Harmon Bhasin
harm0n.bsky.social
Harmon Bhasin
@harm0n.bsky.social
Research Analyst I @ SecureBio/MIT

Pandemic prevention, gene regulation, and genomic foundation model enthusiast

harm0n.com
Reposted by Harmon Bhasin
Now out "in print": we review domain adaptation methods, along with gaps and considerations for datasets of "biological scale" (many features, few samples, etc.). A fun CIFAR-funded collaboration with @meganakpeters.bsky.social 🧬 🖥️
www.science.org/doi/full/10....
Domain adaptation in small-scale and heterogeneous biological datasets
Research using biological data can benefit from domain adaptation modeling approaches, but it also carries distinct challenges.
www.science.org
December 22, 2024 at 9:19 PM
Reposted by Harmon Bhasin
Finally out! We present EXTRA-seq, a new EXTended Reporter Assay to quantify endogenous enhancer-promoter communication at kb scale!
www.biorxiv.org/content/10.1...
A 🧵about what it can do:
#SynBio #DeepLearning #GeneRegulation
EXTRA-seq: a genome-integrated extended massively parallel reporter assay to quantify enhancer-promoter communication
Precise control of gene expression is essential for cellular function, but the mechanisms by which enhancers communicate with promoters to coordinate this process are not fully understood. While seque...
biorxiv.org
December 16, 2024 at 2:39 PM
CGSI, computationalgenomics.bioinformatics.ucla.edu, posts all of their talks on their youtube channel, youtube.com/@computation.... Highly relevant for those interested in genomics #bioinformatics.
Computational Genomics Summer Institute CGSI
youtube.com
December 14, 2024 at 10:33 PM
Very relevant for any folks in #biosecurity. Also check out the 300 page report, purl.stanford.edu/cv716pj4036.
December 12, 2024 at 7:56 PM
Reposted by Harmon Bhasin
Introducing ESM Cambrian, a new family of protein language models, focused on creating representations of the underlying biology of proteins.
December 4, 2024 at 5:45 PM
Here's another youtube channel with a bunch of talks on the intersection of deep learning/ml and bio www.youtube.com/@valence_lab.... #bioinformatics
Valence Labs
Harnessing computation to radically improve lives. Learn more: https://www.valencelabs.ca/
www.youtube.com
November 29, 2024 at 3:43 PM
Recently stumbled upon these talks from the 2024 Genome Sciences Symposium at the University of Washington. #bioinformatics

youtube.com/playlist?lis...
2024 Genome Sciences Symposium - AI For Genomics and Proteomics - YouTube
October 18, 2024 - A symposium at the University of Washington presented by Genome Sciences, Computer Science & Engineering, and the Fred Hutchinson Cancer C...
youtube.com
November 24, 2024 at 2:41 AM
Reposted by Harmon Bhasin
Here is a #compbio starter kit! go.bsky.app/QVPoZXp To all the #Bioinformatics #Genomics #MachineLearning folks: please RP and let’s build this together!
November 23, 2024 at 4:17 AM
Reposted by Harmon Bhasin
Two BioML starter packs now:

Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc

DM if you want to be included (or nominate people who should be!)
I tried to make a bioml starter pack. DM if you want me to add or remove you?

go.bsky.app/2VWBcCd
Anybody have a bioml starter pack?
November 18, 2024 at 5:09 PM
Reposted by Harmon Bhasin
👀 Working on a #StarterPack for early career researchers (PhD students & Postdocs) in #genomics & #bioinformatics 🧬🖥️ Please share! Happy to add those working in this area so please suggest. Seeing a lot of PIs on here but would love to see more students 🎓🚀
November 20, 2024 at 3:38 PM
Reposted by Harmon Bhasin
Delighted to share our work to develop a genomic DNN, Enformer Celltyping, to accurately predict epigenetic signals in previously unseen cell types has now been published doi.org/10.1038/s414...
Predicting cell type-specific epigenomic profiles accounting for distal genetic effects - Nature Communications
Enformer Celltyping is a genomic deep learning model that predicts epigenetic signals in unseen cell types using distal DNA interactions and chromatin accessibility data. Here, authors show it general...
doi.org
November 18, 2024 at 8:57 AM
Reposted by Harmon Bhasin
Uncertainty-aware genomic deep learning with knowledge distillation https://www.biorxiv.org/content/10.1101/2024.11.13.623485v1
Uncertainty-aware genomic deep learning with knowledge distillation https://www.biorxiv.org/content/10.1101/2024.11.13.623485v1
Deep neural networks (DNNs) have advanced predictive modeling for regulatory genomics, but challenge
www.biorxiv.org
November 16, 2024 at 2:35 AM
Reposted by Harmon Bhasin
JUST ACCEPTED at Science Advances!
Domain adaptation in small-scale and heterogeneous biological datasets
by Mehdi Orouji, Martin Liu, Tal Korem, & me!

a truly interdisciplinary collaboration: #neuroscience 🧠🤖 #cogpsyc, machine learning #MLSky, & microbiome

preprint: arxiv.org/abs/2405.19221

🧵1/n
Domain adaptation in small-scale and heterogeneous biological datasets
Machine learning techniques are steadily becoming more important in modern biology, and are used to build predictive models, discover patterns, and investigate biological problems. However, models tra...
arxiv.org
November 11, 2024 at 9:44 PM
Reposted by Harmon Bhasin
Evo: A genomic language model of prokaryote genomes generates functional cas9 proteins and transposons.

@brianhiestand.bsky.social

www.science.org/doi/10.1126/...
November 14, 2024 at 8:53 PM
Reposted by Harmon Bhasin
#AMIA2024 WELCOME TO BLUESKY! 🦋

I'm so excited to see people finally arrive at the shores of Bluesky!

I want to make sure you stick around so let me give you a guided tour on how to maximize your fun and engagement here! 🧵
November 12, 2024 at 3:02 PM
Reposted by Harmon Bhasin
There are so many people moving over that I'm sure I'm missing folks. Can we make a #compbio / #genomics intro thread to get reacquainted?

I'm at the University of Colorado. I often say that if you pick two of three from #transcriptome, #ML, and #publicdata, my lab is probably interested.
November 12, 2024 at 8:04 PM