Piyush G.

AlphaGenome: AI for better understanding the genome Introducing a new, unifying DNA sequence model that advances regulatory variant-effect prediction and promises to shed new light on genome function — now available via API.

Google introduced AlphaGenome: A new AI tool that predicts genetic variant impacts on gene regulation and disease biology, accelerating scientific discoveries! 🧬🔬 #AI #Genetics #Science #Technology

Read more:
deepmind.google/discover/blo...

Breakthrough from Google DeepMind: AlphaGenome is Here 🧬

Hi @bioinformer.bsky.social, can you share the webinar link ?
Great work btw!! Looking forward to hear more

DeepMind’s new AlphaGenome AI tackles the ‘dark matter’ in our DNA Tool aims to solve the mystery of non-coding sequences — but is still in its infancy.

Interesting... but we need better data for this to work www.nature.com/articles/d41... #genomics #artificialintelligence #dna #bioinformatics

always always always run the sample data first when testing a new program #bioinformatics

The Windows Subsystem for Linux is now open source Today we’re very excited to announce the open-source release of the Windows Subsystem for Linux. This is the result of a multiyear effort to prepare for this, and a great closure to the first ever iss...

It's great to see Windows Subsystem for Linux being open source by Microsoft! 🎉 I've been using WSL2 for my everyday Linux CLI tasks for Bioinformatics 🖥 🧬 – personally and professionally.
#WSL #OpenSource #Microsoft #Linux #Development #Technology
Blog Post: blogs.windows.com/windowsdevel...

Regeneron Enters into Asset Purchase Agreement to Acquire 23andMe® for $256 Million; Plans to Maintain Consumer Genetics Business and Advance Shared Goals of Improving Human Health and Wellness | Rege... Purchase is subject to bankruptcy court and regulatory approvals Regeneron will prioritize the privacy, security and ethical use of 23andMe’s customer data; stands ready to work with independent, cour...

Regeneron brought 23&Me customer data for $256M! 💰 This is HUGE for RWE data utilization, but will security & data privacy remain the same? 🤔 🧬 🖥 #Biotech #DataPrivacy #Investment #Healthcare #Technology
Full press release: investor.regeneron.com/news-release...

AI can now model and design the genetic code for all domains of life with Evo 2 | Arc Institute Arc Institute develops the largest AI model for biology to date in collaboration with NVIDIA, bringing together Stanford University, UC Berkeley, and UC San Francisco researchers

🧪 The Arc Institute's Evo2 models DNA like an LLM models language, predicting mutations, gene function, and evolutionary signals. With 40B parameters trained on 128K genomes, it hints at AI-driven biological discovery. 🧬💻 #MLSky
Link to the paper: https://arcinstitute.org/manuscripts/Evo2

Yeah, if you regularly switch between R & Python (which Bioinformatics people usually have to do) Spyder for Python, RStudio for R is a great combo

Update ?

process_arrays.sh — Codefile Create collaborative code files online for your technical interviews, pair programming, teaching, etc.

Try this out:
codefile.io/f/Wy3y3ONyn7

Protecting Privacy When Genetic Databases Are Commercialized This Viewpoint questions whether people’s health data obtained in direct-to-consumer genetic testing can be used, shared, or marketed in the future.

This a very important topic considering recent sudden dissappearance of Atlas Biomed, continuing problems at 23andMe, acquisition of Ancestry by an investment firm Blackstone, & multiple security incidents. #genomics #healthinformation
jamanetwork.com/journals/jam...

Accurate. #chemsky

By instagram.com/nathanwpyles...

Thanks, as someone who uses different tools and needs up-to-date references at times.. this is great. I was thinking to start a pet-project myself to automate it

This is what I have added to my .bashrc file

alias untar="tar xvf"
alias untgz="tar xvzf"
alias untargz="tar xvzf"
alias unbz2="tar xvjf"

#Linux #Bash #bioinformatics

I would say ppt and pdf serves different purpose. For a quick glance at things ppt is best, for a indepth look at the pipeline pdf is best. Show ppt with the gist then open pdf for a detailed discussion.

Benchmarking AI Models for In Silico Gene Perturbation of Cells https://www.biorxiv.org/content/10.1101/2024.12.20.629581v1 🧬🖥️🧪

RNA-seq tutorial with DESeq2: Differential gene expression project YouTube video by OMGenomics

🎁 New RNA-Seq tutorial! Learn to run differential expression analysis with DESeq2, and create your own bioinformatics projects using public data and the Expression Atlas 🧬 🖥️

youtu.be/NGbZmlGLG5w

Put 👏🏼 the 👏🏼 sample 👏🏼 size 👏🏼 in 👏🏼 the 👏🏼 abstract 👏🏼

Lore accurate

Apart from Claude 3.5 sonnet, rest all will go into infinite loop of solutions that would never work even if given better context in the chat later on. Only Claude is able to improve and iterate (at times claude fails as well.. ask it to perform a complex unix task such as rename files recursively)

Friends don't let friends make bad graphs repo has been updated!

Friends don't let friends use histogram for small sample sizes. Bin numbers affect the appearance of histograms, thus not robust to small (and modest sample sizes). They stabilize w/ large sample sizes.

github.com/cxli233/Frie...

Another day, another "bio" founder living in their bubble 🫧

The convergence of quantum computing and early drug discovery Drug development is an increasingly costly and time-consuming endeavour for biopharma companies, but the emergence of quantum computing is expected to transform the early drug discovery process.

Here's a great article discussing the future of Quantum chips and rapid early drug discovery advancements
www.kvantify.com/inspiration/...

Meet Willow, our state-of-the-art quantum chip Our new quantum chip demonstrates error correction and performance that paves the way to a useful, large-scale quantum computer.

#Google just announced the Willow their new #quantumchips

Can we expect a future where we will be doing seconds (yes, seconds) of MD Simulations using such quantum chips. .

blog.google/technology/r...

#drugdiscovery #mdsimulation #willow #quantumchip

Release DeepVariant 1.8.0 · google/deepvariant In this release: Small model integration: Speed increased by ~1.7x (40% runtime reduction) for WGS, PacBio, and ONT by introduction of additional small model. The small model identifies easy-to-...

Ok so this #deepvariant caller update from #google is BIG.
github.com/google/deepv...

- 1.6x time reduction (40% increase ??)
- Pangenome integration
- New model and improvements over previously model

Excited to try this new update 🧬💻

#bioinformatics #wgs #ngs #variantcalling

New in @theinnovation.bsky.social! Thirteen years of clusterProfiler.
This article provides a comprehensive review of the 13-year developmental trajectory of the research team in advancing #clusterProfiler. Read more
doi.org/10.1016/j.xi...
#bioinformatics #genomics #lifesciences

When you check on your cell culture after the weekend