A Nigerian scientist, Dr. Elijah Kolawole Oladipo, has led an international research team that used artificial intelligence  to identify promising animal-derived molecules that could pave the way for more targeted breast cancer treatments with fewer side effects.

The study, published in the Future Journal of Pharmaceutical Sciences, combined AI-powered drug discovery with advanced 3D protein modelling to identify therapeutic peptides capable of targeting breast cancer-driving proteins more effectively than an existing FDA-approved anticancer peptide in computer simulations.

Breast cancer remains one of the world’s deadliest diseases among women, accounting for about 36 per cent of female cancer diagnoses globally and millions of new cases every year. Conventional treatments such as chemotherapy, surgery and radiation often damage healthy cells alongside cancerous ones, while many tumours eventually become resistant to existing drugs.

To address the challenge, Oladipo, who is based at Adeleke University and the Helix Biogen Institute, led researchers from Nigeria, Ethiopia, the United Kingdom and the United States in designing potential cancer-fighting molecules using AI instead of relying solely on years of laboratory testing.

The international team included Omolara Omoboye Adegboye, Stephen Feranmi Adeyemo and Modinat Wuraola Akinboade of Helix Biogen Institute; Prof. Bamidele Abiodun Iwalokun of the Nigerian Institute of Medical Research; Dr. Olumide Faith Ajani of the Africa Centres for Disease Control and Prevention in Ethiopia; Dr. Olumuyiwa Elijah Ariyo of Afe Babalola University and Federal Teaching Hospital Ado-Ekiti; Prof. Helen Onyeaka of the University of Birmingham; and academic collaborators at Stony Brook University in New York.

Speaking on the significance of the research, Oladipo said the project demonstrated how AI could dramatically speed up the search for safer cancer therapies.

“We turned to artificial intelligence to design precise, nature-inspired therapeutics aimed at developing treatments that can target cancer cells while sparing healthy tissue,” he said.

Rather than manually testing thousands of compounds in laboratories, the researchers deployed machine-learning algorithms and Colab AlphaFold2, an advanced protein-structure prediction system, to screen a global database of more than 1,500 natural peptides.

The AI platform evaluated the compounds for structural stability, toxicity and allergenic potential before narrowing the search to three leading candidates derived from animal sources.

The shortlisted molecules were then tested through virtual simulations against two proteins that play critical roles in breast cancer progression—Matrix Metalloproteinase 1 (MMP1), which enables cancer to spread, and Epidermal Growth Factor Receptor (EGFR), which accelerates tumour growth.

According to the study, one AI-optimised peptide inspired by the green shield bug, Metalnikowin IIA, showed stronger binding affinity, greater precision and superior structural stability than Buserelin, an FDA-approved anticancer peptide used as the benchmark during the simulations.

The researchers, however, cautioned that the findings remain at the computational stage and have not yet been validated in laboratory or clinical studies.

“These findings are currently at the AI-predicted stage,” the researchers noted, stressing that further testing in living cells and animal models would be required before the compounds could advance towards human treatment.

To move the research beyond computer simulations, the team is seeking international research grants, pharmaceutical partnerships and global health collaborations to fund laboratory validation.

The researchers said such support would provide the crucial bridge between digital innovation and real-world clinical cancer care, potentially opening a new chapter in the development of more precise and less harmful breast cancer treatments.