Azim Dehghani Amirabad

Principal AI Scientist at J&J. Ex. postdoc at MIT & Broad Institute, PhD. Max Planck for Informatics
AI/ML, Multimodal Learning, Single Cell Genomics

[Azim Dehghani Amirabad @Azim30153364]

I'm super excited to share that I have joined @MIT_CSAIL and @BroadInstitute as a postdoctoral researcher in the Computational Biology Group!

[Azim Dehghani Amirabad @Azim30153364]

Super cool indeed! Expect more multimodal foundational models for biology soon! 🚀

#biotechnology #Genomics
Sequence modeling and design from molecular to genome scale with Evo https://t.co/ZZw69ktTok

[Felix Teufel @felixgteufel]

How well do🧬 DNA LMs perform on prediction tasks that are biologically relevant, are naturally very imbalanced and require reasoning over long contexts? We present BEND, a benchmark for DNA LMs on the human genome
https://t.co/VTHS2OeyDT

[Bo Wang @BoWang87]

Interested in LLMs for genomic research but don't know where to start? looking for a review/survey to get started in this field? 👇👇😀

I am very excited to share that our review paper titled "To Transformers and Beyond: Large Language Models for the Genome" is now available as a preprint (https://t.co/U24TUSseNr)! Our review unveils a revolution in genomics analysis with Genome LLMs. 🧬

🔍 What's Inside:
✅ The power & challenges of transformers in genomics.

✅ Cutting-edge models like HeynaDNA and scGPT & their impact.

✅ Deep dives into Enformer, DNABERT, and other Genome LLMs.

🌍 Why it Matters:
1. GPT-4's influence reshapes AI in genomics.
Unmatched insights into transformers' role in genomics.

2. Critical analysis of new models, addressing interpretability, privacy, & computational needs.

3. Essential for computational biologists & computer scientists to navigate the future of genomic data analysis.

This is a work led by the amazing PhD student, Mica Consens, in the lab! Also, a huge collaborative work with lots of field leaders @fabian_theis @genophoria @MKarimzade @michaelwainberg and Alan Moses!

@UofT @VectorInst @UofTCompSci @UofT_LMP @UHN @pmcc_ai @UHNAIHUB

[Kathleen Keough @keoughkath]

The question of what makes us human remains enigmatic, but we investigate how enhancer hijacking, or fondly, "HARjacking", may have played a role in human-specific genome evolution in our study now out in @ScienceMagazine ! https://t.co/abm1c7LdAO

[Santiago @svpino]

11 ways ChatGPT saves me hours of work every day, and why you'll never outcompete those who use AI effectively.

A list for those who write code:

1 of 16

[Sushmita Roy @sroyyors.bsky.social,genomic.social @sroyyors]

really nice review by @fabian_theis group on thinking about predicting the impact of perturbations and the promise of single cell omics and ML for this: https://t.co/VUgAXhkeN7 Also comes with a nice GitHub page of resources.

[Nature Biomedical Engineering @natBME]

Graph neural networks and transformers taking advantage of contextual information and large unannotated multimodal datasets are redefining what is possible in computational medicine.

https://t.co/nvxxkAPHvf

[elvis @omarsar0]

2022: A Year in Review (ML Papers Edition)

In this thread, let's take a look at some of the top trending ML papers of 2022 ↓

[Scott Tyler (@[email protected]) @ScienceScottT]

Doing #SingleCell #RNAseq? Ever wonder if all those clusters are real? Turns out most feature selection & clustering pipelines can't tell when there's only 1 cluster! But I found a solution! 🧵👇

[Zain Kahn @heykahn]

AI is going to permanently change how marketing works.

If you're not paying attention, you're going to be out of a job pretty soon.

I played around with ChatGPT (a new AI tool) recently.

Here's how AI will change marketing forever:

[Azim Dehghani Amirabad @Azim30153364]

Market landscape of generative AI.

Generative AI: A Creative New World https://t.co/PAopyhXpZF

[Azim Dehghani Amirabad @Azim30153364]

On my way to #NeurIPS2022 , excited to see talks and posters on AI in biomedicine.

[Azim Dehghani Amirabad @Azim30153364]

@Mahmoudreza_B @kgummadi @nekozzang @autreche @adishs @IValeraM @Max_Planck_CHM @iyadrahwan @JFBonnefon Congrats @Mahmoudreza_B !

[Ibrahim I. Taskiran @ibrahimihsan]

Our work on the interpretation of allele-specific chromatin accessibility using cell state-aware deep learning is online in advance @genomeresearch!
Wonderful joint work with @kalender_atak in the @steinaerts lab.
Link to paper: https://t.co/wBsGLyIhMg
(1/8)

[Broad Institute @broadinstitute]

We are thrilled to announce the launch of the Eric and Wendy #SchmidtCenter. Merging biology and machine learning to understand the programs of life, the Center will enable a new field of interdisciplinary research aimed at improving human health.
https://t.co/CuPENZPDzQ

[R Function A Day @rfunctionaday]

It can be a daunting task to construct regular expressions, especially complex ones.

The {rx_} function family from {RVerbalExpressions} 📦 makes this more accessible by allowing one to construct regex using verbal expressions 🔡

https://t.co/5G77171gYA

#rstats #DataScience

[Pardis Sabeti @PardisSabeti]

Making music with @1000daysband and listening to others' music has been my fuel for many outbreaks. Here is our latest tune afer an exceptionally hard year for so many. This is for you -- Don't Count Me Out https://t.co/0cz5U5mkgj

[Jesse Engreitz @jengreitz]

How do human promoters sense genomic context to control gene expression?

Exciting study from @BarakACohen integrating hundreds of promoters into different loci

Promoters are broadly compatible with activation in different contexts

https://t.co/K4rOgtVVmg

[Azim Dehghani Amirabad @Azim30153364]

A very interesting idea!
Discovering single nucleotide variants and indels from bulk and single-cell ATAC-seq https://t.co/6EXakBL5Vt

[William J. Greenleaf @WJGreenleaf]

Our paper describing ArchR, a single cell analysis platform designed for scalable analysis of open chromatin data, is out in Nature Genetics. Congrats to Jeff and Ryan!
https://t.co/818T6S3ff5