Technology 3 min read

IBM Makes Its Cancer-Fighting AI Projects Open Source

IBM launches three new AI projects to help researchers and medical experts study cancer and find better treatment to the said disease in the future.

Image courtesy of Shutterstuck

Image courtesy of Shutterstuck

IBM has just released three of its cancer-fighting AI projects to the open-source community.

According to the National Cancer Institute, roughly 38.4 percent of men and women will be diagnosed with cancer at some point during their lifetimes. Whether it’s a genetic predisposition or environmental factors, the disease appears inevitable for some.

While several advancements have allowed us to treat many forms of cancer, there’s still much to learn.

That’s why the researchers from IBM’s Computational Systems Biology group in Zurich are working on an artificial intelligence and machine learning approach to the disease. Not only will this improve our understanding of the leading drivers of cancer, but we’ll also have a better knowledge of tumor composition.

In a press release, IBM wrote:

“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.”

The company’s three open-sourced AI projects are dubbed PaccMann, INtERAcT, and PIMKL. Later this month, IBM is expected to discuss how each of these projects can help further our understanding of cancers and their treatments.

But, here is what we know right now.

IBM’s Three Cancer-Fighting AI Projects.

1. PaccMann

No, it’s not the computer game, Pac-Man, from the 80s. Instead, PaccMann stands for “Prediction of anticancer compound sensitivity with Multi-modal attention-based neural networks.”

The PaccMann algorithm is designed to automatically analyze chemical compounds and predict which will most likely find cancer strains. Aside from streamlining the process of developing new drugs and therapies for the disease, it could potentially save millions of dollars.

Also, the machine learning algorithm depends on data on gene expression, including the molecular structures of chemical compounds.

2. INtERAcT

The second AI project, INtERAcT, is an acronym for “Interaction Network infErence from vectoR representATions of words,” and It’s designed to extract cancer-related data from scientific publications.

Cancer researchers publish as much as 17,000 papers every year. As you can imagine, keeping up with this body of knowledge is difficult – if not impossible. That’s where INtERAcT comes in.

Its goal is to reduce the burden of academic research on cancer by automatically extracting information from these papers.

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.”

3. PIMKL

The third AI project is the “pathway-induced multiple kernel learning,” or PIMKL. Thanks to molecular interactions dataset, the algorithm can predict the progression of cancer and the probability of relapses.

PIMKL uses multiple kernel learning to identify molecular pathways, which is necessary for placing patients in categories. That way, health professionals can administer individualized and tailored treatment plans.

IBM has released PaccMann and INtERAcT’s code on the project’s websites. Meanwhile, the tech giant has also deployed PIMKL on its cloud, including the source code too.

Read More: IBM Unveils the World’s First Commercial Quantum Computer

Found this article interesting?

Let Sumbo Bello know how much you appreciate this article by clicking the heart icon and by sharing this article on social media.


Profile Image

Sumbo Bello

Sumbo Bello is a creative writer who enjoys creating data-driven content for news sites. In his spare time, he plays basketball and listens to Coldplay.

Comments (0)
Most Recent most recent
You
share Scroll to top

Link Copied Successfully

Sign in

Sign in to access your personalized homepage, follow authors and topics you love, and clap for stories that matter to you.

Sign in with Google Sign in with Facebook

By using our site you agree to our privacy policy.