Designing Algorithms to Fight Cancer

---

By studying cancer mutation datasets to understand the history of mutational processes shaping the cancer genome. Many successful cancer therapies work by causing DNA damage or inhibiting DNA damage repair, which cancer cells are less able to survive than healthy cells. Thus, identifying molecular markers for mutational processes such as DNA repair deficiencies is a priority. Large cancer sequencing projects have recently revealed dozens of signatures of mutational processes, each consisting of a different pattern of base substitutions. A major unmet challenge lies in characterizing the signatures with unknown causes. This is a difficult computational problem because dozens of factors affect the mutational process activity in a given cell, and combinations of factors sometimes leave similar signatures. Our approach to this challenge is to use probabilistic models of mutation signatures and their properties or covariates in order to distinguish similar signatures, discover rare signatures, and infer their underlying causes. One such property we are studying is sequential dependency along the genome, as some mutational processes cause mutations in localized clusters.

Cancer is the name given to a collection of related diseases. In all types of cancer, some of the body’s cells begin to divide without stopping and spread into surrounding tissues.













Max Leiserson, an assistant professor of computer science with an appointment in UMIACS, uses computational biology in the fight against cancer. His research focuses on cancer genomics, cancer immunotherapy and network biology.








The Ontario Institute for Cancer Research (OICR) discovered that the mutation, termed the U1-snRNA mutation, could disrupt normal RNA splicing and thereby alter the transcription of cancer-driving genes.

These molecular mechanisms represent new ways to treat cancers carrying the mutation. One of the potential treatment approaches includes repurposing existing drugs, which, by bypassing early drug development stages, could be brought into the clinic at an accelerated rate.

1 of 4 :: What is cancer

---

2 OF 4 :: Designing algorithms to fight cancer

---

3 OF 4 :: NEW CANCER-DRIVING MUTATION  DISCOVERED

For 150 years, pathologists have been looking through microscopes at tissue samples mounted on slides to diagnose cancer. Each assessment is weighty: Does this patient have cancer or not?

The job of a pathologist is daunting. A single slide could contain hundreds of thousands of cells. Only a handful might be cancer. Inaccurate diagnosis rates range from 3-9% of cases, according to a recent review.

4 OF 4 :: AI & Cancer research

---

Enter artificial intelligence (AI), an extra set of unbiased, indefatigable artificial eyes that could help catch errors. Many researchers are pursuing this possibility, but Novartis pathologists think AI might have an additional role to play. They hypothesize that pathology slides could contain information that helps explain why some patients respond to therapy when other seemingly similar patients do not.