Adam He (@missing_a_rib) profile picture

Adam He

@missing_a_rib

Machine learning, RNA transcription, genomics, statistical genetics. Postdoc @StanfordMed with @anshulkundaje. Previously PhD student with @charlesdanko

 Palo Alto, CA
adamyhe.github.io/
Joined July 2013
  • Tweets364
  • Following607
  • Followers239
23Media
Photo by Adam He (@missing_a_rib)Photo by Adam He (@missing_a_rib)Photo by Adam He (@missing_a_rib)Photo by Adam He (@missing_a_rib)Photo by Adam He (@missing_a_rib)Photo by Adam He (@missing_a_rib)Photo by Adam He (@missing_a_rib)Photo by Adam He (@missing_a_rib)Photo by Adam He (@missing_a_rib)Photo by Adam He (@missing_a_rib)
Adam He retweeted
NYGCtech (@NYGCtech) profile picture
NYGCtech@NYGCtechNov 9
Excited to share our latest preprint! 🎉 SPACE-Tag enables high-throughput spatial chromatin profiling with CUT&Tag. Huge congrats to Chao, Ruiyang, Sara, Maros, Silas, Ivan, and Sanja! 👏 🔬 biorxiv.org/content/10.64898…
SPACE-Tag Enables High-Throughput Spatial Chromatin Profiling With CUT&Tag

SPACE-Tag Enables High-Throughput Spatial Chromatin Profiling With CUT&Tag

Spatial epigenomics maps chromatin states within intact tissues, yet current methods remain limited by accessibility and scale. We developed SPACE-Tag, a spatial CUT&Tag framework that converts...

biorxiv.org
14
1
53
5,089
amazing work showing that predictions from different tracks of seq2exp models do not reflect a coherent model of transcription biorxiv.org/content/10.64898…
Systematic promoter perturbation reveals limitations of AlphaGenome gene expression predictions

Systematic promoter perturbation reveals limitations of AlphaGenome gene expression predictions

Sequence-to-function (S2F) models promise to facilitate the interpretation of noncoding variants by predicting their effects on gene regulation directly from genomic sequence. However, whether these...

biorxiv.org
2
15
55
5,405
Adam He retweeted
antisense. (@razoralign) profile picture
antisense.@razoralignNov 8
Learning Strand-Equivariant Tokenizations of DNA with MirrorDNA biorxiv.org/content/10.64898…
Image from antisense. (@razoralign)
1
5
17
1,486
Our latest preprint: • Improved split-pool Perturb-seq method • Gene programs in hiPSC-endothelial differentiation • New role for Hippo pathway in vitro and in vivo • Strategy for improving differentiation by faking cell density biorxiv.org/content/10.64898… 1/
Image from Jesse Engreitz (@jengreitz)
1
28
1
102
6,842
We’re excited to welcome Chengzhong Ye (UC Berkeley @chengzhong_ye) to our AI+Biomedicine Seminar! Chengzhong will present "GPN-Star: Phylogeny-Informed Genomic Language Models for Functional Constraint Prediction" next Tuesday. Join us @ Gates 415 | Nov. 10 @ 2:30pm PT
Image from Stanford AI+Biomedicine Seminar (@Stanford_AI_Bio)
5
1
30
2,059
Adam He retweeted
Jian Zhou (@zhou_jian) profile picture
Jian Zhou@zhou_jianNov 5
Check out our new work! Understanding genome regulation at single-molecule level is key to deciphering the regulatory code. Mola is a sequence-to-distribution model that generates single-molecule chromatin states across 10 kb from sequence. Led by the one and only @jimwry! 1/2
Ruoyu Wang (@jimwry) profile pictureRuoyu Wang@jimwryNov 5
We are excited to share our latest work, Mola, a sequence-to-distribution (S2d) model for single-molecule regulatory genomics. Gene regulation happens at the single-molecule level. Mola predicts single-molecule chromatin-state distributions from DNA sequence. (1/8)
5
16
74
4,462
Adam He retweeted
antisense. (@razoralign) profile picture
antisense.@razoralignNov 4
RAPTORGraph: graph-based pathway modeling for causal discovery in single-cell perturbations biorxiv.org/content/10.64898…
Image from antisense. (@razoralign)
1
3
24
1,261
The @GoogleDeepMind #Genomics team in London is hiring a Student Researcher for 2027. We're looking for PhD students with strong experience in machine learning (post-training and RL) and an interest in applying these methods to genomic models. Link to apply:
6
16
164
14,657
Adam He retweeted
Cell (@CellCellPress) profile picture
Cell@CellCellPressNov 1
In the latest issue! Structural basis of a SWI/SNF-associated transcription pre-initiation complex dlvr.​it/TW8DQG
Image from Cell (@CellCellPress)
2
29
1
106
13,583
Adam He retweeted
Cell (@CellCellPress) profile picture
Cell@CellCellPressOct 31
In the latest issue! Genome-scale perturb-seq in primary human CD4+ T cells maps context-specific regulators of T cell programs and human immune traits dlvr.​it/TW7dk3
Image from Cell (@CellCellPress)
2
30
1
110
13,590
Our latest, sent on behalf of the outstanding but X-less Aidan Keith: OPTIMuS PRIME-Del uses paired prime editing to program targeted deletions at candidate enhancers, while concurrently replacing them w/ a molecular tag to verify & quantify deletions 1/7 biorxiv.org/content/10.64898…
1
33
2
101
9,303
The week of drops continues: this time, the figwig data format for genomics! figwig generalizes bigwigs to n-dimensional arrays, so can efficiently store huge sets of tracks, single-cell experiments, fiber-seq, and even Hi-C and scHi-C experiments. github.com/jmschrei/figwig
GitHub - jmschrei/figwig: A fast, multithreaded reader and writer of bigWig and figwig files.

