PhD, Illumina AI lab; interested in Deep Learning and genome regulation; also drawing, martial arts, guitar, and death metal! (he/him)
Joined January 2018
- Tweets 774
- Following 400
- Followers 274
- Likes 3,787
23 Photos and videos
Pinned Tweet
Excited to share my first contribution here at Illumina! We developed PromoterAI, a deep neural network that accurately identifies non-coding promoter variants that disrupt gene expression.🧵 (1/)
2
30
110
33,594
Gherman Novakovsky (слава Україні! 🇺🇦) retweeted
New study using PromoterAI to show that disruption of key transcription factor motifs reduces gene expression and further strengthens experimental results (Figure 7).
biorxiv.org/content/10.64898…
1
5
759
Gherman Novakovsky (слава Україні! 🇺🇦) retweeted
May 30
Just want to give a shout-out to David Kelley @drklly who I think often does not get the credit he deserves (outside our core community).
I want to highlight why I think he is such a fantastic scientist and leader in regulatory genomics. 1/
7
32
263
46,646
RT @anshulkundaje: This administration entire policy is to torture hard working people who actually contribute to the nation. This will lea…
17
Gherman Novakovsky (слава Україні! 🇺🇦) retweeted
Rare disease diagnoses can rely on exome sequencing, but answers may be hiding in noncoding regions. 🧬 PromoterAI is a new deep learning tool that identifies pathogenic promoter variants, which may account for up to 6% of rare disease genetic burden 🔍
science.org/doi/10.1126/scie…
2
24
80
8,114
Gherman Novakovsky (слава Україні! 🇺🇦) retweeted
In a saturation MPRA of the MAPT promoter, PromoterAI tracked measured variant effects, supporting its use for prioritizing pathogenic promoter variants.
biorxiv.org/content/10.64898…
1
2
3
478
Gherman Novakovsky (слава Україні! 🇺🇦) retweeted
When linear models and deep learning give the same results, orders of magnitude more training data are needed nature.com/articles/s41592-0… ;
3
18
78
15,521
Gherman Novakovsky (слава Україні! 🇺🇦) retweeted
May 12
Excited to share our RegVelo paper in Cell
cell.com/cell/fulltext/S0092…
We unify RNA velocity GRNs into one model → better OOD prediction of perturbations (e.g. gene KOs), with examples incl. neural crest KO predictions 🔬
Big thanks to W Wang, Z Hu & T Sauka-Spengler 🙏
7
107
453
36,433
Gherman Novakovsky (слава Україні! 🇺🇦) retweeted
Exciting new insights on CpG islands (CGIs) regulation by transcription factors (TFs)! CGIs drive most transcription initiation with unclear regulation. We find that chromatin-opening TFs are key players—following a surprisingly simple rule.
biorxiv.org/content/10.64898…
1/9
3
53
189
15,233
Gherman Novakovsky (слава Україні! 🇺🇦) retweeted
1/ PromoterAI scores are now viewable as a track in @GenomeBrowser. Below is a ClinVar example that clearly highlights the value:
2
8
31
5,265
Gherman Novakovsky (слава Україні! 🇺🇦) retweeted
Our Human Multiomic Development Atlas paper is out in Nature today! A heart-felt "thank you" to all co-authors for their tireless work on this complex yet exciting project! Congrats all! nature.com/articles/s41586-0…
6
98
356
22,566
Gherman Novakovsky (слава Україні! 🇺🇦) retweeted
It’s well known that inflammation increases cancer risk, but how?
The answer: the epigenome "remembers" inflammation and primes stem cells for cancer.
Here is our paper: nature.com/articles/s41586-0…
And a special shoutout to the lead author @snaga13
A 🧵
15
130
568
42,624
Gherman Novakovsky (слава Україні! 🇺🇦) retweeted
Mar 20
We are also releasing self-contained lecture notes that explain flow matching and diffusion models from scratch. This goes from "zero" to the state-of-the-art in modern Generative AI.
📖 Read the notes here: arxiv.org/abs/2506.02070
Joint work with @EErives40101.
Mar 18
🚀MIT Flow Matching and Diffusion Lecture 2026 Released (diffusion.csail.mit.edu/)!
We just released our new MIT 2026 course on flow matching and diffusion models! We teach the full stack of modern AI image, video, protein generators - theory and practice. We include:
📺 Videos: Step-by-step derivations.
📝 Notes: Mathematically self-contained lecture notes
💻 Coding: Hands-on exercises for every component
We fully improved last years’ iteration and added new topics: latent spaces, diffusion transformers, building language models with discrete diffusion models.
Everything is available here: diffusion.csail.mit.edu/
A huge thanks to Tommi Jaakkola for his support in making this class possible and Ashay Athalye (MIT SOUL) for the incredible production! Was fun to do this with @RShprints!
#MachineLearning #GenerativeAI #MIT #DiffusionModels #AI
38
645
5,541
474,280
Gherman Novakovsky (слава Україні! 🇺🇦) retweeted
Mar 18
Models are typically specialized to new domains by finetuning on small, high-quality datasets.
We find that repeating the same dataset 10–50× starting from pretraining leads to substantially better downstream performance, in some cases outperforming larger models. 🧵
19
80
617
94,616
Gherman Novakovsky (слава Україні! 🇺🇦) retweeted
Mar 18
Great to the see the flurry of single gene knockdown Perturb-seq like atlases from cell-lines, mouse brain etc over the last few days. These are undoubtedly very valuable datasets. I just want to re-iterate a few other very important expt. design considerations 1/
2
66
278
28,435
Gherman Novakovsky (слава Україні! 🇺🇦) retweeted
Gaps *this* wide have been shown before, in Figure 2D, for splice variant effect prediction (SpliceAI is 700K parameters). The x-axis ranges from 0 to 1 here so it may not be immediately apparent, but its the same 0.6 to 0.9 gap.
1
5
19
2,524
Nature research paper: Functional dissection of complex trait variants at single-nucleotide resolution
go.nature.com/4ck0zkd
40
153
18,818
Gherman Novakovsky (слава Україні! 🇺🇦) retweeted
Feb 21
Can we simulate realistic evolutionary trajectories and “replay the tape of life”? In this work, we propose a flexible, generalizable framework for modeling how the entire protein seq evolves over time while capturing complex interactions across sites. 1/n
doi.org/10.64898/2026.02.19.…
5
82
289
34,068
Nature research paper: Regulatory grammar in human promoters uncovered by MPRA-based deep learning
go.nature.com/3NUvNEh
1
28
131
17,805
Gherman Novakovsky (слава Україні! 🇺🇦) retweeted
Jan 28
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
477
1,863
225,763
Gherman Novakovsky (слава Україні! 🇺🇦) retweeted
Jan 15
Molecular Genetics @ University of Toronto 🇨🇦@UofT🦠 is recruiting an Assistant Professor in #Virology!!
Come build your dream lab!
🔗jobs.utoronto.ca/job/Toronto…
1
19
42
4,307