based combination therapies. J Transl Med 21(1): 9.

[3] EBELING M, SCHEURER M, SAKKAS A, PIETZKA S, SCHRAMM A & WILDE F. 2023. BRAF inhibitors in BRAF V600E-mutated ameloblastoma: systematic review of rare cases in the literature. Med Oncol 40(6): 163.

[4] EFFIOM OA, OGUNDANA OM, AKINSHIPO AO & AKINTOYE SO. 2018. Ameloblastoma: current etiopathological concepts and management. Oral Dis 24(3): 307-316.

[5] FREGNANI ER, PEREZ DE, PAES DE ALMEIDA O, FONSECA FP, SOARES FA, CASTRO-JUNIOR G & ALVES FA. 2017. BRAF-V600E expression correlates with ameloblastoma aggressiveness. Histopathology 70(3): 473-484.

[6] GUO H, XU X, ZHANG J, DU Y, YANG X, HE Z, ZHAO L, LIANG T & GUO L. 2024. The Pivotal Role of Preclinical Animal Models in Anti-Cancer Drug Discovery and Personalized Cancer Therapy Strategies. Pharmaceuticals (Basel) 17(8): 1048.

[7] GUPTA R, SRIVASTAVA D, SAHU M, TIWARI S, AMBASTA RK & KUMAR P. 2021. Artificial intelligence to deep learning: machine intelligence approach for drug discovery. Mol Divers 25(3): 1315-1360.

[8] HILLARY VE ET AL. 2024. The impact of generative artificial intelligence (AI) on the development of personalized pharmaceuticals and the future of precision medicine. EXCLI J 23: 1459-1462.

[9] MARTINS-DE-BARROS AV, DA COSTA ARAÚJO FA, FARO TF, DE AQUINO AAT, BARBOSA NETO AG, DA SILVA HAM, DE LIMA ELS, MUNIZ MTC, DE OLIVEIRA E SILVA ED & DE VASCONCELOS CARVALHO M. 2024. BRAF p.V600E Mutational Status Does Not Correlate with Biological Behavior in Conventional Ameloblastomas: A Disease-Free Survival Analysis. Head Neck Pathol 18(1): 23.

[10] PROIETTI I ET AL. 2020. Mechanisms of Acquired BRAF Inhibitor Resistance in Melanoma: A Systematic Review. Cancers (Basel). 29; 12(10): 2801. doi:10.3390/cancers12102801.

[11] YANG S & KAR S. 2023. Application of artificial intelligence and machine learning in early detection of adverse drug reactions (ADRs) and drug-induced toxicity. Artif Intel Chem 1(2): 100011.

[12] YANG Z, ZENG X, ZHAO Y & CHEN R. 2023. AlphaFold2 and its applications in the fields of biology and medicine. Signal Transduct Target Ther 8(1): 115.

[13] ZHONG J, YAN W, WANG C, LIU W, LIN X, ZOU Z, SUN W & CHEN Y. 2022. BRAF Inhibitor Resistance in Melanoma: Mechanisms and Alternative Therapeutic Strategies. Curr Treat Options Oncol 23(11): 1503-1521.