Alexander Karollus (@AlexKarollus) profile picture
Joined September 2022
Photo by Alexander Karollus (@AlexKarollus)Photo by Alexander Karollus (@AlexKarollus)Photo by Alexander Karollus (@AlexKarollus)Photo by Alexander Karollus (@AlexKarollus)Photo by Alexander Karollus (@AlexKarollus)Photo by Alexander Karollus (@AlexKarollus)Photo by Alexander Karollus (@AlexKarollus)Photo by Alexander Karollus (@AlexKarollus)Photo by Alexander Karollus (@AlexKarollus)Photo by Alexander Karollus (@AlexKarollus)
Alexander Karollus retweeted
Extra non-commercial API quota request: forms.gle/ftBfHGH7NUrCZEjN6 Commercial API is rolling out on Google Cloud, currently in private preview. Model weights & AG2 Skills in Antigravity will be released in the future. Huge thanks to the @GoogleDeepMind team, early testers & data consortia!
4
18
1,283
Alexander Karollus retweeted
Most genetic variants linked to human disease sit outside genes and act only in specific cell states. Today we are sharing AlphaGenome 2 to help connect those variants to the cells and genes driving disease. Preprint: storage.googleapis.com/deepm… Blog: deepmind.google/blog/alphage…
3
14
91
4,331
Alexander Karollus retweeted
Single-cell atlases continue to map the diversity of cell states, but how can we use them to interpret non-coding genetic variants? Excited to share AlphaGenome 2, our model for predicting cell-type-specific regulatory activity and variant effects from DNA sequence. deepmind.google/blog/alphage…
12
83
7
290
39,287
Alexander Karollus retweeted
AlphaGenome is out in @nature today along with model weights! 🧬 📄 Paper: nature.com/articles/s41586-0… 💻 Weights: github.com/google-deepmind/a… Getting here wasn’t a straight path. We sat down @googledeepmind to discuss the story behind the model, paper & API: youtu.be/V8lhUqKqzUc
29
475
29
1,855
227,609
Alexander Karollus retweeted
I'm excited that our paper, "scooby: modeling multimodal genomic profiles from DNA sequence at single-cell resolution," has been published in Nature Methods! scooby is a new deep-learning framework to understand how DNA sequence shapes gene expression in individual, single cells.
1
1
3
208
Alexander Karollus retweeted
Happy to share that Flashzoi is now published! We enhanced Borzoi with RoPE & FlashAttention for >3x faster training/inference & 2.4x reduction in memory usage. This brings large-scale genomic analysis and fine-tuning within reach of academic budgets. 📄: doi.org/10.1093/bioinformati…
1
1
1
4
266
Alexander Karollus retweeted
Excited to share #AlphaGenome, a start of our AlphaGenome named journey to decipher the regulatory genome! The model matches or exceeds top-performing external models on 24 out of 26 variant evaluations, across a wide range of biological modalities.1/6
14
206
17
900
87,733
Alexander Karollus retweeted
Introducing Flashzoi⚡! We’ve upgraded the Borzoi model with rotary pos. encodings and FlashAttention, resulting in a 3x speedup with similar or better accuracy for faster variant effect prediction or model development, and more efficient genomic analysis biorxiv.org/content/10.1101/…
1
5
1
12
3,267
Alexander Karollus retweeted
Excited to share our preprint: Efficient Inference, Training, and Fine-tuning of Protein Language Models! ⚡We introduce advanced techniques to make large protein models accessible to more researchers. Read it here: doi.org/10.1101/2024.10.22.6…
1
3
12
2,364
Alexander Karollus retweeted
Information leakage due to homology: A pervasive and non-trivial issue in bioinformatics. Excited to hear about @muntakim_rafi's insights and recommendations for sequence-based modeling on Wednesday at the Kipoi seminar.
Join us for the next Kipoi Seminar with with Abdul Muntakim Rafi (Rafi) @muntakim_rafi @CarldeBoerPhD @UBC! 👉Detecting and avoiding homology-based data leakage in genome-trained sequence models 📅Wed Nov 6, 5:30pm CET 🧬tum-conf.zoom.us/meeting/reg…
5
12
2,093
Excited to present “scooby”, which models multi-omic profiles (scRNA-seq coverage & scATAC-seq insertions) directly from 500 kb DNA sequence at single-cell resolution. This was a fantastic collaboration co-led with @thisisjohahi. biorxiv.org/content/10.1101/…
4
51
3
220
31,207
Have you ever wondered what the genome looks like through the eyes of a DNA language model? In our newest preprint we use DNA LMs to study nucleotide dependencies in the genome, revealing functional elements, characterizing variants and evaluating DNA LMs tinyurl.com/6wbwjaf4
6
45
6
197
27,997
Alexander Karollus retweeted
Hope you are ready for our kick-off meeting #MunichRNA21F! Come and hear the great research by @shu_bhayankar from @ProtzerLab and @AlexKarollus from @gagneurlab . See you very soon! 📅21F 3pm 📍@HelmholtzMunich
7
1
19
2,316
Cracking the regulatory code: We have genomes for 1000s of species, but ENCODE only for 2 – what do we do? Natural language models have shown that syntax and semantics can be learned from text alone. Can we do the same for genomes?⬇️ biorxiv.org/content/10.1101/…
3
31
2
116
20,906
Finally, our models have learned representations that can boost supervised learning. In fact, we outperform SOTA on gene expression and mRNA half-life tasks using simple regression on the last layers embeddings.
1
4
770
In all these tasks, providing the model with species information was crucial. We expect that species-aware DNA language models leveraging massive sequencing projects will prove a powerful tool to investigate understudied species.
7
511