International genomics research has used artificial intelligence (AI) to study an aggressive form of cancer, which could improve patient outcomes.

Mesothelioma is caused by breathing asbestos particles and most commonly occurs in the linings of the lungs or abdomen. Currently, only seven per cent of people survive five years after diagnosis, with a prognosis averaging 12 to 18 months.

Malignant Pleural Mesothelioma (MPM) is typically diagnosed 20–50 years after exposure to asbestos and evolves along an unknown evolutionary trajectory. To elucidate this path, the authors conducted multi-regional exome sequencing of 90 tumour samples from 22 MPMs acquired at surgery.

New research undertaken has now revealed, using AI analysis of DNA-sequenced mesotheliomas, that they evolve along similar or repeated paths between individuals. These paths predict the aggressiveness and possible therapy of this otherwise incurable cancer.

The authors also show that exomic intratumour heterogeneity varies widely across the cohort. Phylogenetic tree topology ranges from linear to highly branched, reflecting a steep gradient of genomic instability. Using transfer learning, they detect repeated evolution, resolving 5 clusters that are prognostic, with temporally ordered clonal drivers. 

BAP1/−3p21 and FBXW7/-chr4 events are always early clonal. In contrast, NF2/−22q events, leading to Hippo pathway inactivation are predominantly late clonal, positively selected, and when subclonal, exhibit parallel evolution indicating an evolutionary constraint. Very late somatic alteration of NF2/22q occurred in one patient 12 years after surgery. Clonal architecture and evolutionary clusters dictate MPM inflammation and immune evasion. These results reveal potentially drugable evolutionary bottlenecking in MPM, and an impact of clonal architecture on shaping the immune landscape, with potential to dictate the clinical response to immune checkpoint inhibition.

The senior author said: "It has long been appreciated that asbestos causes mesothelioma, however how this occurs remains a mystery.

"Using AI to interrogate genomic 'big data', this initial work shows us that mesotheliomas follow ordered paths of mutations during development, and that these so-called trajectories predict not only how long a patient may survive, but also how to better treat the cancer."

While use of asbestos is now outlawed - and stringent regulations in place on its removal - each year around 25 people are diagnosed with mesothelioma in Leicestershire and 190 are diagnosed in the East Midlands. Cases of mesothelioma in the UK have increased by 61% since the early 1990s.

Until very recently, chemotherapy was the only licenced choice for patients with mesothelioma. However, treatment options start to become limited once people stop responding to their treatment.

The authors made a major breakthrough in treating the disease by demonstrating that use of an immunotherapy drug called nivolumab increased survival and stabilised the disease for patients. This was the first-ever trial to demonstrate improved survival in patients with relapsed mesothelioma.

https://le.ac.uk/news/2021/march/mesothelioma

https://www.nature.com/articles/s41467-021-21798-w

http://sciencemission.com/site/index.php?page=news&type=view&id=publications%2Fclonal-architecture-in&filter=22