According to reports, IBM has recently released three artificial intelligence (AI) projects tailored to take up the challenge of curing cancer to the open-source community.
At the 18th European Conference on Computational Biology (ECCB) and the 27th Conference on Intelligent Systems for Molecular Biology (ISMB), which will be held in Switzerland later this month, the tech giant will dive into how each of the projects can broaden our knowledge of cancers and their treatments.
Reportedly, cancer alone is estimated to have caused 9.6 million deaths in 2018, with an estimated 18 million new cases reported in the same year. Predisposition through genetic science, environmental factors which include pollution, smoking, and diet are all considered key factors in how likely someone is to inherit such a disease, and while we can treat many forms, we still have much to know.
Researchers from IBM’s Computational Systems Biology group in Zurich are gearing up on AI and machine learning (ML) approaches to help accelerate our knowledge of the leading drivers and molecular mechanisms of these complex diseases, as well as methods to improve our understanding of tumor composition.
“Our goal is to deepen our understanding of cancer to equip industries and academia with the information that potentially one day facilitate fuel new treatments and therapies,” IBM says.
The first project, dubbed PaccMann, not to be confused with the popular Pac-Man computer game, is termed as the “Prediction of anticancer compound sensitivity with Multi-modal attention-based neural networks.”
The second project is called “Interaction Network influence from vector representations of words,” otherwise known as INtERAcT. This tool is particularly fascinating, one given its automatic extraction of data from valuable scientific papers related to our understanding of cancer.
The third and final project is “pathway-induced multiple kernel learning,” or PIMKL. This algorithm utilizes datasets describing what we currently know when it comes to molecular interactions to predict the progression of cancer and potential relapses in patients.
Each project is open-source and has currently been created available in the public domain. IBM hopes that by creating the source code available to different researchers and academics, their potential impact can be maximized by the scientific community.