Breakthroughs in Machine Learning and AI are leading to major changes in the way we analyze biological data. Conferences are our chance check in with scientists from around the world to get a sense of what they are thinking. Be sure to catch up with Cameron at “AI in Biology” …
We continued our spring tradition of escaping the office for some fresh air and fresh thinking. We were lucky to find the park in wild spring form. As usual we made time for discussions about where we are on our scientific voyage. Here you can even see Alan making a …
Wow. Iva’s paper is finally published. There is only one human proteome, and there are many disordered protein regions in there. For the first time systematic predictions of their biological functions are now available. Of course, this is only the *first* attempt to systematically map the function of the human …
It’s always bittersweet to say good-bye to valued members of our group. Yesterday at lunch, we looked back for a moment to celebrate their accomplishments over the past semester and before. Each made lasting impact on our group by pushing us forward in different ways: Denise trained our first protein …
Ami’s paper is now published! A protein language model has learned that proteins are made of functional units, often known as protein domains or regions. 10,000s of protein domains have been identified over the years by some of our favourite bioinformatics teams (e.g., pfam). But Ami shows that by looking …
Incredibly creative work by our lab this year. After the ballots are all counted, our pumpkin won 1st place! You can see that the pumpkin has been turned into a pineapple, and then into a house. Thanks to everyone who worked on it. It has been an incredible run for …
Taking a walk outside for is a great source of inspiration. This year, the Moses Lab took that walk at Ontario’s Matterhorn – Dundas Peak. There was a very high waterfall, and the locals were a bit skeptical of visitors. The temperatures might’ve been low, but the spirits were high …
In the past few years, a new organization has formed to focus on machine learning for non-globular proteins: ML4NGP. Be sure to catch up with Alan at this year’s conference!
Genome sequences specify 1000s of the components of cells and organisms, usually using millions or billions of A,C,G and Ts. As computational biologists, ideally, we would use the entire genome sequence to make predictions about phenotype. Leveraging recent IT breakthroughs (thanks NVIDIA), Cameron figured out a way train deep learning …
The origin of life is one of the great mysteries of science. Of course, no one was there to observe it and there are many reasons that it’s tricky to figure out how you could get a living thing from non-living material. Inspired by recent research in biological condensates, Alan …
