Chirag Lakhani

441 posts

Chirag Lakhani

Chirag Lakhani

@cmlakhan

Currently: Staff Scientist @nygenome in the @david_a_knowles lab. Previously: @HarvardDBMI Postdoctoral Research Fellow in @chiragjp lab https://t.co/APTLHsivM2

Katılım Mayıs 2013
4.1K Takip Edilen525 Takipçiler
Chirag Lakhani retweetledi
Anshul Kundaje
Anshul Kundaje@anshulkundaje·
Plenty of excitement about DIY genome sequencing, genetics & AI for Bio. But its going to take decades to decipher the genetic & molecular basis of diseases. Requires increasing, not gutting NIH funding of academic research (expts, computational, clinical) to get to the answers.
Sheryl Gay Stolberg@SherylNYT

NEW: NIH spending on new medical research has fallen roughly $1 billion behind the pace of years past, delaying thousands of scientific projects. @benjmueller @irenatfh nytimes.com/2026/04/22/sci…

English
1
9
77
11.4K
Arjun (Raj) Manrai
Arjun (Raj) Manrai@arjunmanrai·
A short summary of our recent article in @NatureMedicine. It’s been a privilege to work w @chiragjp for ~a decade on these and related projects (thanks @zakkohane @HarvardDBMI for creating the environment). Will do a thread on the implications of our new studies soon
Chirag Patel@chiragjp

A research article briefing with the story behind the story: Link: nature.com/articles/s4159… Looking forward to hear from us for new directions and ideas! cc @nexusexposomics

English
2
6
16
3.2K
Chirag Lakhani
Chirag Lakhani@cmlakhan·
@chiragjp Congratulations! Inspiring to see you guys continuing to chart new waters in the study of the Exposome! Always inspired in how you have developed usable tools beyond just publication.
English
0
0
1
28
Chirag Lakhani retweetledi
Chirag Patel
Chirag Patel@chiragjp·
The next frontier: advancing #exposomics to understanding biology of disease. Causal attribution: where the heck do the exposures came from and how do they change from birth to death? But, not least, understanding how they matter to the health of the individual with the tools of AI and continuous monitoring. 🚀
English
2
2
2
223
Chirag Patel
Chirag Patel@chiragjp·
Imagine navigating a city with only a photo of one street corner. That's what candidate-exposure studies give us — few factor/chemical/agent and one disease --> one snapshot. It's impossible to make sense of it all and how it relates to our health. I team up w/ @arjunmanrai & John Ioannidis to write a new article in @NatureMedicine that attempts to draw a first map between #exposome -- the entirety of our environmental makeup -- and >200 disease risk factors we all care about. Read our paper: rdcu.be/e8Ls2 Press: hms.harvard.edu/news/large-sca… @HarvardDBMI @nexusexposomics @NatureMedicine @StanfordDBDS @harvardmed
English
4
12
27
5.9K
Chirag Lakhani retweetledi
Chirag Patel
Chirag Patel@chiragjp·
We built open tools so you can explore it yourself: 📦 R package nhanespewas → github.com/chiragjp/nhane… 🗂️ Browsable Phenome-Exposome Atlas (all 120k+ associations): pe.exposomeatlas.com 📓 Quickstart + ExWAS tutorial notebooks 📚 And a course/tutorial walking through the methods end to end: exwas-course.exposomeatlas.com Paper: nature.com/articles/s4159… Thank you to the @NIH_NIEHS @NIDDKgov and @NIHAging for funding support!
English
1
1
0
184
Ryan Corces
Ryan Corces@ryancorces·
I'm truly honored to be one of this year's MIND Prize recipients. I look to many of the past recipients as the rising stars in neuro research and to be considered among them is inspiring. Can't wait to see what we can find with this support at a critical time in science funding.
MIND Prize@MindPrize

Congratulations again to the eight winners of our 2026 MIND Prize! 🎉 Learn more about these scientists and their innovative projects here: pershingsquarephilanthropies.org/news/pershing-…

English
7
2
46
3.8K
Chirag Lakhani retweetledi
Han Yuan
Han Yuan@HY3952·
Our manuscript for parameter-efficient fine-tuning of Borzoi is now out in Genome Biology: link.springer.com/article/10.118… We’ve also included transfer tutorials for - hg38: github.com/calico/baskerv… - mm10: github.com/calico/baskerv… Happy to hear your feedback!
Han Yuan@HY3952

1/ DNA sequence models like Borzoi predict gene expression and variant effects across 1000s of tissues — but what if your data comes from a custom experiment? @drklly @jjohlin and I propose a lightweight solution: parameter-efficient fine-tuning (PEFT). biorxiv.org/content/10.110…

English
2
26
89
9.7K
Chirag Lakhani
Chirag Lakhani@cmlakhan·
Quanta always has very interesting and in-depth articles about the latest breakthroughs in science. I especially enjoyed this one on how neural networks are being used in fluid dynamics research.
Quanta Magazine@QuantaMagazine

Yongji Wang, a researcher at Google Deepmind, helped develop physics-informed neural networks that can spot potential “unstable” singularities in fluid equations, a long-sought goal in mathematical physics. quantamagazine.org/using-ai-mathe…

English
0
0
1
67
Ronghui (Ron) Zhu
Ronghui (Ron) Zhu@RonZhu2015·
Together with Emma Dann, we are thrilled to present a massive new Perturb-seq atlas of 22M primary CD4+ T cells, from 4 donors, across 3 timepoints – the result of a decade-long collaboration between the Marson (@MarsonLab) and Pritchard (@jkpritch) labs. 🧵👇
Ronghui (Ron) Zhu tweet media
English
4
52
241
38.9K
Chirag Lakhani retweetledi
Peter Koo
Peter Koo@pkoo562·
Mark your calendars: The AI x Bio meeting of 2026 will be held at CSHL on May 26-31! The program brings together 50+ invited leaders in genomics, transcriptomics, protein design, drug discovery, neuroAI, pathology, agentic AI, and more! Abstract: 3/26 meetings.cshl.edu/meetings.aspx?…
English
4
104
339
33.6K
Chirag Lakhani retweetledi
60 Minutes
60 Minutes@60Minutes·
“We are doing a service for the United States because they’ve identified needs that need to be met,” says Harvard bioengineer Don Ingber, defending federal grants and contracts to universities for scientific and medical research. cbsn.ws/43WLa47
English
59
45
142
17.4K
Chirag Lakhani
Chirag Lakhani@cmlakhan·
This looks awesome
Chieh-Hsin (Jesse) Lai@JCJesseLai

Tired to go back to the original papers again and again? Our monograph: a systematic and fundamental recipe you can rely on! 📘 We’re excited to release 《The Principles of Diffusion Models》— with @DrYangSong, @gimdong58085414, @mittu1204, and @StefanoErmon. It traces the core ideas that shaped diffusion modeling and explains how today’s models work, why they work, and where they’re heading. 🧵You’ll find the link and a few highlights in the thread. We’d love to hear your thoughts and join some discussions! ⚡ Stay tuned for our markdown version, where you can drop your comments!

English
0
0
1
95
Tim Dettmers
Tim Dettmers@Tim_Dettmers·
Did Anthropic cut rate limits again? I never hit rate limits before on my plan, but now hitting rate limits very quickly. Does anybody have similar experiences?
English
19
1
86
15.3K
Chirag Patel
Chirag Patel@chiragjp·
Hard at work: Day 2 genomics meets exposomics, Brno, Mendel Museum. @nexusexposomics he’s looking over us
Chirag Patel tweet media
English
3
1
11
524
Chirag Lakhani retweetledi
Yun S. Song
Yun S. Song@yun_s_song·
We are excited to share GPN-Star, a cost-effective, biologically grounded genomic language modeling framework that achieves state-of-the-art performance across a wide range of variant effect prediction tasks relevant to human genetics. biorxiv.org/content/10.110… (1/n)
Yun S. Song tweet media
English
17
162
529
85.8K
Chirag Lakhani retweetledi
Anshul Kundaje
Anshul Kundaje@anshulkundaje·
Excited for a major milestone in a collab effort led by @jengreitz to map enhancers & interpret variants in the human genome: The E2G Portal e2g.stanford.edu collates predictions of enhancer-gene regulatory interactions across >1,600 cell types & tissues. Use cases 👇1/
English
6
29
124
12.4K

Keşfet

@arjunmanrai @zakkohane @NatureMedicine @chiragjp @HarvardDBMI @nexusexposomics @StanfordDBDS @harvardmed