Laboratory of AI Genome Informatics
LightNews LightNews
banner
kazusaaigeni.bsky.social
Laboratory of AI Genome Informatics
@kazusaaigeni.bsky.social
8 followers 11 following 6 posts
Kazusa DNA Research Institute
2-6-7 Kazusa-kamatari, Kisarazu, Chiba 292-0818, Japan
https://www.kazusa.or.jp/en-laboratories/en-advanced-department/en-ai-genome-lab/
Posts Replies Media Videos
Pinned
kazusaaigeni.bsky.social
Laboratory of AI Genome Informatics @kazusaaigeni.bsky.social · Oct 1
The Laboratory of AI Genome Informatics (AI GENi) upholds the vision of “unveiling the mysteries of life through the power of AI.” In particular, by applying AI technologies, we aim to decipher the “biological language” encoded in genomes, contributing to next-generation life science and healthcare.
kazusaaigeni.bsky.social
Got my hands on the NVIDIA H200 NVL 141GB water-cooled model!
November 13, 2025 at 4:09 AM
kazusaaigeni.bsky.social
Machine Learning‐Based Predictive Modeling Maximizes the Efficacy of mTOR/p53 Co‐Targeting Therapy Against AML - Li - 2025 - Cancer Science - Wiley Online Library onlinelibrary.wiley.com/doi/10.1111/...
Machine Learning‐Based Predictive Modeling Maximizes the Efficacy of mTOR/p53 Co‐Targeting Therapy Against AML
Although mTOR inhibitors show limited clinical efficacy against AML, this study demonstrates that combining mTOR inhibition with TP53 activation enhances anti-leukemic effects. We also developed a ge...
onlinelibrary.wiley.com
November 4, 2025 at 12:37 AM
kazusaaigeni.bsky.social
Bioinformatics Research Scientist Recruitment at Kazusa DNA Research Institute
jrecin.jst.go.jp/seek/SeekJor...
JREC-IN | Bioinformatics Research Scientist Recruitment at Kazusa DNA Research Institute
イノベーション創出を担う研究人材のためのキャリア支援ポータルサイト
jrecin.jst.go.jp
October 21, 2025 at 12:39 AM
kazusaaigeni.bsky.social
Recruitment for Bioinformatics Researcher at the Kazusa DNA Research Institute
jrecin.jst.go.jp/seek/SeekJor...
JREC-IN | 公益財団法人 かずさＤＮＡ研究所 バイオインフォマティクス研究員
イノベーション創出を担う研究人材のためのキャリア支援ポータルサイト
jrecin.jst.go.jp
October 21, 2025 at 12:38 AM
kazusaaigeni.bsky.social
Recruitment for IT Technical Staff at the Kazusa DNA Research Institute
jrecin.jst.go.jp/seek/SeekJor...
JREC-IN | 公益財団法人 かずさDNA研究所　IT技術員・特任技術員
イノベーション創出を担う研究人材のためのキャリア支援ポータルサイト
jrecin.jst.go.jp
October 21, 2025 at 12:31 AM
Reposted by Laboratory of AI Genome Informatics
nicweyand.com
On Google’s website: “AI got better understanding the genome”

In the actual paper: “It’s deep learning”

www.biorxiv.org/content/10.1...
Google DeepMind: AlphaGenome: AI for better understanding the genome. 25 June 2025. Today, we introduce AlphaGenome, a new artificial intelligence (Al) tool that more comprehensively and accurately predicts how single variants or mutations in human DNA sequences impact a wide range of biological processes regulating genes. This was enabled, among other factors, by technical advances allowing the model to process long DNA sequences and output high-resolution predictions. To advance scientific research, we're making AlphaGenome available in preview via our AlphaGenome API for non-commercial research, and planning to release the model in the future. We believe AlphaGenome can be a valuable resource for the scientific community, helping scientists better understand genome function, disease biology, and ultimately, drive new biological discoveries and the development of new treatments. Abstract Deep learning models that predict functional genomic measurements from DNA sequence are powerful tools for deciphering the genetic regulatory code. Existing methods trade off between input sequence length and prediction resolution, thereby limiting their modality scope and performance. We present AlphaGenome, which takes as input 1 megabase of DNA sequence and predicts thousands of functional genomic tracks up to single base pair resolution across diverse modalities - including gene expression, transcription initiation, chromatin accessibility, histone modifications, transcription factor binding, chro- matin contact maps, splice site usage, and splice junction coordinates and strength. Trained on human and mouse genomes, AlphaGenome matches or exceeds the strongest respective available external models on 24 out of 26 evaluations on variant effect prediction. AlphaGenome's ability to simultaneously score variant effects across all modalities accurately recapitulates the mechanisms of clinically-relevant variants near the TAL 1 oncogene. To facilitate broader use, we provide tools for making genome track and variant effect predictions from sequence. Competing Interest Statement This work was done in the course of employment at Google DeepMind, with no other competing financial
July 29, 2025 at 10:07 PM
kazusaaigeni.bsky.social
The Laboratory of AI Genome Informatics (AI GENi) upholds the vision of “unveiling the mysteries of life through the power of AI.” In particular, by applying AI technologies, we aim to decipher the “biological language” encoded in genomes, contributing to next-generation life science and healthcare.
October 1, 2025 at 2:19 AM