Akshat Singhal, PhD

Director of Bio Machine Learning - 136085 Director of Bio Machine Learning - 136085 | Careers at UC San Diego

We @idekerlab.bsky.social are looking for the "Director of Bio Machine Learning". Please apply and repost. lnkd.in/gvPP9X6v

#oncsky #ML

And it's posted! If you're interested and eligible, please consider applying through the UMD portal: umd.wd1.myworkdayjobs.com/en-US/UMCP/j....

If you're a PI working in algorithmic genomics (& you can recommend my lab to your top graduating students ;P), please let them know!

The Ideker Lab is thrilled to be part of the recently launched ARPA-H ADAPT program. Read More: "ARPA-H pioneers game-changing cancer care designed to adapt throughout treatment"
arpa-h.gov/news-and-eve...

Senior Bio Machine Learning Scientist - 136085 Senior Bio Machine Learning Scientist - 136085 | Careers at UC San Diego

The Ideker Lab is recruiting a Director of BioMachine Learning (BioML) to lead machine learning research and development for the "Dynamic Digital Tumors for Precision Oncology" project, a new precision cancer therapy initiative funded by the ARPA-H ADAPT Program. employment.ucsd.edu/senior-bio-m...

Ideker lab is on Bluesky now!

@jengreitz.bsky.social l & my lab want to co-hire a computational biologist/biostatistician with project management expertise to help map the regulatory code of the human genome and discover genetic mechanisms of disease.

Details below
careersearch.stanford.edu/jobs/computa...

Plz RT

Math is easy; aftermath is hard

We are on the lookout for postdocs for two different projects at the intersection of ecology, evolution, and the human microbiome.

See thread for more information and reach out!

Curebound | Accelerating Cancer Research Into Cures Curebound Investing in Cures. $37+ million raised for cancer research in San Diego.

Hi Everyone,
I'm raising funds for CureBound which supports cancer research across various institutions in San Diego including UC San Diego, Rady Children's Hospital, Salk, and Scripps, among others.
URL: curebound.donordrive.com/participant/...
Curebound: www.curebound.org.
#oncsky #medsky

Staff scientist position (computational):

I am looking for a computational scientist to join my genomics lab at Stanford. They should have an outstanding skillset in ML/statistical methods for genomic applications, postdoc experience and a strong publication record.
#sciencejobs

"in 2025 we will have flying cars" 😂😂😂

(Longish thread. Apologies)

I have met many inspiring colleagues over the past few months, many of whom are in academic institutions targeted by the current administration, and many others who are about to be (the analogy to the ‘eye of Sauron’ has been invoked many times; gallows humor). 1/

Incredible work by Leah, @clarahu.bsky.social, and the rest of the team. Congrats!

So I guess Jurassic Park in real life would be billions in VC investment and years of press releases followed by a tank containing five deformed iguanas

Excited to present "AI for precision oncology: Real-world analysis of a CDK4/6 inhibitor model" with @akshatsinghal.bsky.social at #ACSSpring2025 this weekend! Love sharing our work with different crowds!

I'm defending my PhD this Friday. So I wrote an invitation letter for comic relief.
#AcademicSky #PiDay #PhdSky

Censor, purge, defund: how Trump following the authoritarian playbook on science and universities I have mapped 35 of the Trump administration's attacks on science and universities to the authoritarian playbook - and consider what it means for attacks still to come

My latest post is now out.

I show how Trump's attacks on science and universities are neither random nor new - they fit very precisely into the authoritarian playbook.

This means we can guess what might come next and prepare - and we must!

christinapagel.substack.com/p/censor-pur...

Alt text/caption:
Meme showing the iconic Titanic musicians playing violin, with overlaid text reading 'ACADEMIC CONFERENCES IN THE US IN 2025' to mournfully evoke the tragic end of an era.

Only problem is Musk doesn't care about the correctness of AI for these black-mirroresque applications. An AI can easily decide who to fire based on email because it can come up with any arbitrary metric and a seemingly perfect explanation for it. Problem solved.

Meme showing the iconic Titanic musicians playing violin, with overlaid text reading 'ACADEMIC CONFERENCES IN THE US IN 2025' to mournfully evoke the tragic end of an era.

Gene editing technology began by people studying salt marshes. Ozempic began by folks studying the venom of Gila Monsters. Support for basic science has empowered us to understand our world. Tethering it to applications health has transformed and saved countless lives.

[SAVE THE DATE] MLCB 2025 is happening Sept 10-11 at the NY Genome Center in NYC!

Attend the premier conference at the intersection of ML & Bio, share your research and make lasting connections!

Submission deadline: June 1
More details: mlcb.github.io

Help spread the word—please RT! #MLCB2025

It is Faculty interview season, so I created a doc with compiled Chalk Talk advice! Please share widely- this shouldn't be hidden curriculum... there is a recipe for success! I will also share videos of my practice and actual UCSD chalk talk with anyone who wants it! DM me!

A checklist for AI in precision oncology 🤖

Seven key features have been identified, to build trustworthy cancer prediction models for clinical use.

rebrand.ly/99xw93e

@bhaibeka.bsky.social
@ucsandiego.bsky.social
@akshatsinghal.bsky.social
@uhnresearch.bsky.social
@theaacr.bsky.social

HARMONY checklist. HARMONY = Hallmark-Adhering Recommendations for Models in predictive ONcologY.

And a checklist

A two-panel figure with self-critique of authors’ own model. Panel A. Overview of the TCRP model approach. B, Scorecard for the TCRP model based on the criteria defined for scoring each hallmark.

Add-ons: A model scorecard

The seven hallmarks of predictive oncology. Starting from the top left, in clockwise order, the proposed hallmarks are Data Relevance and Actionability (yellow), Expressive Architecture (blue), Standardized Benchmarking (black), Demonstrated Generalizability (green), Mechanistic Interpretability (orange), Accessibility and Reproducibility (purple), and Fairness (pink), with ethics underlying each of these hallmarks (yellow ring).

Excited to share our perspective on cancer therapy response models, "The Hallmarks of Predictive Oncology"
doi.org/10.1158/2159...

We propose and discuss seven "hallmarks" necessary for clinical adoption of AI models.
@bhaibeka.bsky.social

#Oncsky #CompBio #AI #ML #PrecisionOncology

2.

Can I also join? Thanks!