🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Very excited and grateful that our team's work can be part of this important work from Human Pangenome Research Consortium, which was published in Nature today: nature.com/articles/s4158…

We've added a few links to goo.gl/deepvariant. Take a look if you haven't read our recent blog posts :)

Medicine is inherently multimodal. Thrilled to share Med-PaLM M, the first demonstration of a generalist multimodal biomedical AI system with a stellar team Google AI Google DeepMind Google Health Paper: arxiv.org/pdf/2307.14334…

Excited to share this analysis of Element Biosciences’s data (and their new Cloudbreak chemistry). We see accuracy advantages in Element data, especially at 20x-30x coverages and in homopolymers and repeats. Longer sequening inserts can further improve recall through hard genome regions.

medium.com/girlsgetmagic/… We are proud and thrilled to share this amazing blog from one of our MAGIC mentees, Sofia Sassone. Sofia's MAGIC mentor is Namrata GR Raut. Sofia provides an in-depth look into nanoparticles and it's use on preservation of historical artifacts. Super!

Happy to share this paper which provides more detail about the process we use to assign haplotypes to long reads on-the-fly, which enabled us to speed up the DeepVariant release at v1.4. Implementation by Alexey Kolesnikov, Lead for collaboration, writing, figures Kishwar

MAGIC (Get Magic) is looking for female mentors for for middle and high school girls. We're now open for applications for 2024 Spring (Jan-May). Please see bit.ly/CallForMAGIC for more info. I have been mentoring for MAGIC since 2008. Happy to chat more.

Initial release of DeepSomatic, which identifies subclonal variants when given tumor and normal BAM files. Pre-trained models and case studies available for Illumina and PacBio. Development led by Kishwar which built off a framework by Pi-Chuan Chang github.com/google/deepsom…

Release of DeepVariant v1.6. Support for haploid regions, chrX/Y. Workflow for Pangenome FASTQ-to-VCF. Major DeepTrio improvements for de novo variants. Models for CompleteGenomics T7, G400 Add NovaSeqX to training data Release by Kishwar github.com/google/deepvar…

My 2023 summer mentee (through GetMAGIC) was Isha. It was really fun working with her using microbit (microbit.org) and writing Python to create a project! It's great to see this being a spotlight on MAGIC's Instagram page! instagram.com/p/CzMC8IeujfG

#GivingWeek Please consider donating to MAGIC (Get Magic ) ==> getmagic.org/donate <== a non-profit that I’ve volunteered for since 2008. medium.com/girlsgetmagic/…. As I often said, “MAGIC volunteer” is the job I’ve held for the longest time. 🙂

DeepSomatic (github.com/google/deepsom…) preprint is out showing improvements in somatic variant calling in various platforms. Work lead by Jimin Park and Daniel Cook ∛. Tumor-only lead by Pi-Chuan Chang. In collaboration with Andrew Carroll, Misha Kolmogorov and @BenedictPaten. 🧵1/7

Can you genotype a variant with only the information in the image below? We were surprised DeepVariant can get an F1 of 0.82 for Insertions with only MAPQ, vs F1 0.48 for random guessing. Why? we investigate how DeepVariant uses signals in a new blog (google.github.io/deepvariant/po…)

I have just finished mentoring for GetMAGIC this summer! youtube.com/playlist?list=… We're looking for female mentors for middle and high school girls! Applications are now open for 2025 Spring (Jan-May). Please see bit.ly/CallForMAGIC for more info.

Transformer-based polishing approach DeepPolisher's manuscript is now live. Mira Mastoras polished 180 assemblies using DeepPolisher for the next human pangenome release. Collaboration with @BenedictPaten Mobin Asri. PM Andrew Carroll and eng mng Pi-Chuan Chang. biorxiv.org/content/10.110…

Initiated in 2023 by Maria Nattestad and Been Kim, this project has been a collaborative effort. For over a year, Atilla and Yuchen dedicated 20% of their time to working with Been Kim , Andrew Carroll and myself on this project. It has been a fun exploration!

Release of DeepVariant 1.8. Large speed improvement (~67% faster) via small model for easy sites. New Pangenome-aware option. Reduces error by ~30% for vg-mapped WGS ~10% for BWA WGS ~5% BWA exome. New config for custom model users, see release notes 1/3 github.com/google/deepvar…