In silico generation of synthetic cancer genomes using generative AI
TL;DR
Imagine you have a big puzzle, but you can't see all the pieces because they're hidden for privacy reasons. This makes it hard to solve the puzzle. Scientists have found a way to create new puzzle pieces that look just like the hidden ones, so they can share them with others to help solve the puzzle faster. This means they can understand cancer better and find new ways to treat it.
Understanding how genomic alterations drive cancer is key to advancing precision oncology. To detect these alterations, accurate algorithms are used; however, due to privacy concerns, few deeply sequenced cancer genomes can be shared, limiting benchmarking and representing a major obstacle to the improvement of analytic tools. To address this, we developed OncoGAN, a generative AI model combining adversarial networks and variational autoencoders to create realistic synthetic cancer genomes. Trained on large-scale genomic datasets, OncoGAN accurately reproduces somatic mutations, copy number alterations, and structural variants across cancer types while preserving donors' privacy. The synthetic genomes reflect tumor-specific mutational signatures and positional mutation patterns. Using DeepTumour, we validated the synthetic data's fidelity, showing high concordance between generated and predicted tumors. Moreover, augmenting the training data with synthetic genomes improved DeepTumour's accuracy, underscoring OncoGAN's potential to generate shareable datasets with known ground truths for benchmarking and enhancement of cancer genome analysis tools.
- 1OncoGAN is a multimodel ensemble pipeline combining GANs, TVAEs, and random sampling that generates realistic synthetic cancer genomes for eight distinct tumor types, accurately reproducing somatic mutations, copy number alterations, and structural variants.
- 2Synthetic genomes produced by OncoGAN faithfully replicate tumor-specific mutational signatures, genomic positional mutation patterns, and driver mutation frequencies and intercorrelations observed in real PCAWG data.
- 3On average, only 0.021% of simulated mutations exactly match those in the training set, demonstrating effective donor privacy protection, making the synthetic genomes fully open access.
- 4DeepTumour achieved nearly 100% tumor-type prediction accuracy on OncoGAN-generated synthetic donors, validating the biological fidelity of the simulated genomes.
- 5Augmenting DeepTumour training data with 100 OncoGAN-simulated donors per tumor type improved overall classification accuracy from 89.26% to 90.16%, with the largest gains for underrepresented tumor types such as Lymph-MCLL (F1 score: 75% to 84%).
M87's black hole flipped its magnetic field
Imagine a bar magnet with a north and south pole. Now imagine that magnet suddenly flipping so north becomes south and vice versa. That's essentially what happened with the magnetic field around the giant black hole at the center of galaxy M87 — except this black hole is 6.5 billion times heavier than our Sun. Scientists noticed this flip by watching the powerful beam of energy, called a jet, that shoots out from the black hole. The direction and behavior of that beam changed in a way that revealed the magnetic field had reversed. It's a big deal because those magnetic fields are thought to act like the engine that powers and steers these cosmic jets, and we've rarely caught one flipping in action.
The 2026 World Cup's grass is an engineering problem
Imagine you're trying to play soccer in 16 different places across the United States, Canada, and Mexico — some in freezing cold, some blazing hot, some in stadiums with roofs that block sunlight. Half of those stadiums normally use fake grass. Now FIFA, the organization that runs the World Cup, wants every single pitch to feel and play exactly the same way, like a video game where every level has identical physics. To do that, they hired grass scientists — yes, that's a real job — who figured out how to grow special grass on thin mats with plastic underneath so it can be transported like a carpet, stitched with synthetic fibers so it doesn't rip when players sprint and tackle, and tested by literally shooting balls at it with a cannon to make sure it bounces right. Different grass species are used depending on whether a stadium is hot, cool, or dark. It's basically a giant, living, high-tech floor installation that has to survive the world's best athletes running on it.
Non-Mendelian inheritance of DNA methylation patterns in mice
Imagine your DNA is like a huge book of instructions. Mendel's laws are the normal rules for how chapters of that book get passed from parents to children. But there's also a layer of sticky notes on top of the book—called epigenetic marks—that tell cells which chapters to read and which to ignore. This study found that most of the time (about 93%), these sticky notes follow the normal inheritance rules. But about 7% of the time, they do something unexpected: new patterns appear that neither parent had, or a mark from one parent somehow silences the same mark from the other parent (called paramutation), or males and females end up with completely different sticky notes even when they inherit the same DNA. Scientists discovered this by using a new ultra-precise DNA reading technology in mice, and it opens the door to understanding hidden layers of how traits—and possibly diseases—are passed down through generations.
Digital twin–guided ablation for ventricular tachycardia
Imagine your heart is a city, and ventricular tachycardia is like a traffic jam caused by a broken road — electrical signals get stuck going in circles instead of flowing properly, causing the heart to beat dangerously fast. Doctors can fix this by burning away the broken road using a procedure called ablation. The problem is, finding the exact broken road inside a beating heart is like navigating a city you've never visited before, while driving, in the dark. What these researchers did is take detailed MRI pictures of each patient's heart, build a 3D computer copy — a 'digital twin' — and then simulate where the electrical problem was happening inside that virtual heart. They tested their fix on the computer model first, figured out exactly where to go, and THEN performed the real procedure. What used to take three hours of exploratory surgery was done in about 30 minutes, because the doctors already had a GPS map before they started.