🔥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

Most promising-looking AI research ideas don’t pan out, but testing them burns through compute and labor. Can LMs predict idea success without running any experiments? We show that they do it better than human experts!

A bold step for "Ease of Doing Science". Time to push for 1% of GDP in science funding, ramp up faculty hires in national labs & MHRD institutes, and significantly boost state university support. With US cuts, India can attract top global talent. Principal Scientific Adviser, Govt. of India Indian National Science Academy (INSA)

I am incredibly sad to learn of the passing of Atul Butte. He was a true giant in our field and a profound inspiration to me and countless others. His vision and contributions have fundamentally shaped biomedical data science. I will miss his boundless energy. RIP my friend.

Rest in Peace, dear Atul. We lost a giant and a beautiful soul 🙏 Atul Butte

Saddened to hear of the passing of Atul Butte. A brilliant scientist, visionary leader, and tireless advocate for data-driven medicine. His impact UC San Francisco, precision health, and trainees will be felt for generations. May his memory be a blessing. UCSF School of Medicine UCSF Health

1/12 Excited to share our team's latest work and the first @xaira_thera preprint! Here, we introduce FiCS Perturb-seq, an industrialized platform for generating scaleable, high-quality perturbation data. 📄 Read the preprint: biorxiv.org/content/10.110…

2/12 This work was inspired by the need for large, high-quality perturbation datasets to train foundation models that understand causal relationships of biology. Current methods for generating perturbation data are limited by throughput and batch-to-batch variability.

3/12 To overcome these challenges, we developed FiCS Perturb-seq, a platform that integrates fixation, FACS enrichment, cryopreservation, superloading, and automation for scalable, high-quality Perturb-seq data generation.

An excellent new review of Type 2 diabetes JAMA today jamanetwork.com/journals/jama/…

🔥Monopolizing the smartest AI and healthtech nerds of the country in our research lab (also the largest forum of physician scientists and medicos who code)! I hate monopolies but this is fun ngl😈 If you code and are in healthtech, what is your excuse for not being a part of

Heart disease is still the #1 killer in the United States, but it's no longer from heart attacks...instead it's from heart failure and arrhythmias ahajournals.org/doi/10.1161/JA…

+1 for "context engineering" over "prompt engineering". People associate prompts with short task descriptions you'd give an LLM in your day-to-day use. When in every industrial-strength LLM app, context engineering is the delicate art and science of filling the context window

What a mind-blowing week for AI in biology! 🚀 Xaira just dropped the largest genome-wide perturbation dataset ever last week 🧬 Arc unveiled STATE yesterday, the most powerful foundation model for single-cell perturbation prediction 🧠 DeepMind followed up with AlphaGenome,

Register today for the Virtual Cell Challenge and use AI to solve one of biology’s most complex problems. Announced in Cell, the competition is hosted by Arc Institute and sponsored by NVIDIA, 10x Genomics, and Ultima Genomics.

pnas.org/doi/10.1073/pn… Latest from the lab. ICGEB Official ICGEB, New Delhi Department of Biotechnology Excellent collaboration with Vinay CCMB AIIMS, New Delhi 🇮🇳 and Amit Singhal Thanks to support from DBT/WT India Alliance

A common misunderstanding of DSPy is that it's a "prompt optimizer". This is like thinking SQL Databases are equivalent to "optimizers for JOIN queries". DSPy is about declarative programming: isolating your AI intent from the specifics of LLMs. Like any other declarative

Prevalence data from NHANES (2017-2023) for MASLD, Met-ALD, and ALD and associated fibrosis among US adults. journals.lww.com/jcge/abstract/…

Correspondence: Lifesaving Diagnosis through Prenatal Genomic Sequencing nej.md/45KYWbV #Hematology

Despite a decade of growth and poverty schemes, nutritional progress has quietly stalled. Chasing calories alone hides deeper gaps in food quality, diversity, and equity—undermining long-term human capital. eng.ruralvoice.in/national/calor…

We are really on fire @ISCB this year! We got 1 flash talk & 5 posters! Small thread for promotion 😊 Miguel Fernandez presents our work "Towards a biophysical description of the protein universe" at 3DSIG room 3B, tomorrow 14:40. He is also available at poster 85! (+)