
Dr. Ana Nikolic
2.7K posts

Dr. Ana Nikolic
@anniekey
MD/PhD. Assistant professor, U of Calgary DPLM. Neuropathologist. PI. 🧠❤️, brain tumor research nerd and part-time bioinformagician. she/her



We are releasing Carbon: a crazy fast DNA model Carbon is 275x faster than the next best model. So fast you can process the whole human genome on a single GPU in <2 days. Here are the tricks we used: When modelling DNA sequences a lot of the performance comes down to tokenizing the sequences in a smart way. BPE tokenizer struggle because there are no whitespaces and character (called base in DNA) level tokenizers waste a lot of compute on too many tokens. Carbon is built with a unique tokenizer: we split sequences in chunks of 6 bases, but during both training and inference we can work with single base resolution. That's similar to having word tokens but resolving them at the character level. All possible thanks to the DNA tokens unique structure. The architecture combined with the tokenizer makes the model 275x faster than the previous SoTA (Evo2) at this size. We built an interactive demo so you can explore how the model can generate DNA sequences, investigate the structure of genes, predict the effect of mutations, generate and fold proteins and even reconstruct parts of the tree of life. huggingface.co/spaces/Hugging…

"Writing is thinking." This phrase went viral recently (from lnkd.in/gYj2c9uE), often quoted in the context of objections to use of AI in drafting academic prose. In Nature Reviews Bioengineering we respond: "Thinking is not only writing." Preview below. Shareable full access link: rdcu.be/fiuYi












It is so painful to share the news of @FralickMike sudden and unexpected passing 💔 Mike was an amazing, inspiring and generous person who touched the lives of many. As we mourn, please share and consider supporting his wife and 2-year-old daughter. gofund.me/236771146

Online now: Runx1 transcription factor modulates opioid analgesia and withdrawal in humans and rodents dlvr.it/TQg0V2





Very excited to share our study on the benchmarking of methods to detect spatially variable genes (SVGs) and peaks (SVPs), a collaborative work with @zafateniac, @SongDongyuan, @GuanaoYan, @jsb_ucla, and @lucapinello. 🧵 (1/n)

ABSTRACT DEADLINE IN 2 DAYS! Reminder that the deadline for early-bird registration, abstract submission for talk consideration, and travel award applications is this FRIDAY, SEPTEMBER 19! event.fourwaves.com/ceehrc2025 1/2



