Pinned
paupaiz.bsky.social
@paupaiz.bsky.social
· Jan 27
Inbox | Substack
open.substack.com
TA’ing at Stanford for the past year has really tested my ability to bring concepts back to first principles. So I’d like to open office hours publicly, for free. Here’s how it will work: open.substack.com/pub/heylina/...
Reposted
Check out our web tool for searching for interactors of your favorite cell surface protein, developed by undergrad Pinyu Liao and postdoc postdoc Brendan Floyd @stanford-chemh.bsky.social
cellsurfacemap.org
cellsurfacemap.org
Cell Surface Map
Cell Surface Map - Distribution and organization data on immune cell surface proteins
cellsurfacemap.org
February 21, 2025 at 1:56 AM
Check out our web tool for searching for interactors of your favorite cell surface protein, developed by undergrad Pinyu Liao and postdoc postdoc Brendan Floyd @stanford-chemh.bsky.social
cellsurfacemap.org
cellsurfacemap.org
Reposted
It's been great watching this project develop over the past few years. Maxim is a terrific scientist!
Disease diagnostics using machine learning of B cell and T cell receptor sequences
www.science.org/doi/10.1126/...
TL;DR: BCRs ARE ALL YOU NEED!
(Well actually .... keep reading) 1/
www.science.org/doi/10.1126/...
TL;DR: BCRs ARE ALL YOU NEED!
(Well actually .... keep reading) 1/
Disease diagnostics using machine learning of B cell and T cell receptor sequences
Clinical diagnosis typically incorporates physical examination, patient history, various laboratory tests, and imaging studies but makes limited use of the human immune system’s own record of antigen ...
www.science.org
February 21, 2025 at 8:24 AM
It's been great watching this project develop over the past few years. Maxim is a terrific scientist!
Reposted
Thrilled to see this out! A jax based glm for single cell eqtl mapping! See 👇for details! 🧬
Excited to present our work on developing jaxQTL, a fast single-cell eQTL mapping tool that improves power and robustness in identifying sc-eQTLs using count-based models. See details in threads 🧵
www.medrxiv.org/content/10.1...
www.medrxiv.org/content/10.1...
Efficient count-based models improve power and robustness for large-scale single-cell eQTL mapping
Population-scale single-cell transcriptomic technologies (scRNA-seq) enable characterizing variant effects on gene regulation at the cellular level (e.g., single-cell eQTLs; sc-eQTLs). However, existi...
www.medrxiv.org
January 28, 2025 at 4:52 PM
Thrilled to see this out! A jax based glm for single cell eqtl mapping! See 👇for details! 🧬
Reposted
Combinatorial prediction of therapeutic perturbations using causally-inspired neural networks [updated]
Predicts target combos to reverse disease; unlike perturbation methods, achieves direct prediction via GNNs.
Predicts target combos to reverse disease; unlike perturbation methods, achieves direct prediction via GNNs.
January 29, 2025 at 4:54 AM
Combinatorial prediction of therapeutic perturbations using causally-inspired neural networks [updated]
Predicts target combos to reverse disease; unlike perturbation methods, achieves direct prediction via GNNs.
Predicts target combos to reverse disease; unlike perturbation methods, achieves direct prediction via GNNs.
Reposted
#MLCB2025 will be Sept 10-11 at @nygenome.org in NYC! Paper deadline June 1st & in-person registration will open in May. Please sign up for our mailing list groups.google.com/g/mlcb/ for future announcements. More details at mlcb.github.io. Please RP!
January 27, 2025 at 6:40 PM
#MLCB2025 will be Sept 10-11 at @nygenome.org in NYC! Paper deadline June 1st & in-person registration will open in May. Please sign up for our mailing list groups.google.com/g/mlcb/ for future announcements. More details at mlcb.github.io. Please RP!
Reposted
I’ve enjoyed revisiting my lectures on probabilistic modeling for compbio after a sabbatical year with Dave Kelley’s group at Calico, which was like “studying Catholicism at the Vatican” (to borrow Wallace’s simile). Machine learning in general, and genomics ML, are moving fast
During an internship at Calico, Gav got to work with Kayley Hake and Andy York and their teams to image mitochondria with Snouty. This was an amazing opportunity for learning advanced microscopy, like doing an internship at the Vatican to learn catholicism.
January 27, 2025 at 4:40 PM
I’ve enjoyed revisiting my lectures on probabilistic modeling for compbio after a sabbatical year with Dave Kelley’s group at Calico, which was like “studying Catholicism at the Vatican” (to borrow Wallace’s simile). Machine learning in general, and genomics ML, are moving fast
TA’ing at Stanford for the past year has really tested my ability to bring concepts back to first principles. So I’d like to open office hours publicly, for free. Here’s how it will work: open.substack.com/pub/heylina/...
Inbox | Substack
open.substack.com
January 27, 2025 at 6:11 PM
TA’ing at Stanford for the past year has really tested my ability to bring concepts back to first principles. So I’d like to open office hours publicly, for free. Here’s how it will work: open.substack.com/pub/heylina/...
Reposted
Modern GWAS can identify 1000s of significant hits but it can be hard to turn this into biological insight. What key cellular functions link genetic variation to disease?
I'm very excited to present our new work combining associations and Perturb-seq to build interpretable causal graphs! A 🧵
I'm very excited to present our new work combining associations and Perturb-seq to build interpretable causal graphs! A 🧵
January 26, 2025 at 12:13 AM
Modern GWAS can identify 1000s of significant hits but it can be hard to turn this into biological insight. What key cellular functions link genetic variation to disease?
I'm very excited to present our new work combining associations and Perturb-seq to build interpretable causal graphs! A 🧵
I'm very excited to present our new work combining associations and Perturb-seq to build interpretable causal graphs! A 🧵
Reposted
MutBERT: Probabilistic Genome Representation Improves Genomics Foundation Models [new]
Probabilistic genome representation focuses on informative SNPs, making training more efficient and models better.
Probabilistic genome representation focuses on informative SNPs, making training more efficient and models better.
January 25, 2025 at 12:51 PM
MutBERT: Probabilistic Genome Representation Improves Genomics Foundation Models [new]
Probabilistic genome representation focuses on informative SNPs, making training more efficient and models better.
Probabilistic genome representation focuses on informative SNPs, making training more efficient and models better.
Reposted
Machine learning (ML) is revolutionizing genomics, but common pitfalls can lead to misleading results. Here's a thread on how to avoid them 🧵
January 24, 2025 at 2:45 PM
Machine learning (ML) is revolutionizing genomics, but common pitfalls can lead to misleading results. Here's a thread on how to avoid them 🧵
Reposted
I made one for stats papers
November 18, 2024 at 4:02 AM
I made one for stats papers