GitHub - jmschrei/figwig: A fast, multithreaded reader and writer of bigWig and figwig files.

A fast, multithreaded reader and writer of bigWig and figwig files. - jmschrei/figwig

github.com
7
25
2
100
9,533
New preprint from the lab: "A Compact Regulatory Logic Governs Fibroblast Cell State Plasticity in Fibrosis". We integrated mouse and human epigenomic data to identify 280 fibroblast disease-activated enhancers, then perturbed them by CRISPRi CROP-seq. 🧵 biorxiv.org/content/10.64898…
Image from Michael Alexanian (@m_alexanian)
3
18
4
128
8,362
Curious about ENCODE GRAMMAR? Want to know more about regulatory seq2func models in general? I'll be giving a talk at the BioML Seminar @ Berkeley next Mon (10/19), 7pm. First time speaking at Berkeley, so come say hi! 👋 🔗 Event: luma.com/bioml-r5if?tk=jatdM…
BioML Seminar 5.2 - Decoding the Grammar of Regulatory DNA · Luma

BioML Seminar 5.2 - Decoding the Grammar of Regulatory DNA · Luma

Another week, another seminar from the BioML group in Machine Learning at Berkeley, sponsored by Amplify Partners. This week, we're excited to host Chang Yun,…

luma.com
sarrah rose (@AgaRosegirl) profile picturesarrah rose@AgaRosegirlOct 15
Join us for our next BioML Seminar with Chang Yun (@chang_m_yun) from Stanford, next Monday 10/19! He will discuss ENCODE GRAMMAR, a deep learning model resource for decoding the DNA sequence logic of regulatory elements in the human genome! RSVP: luma.com/bioml-r5if
BioML Seminar 5.2 - Decoding the Grammar of Regulatory DNA · Luma

BioML Seminar 5.2 - Decoding the Grammar of Regulatory DNA · Luma

Another week, another seminar from the BioML group in Machine Learning at Berkeley, sponsored by Amplify Partners. This week, we're excited to host Chang Yun,…

luma.com
2
5
1
23
2,259
Adam He retweeted
antisense. (@razoralign) profile picture
antisense.@razoralignOct 11
GLARE: Genomic Language model for Automated Repetitive Element classification biorxiv.org/content/10.64898…
Image from antisense. (@razoralign)
1
10
42
2,446
Adam He retweeted
David Kelley (@drklly) profile picture
David Kelley@drkllyOct 9
This week we're releasing a preprint exploring state space models for long-sequence genomic prediction, alongside Cerberus, a set of open PyTorch models built on this work. biorxiv.org/content/10.64898…
Cerberus: bidirectional state space blocks improve accuracy and efficiency of regulatory sequence...

Cerberus: bidirectional state space blocks improve accuracy and efficiency of regulatory sequence...

Sequence-to-function models predict regulatory activity and variant effects from DNA sequence alone, and leading models such as Borzoi compute long-range interactions with self-attention. The...

biorxiv.org
4
47
5
161
26,537
Incredibly, incredibly excited to introduce SpliceAI2, the next generation of splicing prediction! 🧬🚀🧵
8
36
4
100
9,524
After a long wait, tangermeme is out @naturemethods! tangermeme implements the primitives of genomic sequence-to-function modeling with efficient, tested, and composable functions. I use it every day in my work, and I hope you find it useful too. nature.com/articles/s41592-0…
Tangermeme: a toolkit for understanding cis-regulatory logic using deep learning models

Tangermeme: a toolkit for understanding cis-regulatory logic using deep learning models

Nature Methods - The tangermeme software package is a comprehensive, flexible and efficient Swiss Army knife for deep learning-based cis-regulatory pattern identification and analysis.

nature.com
7
85
3
299
19,710
Adam He retweeted
Cell (@CellCellPress) profile picture
Cell@CellCellPressOct 1
In the latest issue! Robust regulatory interplay of enhancers, facilitators, and promoters in a native chromatin context dlvr.​it/TVkk6V
Image from Cell (@CellCellPress)
2
16
1
64
11,385
Online Now: Transcription factor clusters enhance gene expression in vivo without modulating bursting dynamics dlvr.it/TVhtS2
Image from Molecular Cell (@MolecularCell)
3
24
126
9,610
Load more