Cancer is estimated to have caused 9.6 million deaths in 2018 alone. Around one in two will develop cancer in their lifetimes, and few will not know someone impacted by its blight.

Fortunately, advancements are making the discovery and treatment of cancer faster and more effective. IBM has been working on three AI-powered projects to help tackle this global challenge.

“Our goal is to deepen our understanding of cancer to equip industries and academia with the knowledge that could potentially one day help fuel new treatments and therapies,” IBM says.

The first project, PaccMann, aims to use deep learning for helping to predict the efficiency of cancer-fighting drugs. Hundreds of millions of dollars can be spent on getting approval for a single drug so identifying compounds likely to be most effective is paramount.

The second tool, INtERAcT (Interaction Network infErence from vectoR representATions of words), is a tool for automating the extraction of knowledge from scientific publications. It’s a tool anyone who spends time dissecting papers will understand, but few have such importance as seeking the information to help treat cancer.

“A particular strength of INtERAcT is its capability to infer interactions in the context of a specific disease,” IBM says. “The comparison with the normal interactions in healthy tissue may potentially help to obtain insight into the disease mechanisms.”

Last but not least is PIMKL, aiming to help predict the progression of a disease. Such a prediction helps clinicians to better personalise and design effective cancer treatments.

A web version of PaccMann is available here, or an open-source version here. The web version of INtERAct is here, or the open-source version here. Finally, the web version of PIMKL can be found here, or the open-source repo here.

deepgeniusai.com/">AI & Big Data Expo events with upcoming shows in Silicon Valley, London, and Amsterdam to learn more. Co-located with the IoT Tech Expo, , & .

The post IBM open-sources three AI projects dedicated to curing cancer appeared first on AI News.