Dov Gertz (@dovgertz) 's Twitter Profile
Dov Gertz

@dovgertz

CEO & Co-Founder of @Converge_Bio. Training LLMs on DNA, RNA, and Protein sequences and using them to design better medications.

ID: 887605571540709378

calendar_today19-07-2017 09:30:33

24 Tweet

46 Followers

343 Following

Burstein lab (@bursteinlab) 's Twitter Profile Photo

Can we "read" microbial genomes using language models? We explore this idea in our paper "Deciphering microbial gene function using natural language processing" nature.com/articles/s4146โ€ฆ ๐Ÿงต

Bruria Samuel (@bruriasamuel) 's Twitter Profile Photo

Meet The Shielded Plasmid๐Ÿ›ก๏ธ๐Ÿงฌ Our new nature paper reveals how plasmids outsmart bacterial defenses during conjugation. It's all about being in the right place at the right time! The positioning of anti-defense genes boosts transfer efficiency๐Ÿงต(1/7) nature.com/articles/s4158โ€ฆ

Meet The Shielded Plasmid๐Ÿ›ก๏ธ๐Ÿงฌ

Our new <a href="/Nature/">nature</a> paper reveals how plasmids outsmart bacterial defenses during conjugation.

It's all about being in the right place at the right time! The positioning of anti-defense genes boosts transfer efficiency๐Ÿงต(1/7) nature.com/articles/s4158โ€ฆ
Shahar Tzafrir (@shahartzafrir) 's Twitter Profile Photo

ืžืžืฉ ืฉืžื— ืœื”ืฆื˜ืจืฃ ืœืงื•ื•ื ื•ืจื’'-ื‘ื™ื• ื‘ืกื‘ื‘ ื”ืกื™ื“ ืฉืœื”ื. ืขื•ื“ ืขืœ ืžื” ื”ื ืขื•ืฉื™ื ื‘ื˜ืงืจื ืฆ'. ื™ืฉ ืœื”ื ื›ื‘ืจ ืฆื•ื•ืช ืคืกื™ื›ื™, ื•ื”ื ืžื—ืคืฉื™ื ืขื•ื“. ื—ื™ื‘ื•ืจ ืžืจืชืง ืฉืœ ื‘ื™ื• ื•-AI ืขื ืื ืฉื™ื ืžื•ืคืœืื™ื, ื ื—ืžื“ื™ื, ื•ื—ื“ื•ืจื™ ืžื˜ืจื” ๐ŸŽฏ. Converge Bio Dov Gertz #ืคื™ื“ื˜ืง

Greg Brockman (@gdb) 's Twitter Profile Photo

During my sabbatical, one project I really enjoyed was training DNA foundation models with the team at Arc Institute. I've long believed that deep learning should unlock unprecedented improvements in medicine and healthcare โ€” not just for humans but for animals too. I think this

During my sabbatical, one project I really enjoyed was training DNA foundation models with the team at <a href="/arcinstitute/">Arc Institute</a>.

I've long believed that deep learning should unlock unprecedented improvements in medicine and healthcare โ€” not just for humans but for animals too. I think this
Or Azulay (@orslimy) 's Twitter Profile Photo

ื”ื™ื™ ื›ื•ืœื! ื‘ื™ื•ื ืฉืœื™ืฉื™ ื”ืงืจื•ื‘ ืืืจื— ื‘ืกืคื™ื™ืก ืืช Dov Gertz, ื”ืžื™ื™ืกื“ ื•ื”ืžื ื›ืœ ืฉืœ Converge Bio, ื•ื ืฉื•ื—ื— ืขืœ ื”ืžืกืข ืฉืœื• ื‘ืชืขืฉื™ื” ื•ืขืœ ืคืœื˜ืคื•ืจืžืช ื”GenAI ืฉื”ื ื‘ื•ื ื™ื ืฉืžื ื’ื™ืฉื” LLMs ืœื“ืื˜ื”-ืกื˜ื™ื ื‘ื™ื•ืœื•ื’ื™ื™ื ืขื‘ื•ืจ ื”ืืฆืช ืžื—ืงืจ ื•ืคื™ืชื•ื— ืฉืœ ืชืจื•ืคื•ืช. ื‘ื•ืื• :) ืœืกืคื™ื™ืก: x.com/i/spaces/1BdxYโ€ฆ

ื”ื™ื™ ื›ื•ืœื! ื‘ื™ื•ื ืฉืœื™ืฉื™ ื”ืงืจื•ื‘ ืืืจื— ื‘ืกืคื™ื™ืก ืืช <a href="/DovGertz/">Dov Gertz</a>, ื”ืžื™ื™ืกื“ ื•ื”ืžื ื›ืœ ืฉืœ Converge Bio, ื•ื ืฉื•ื—ื— ืขืœ ื”ืžืกืข ืฉืœื• ื‘ืชืขืฉื™ื” ื•ืขืœ ืคืœื˜ืคื•ืจืžืช ื”GenAI ืฉื”ื ื‘ื•ื ื™ื ืฉืžื ื’ื™ืฉื” LLMs ืœื“ืื˜ื”-ืกื˜ื™ื ื‘ื™ื•ืœื•ื’ื™ื™ื ืขื‘ื•ืจ ื”ืืฆืช ืžื—ืงืจ ื•ืคื™ืชื•ื— ืฉืœ ืชืจื•ืคื•ืช. ื‘ื•ืื• :) 

ืœืกืคื™ื™ืก: x.com/i/spaces/1BdxYโ€ฆ
Or Azulay (@orslimy) 's Twitter Profile Photo

ืœืžื™ ืฉืคืกืคืก ืืช ื”ืกืคื™ื™ืก ืืžืฉ, ืฉื•ื—ื—ืชื™ ืขื Dov Gertz ืขืœ: - ื”ืฉื ื™ื ื‘ืืงื“ืžื™ื” ื•ื”ืžื—ืงืจ ืฉืœื• ืกื‘ื™ื‘ ืžื ื’ื ื•ื ื™ CRISPR (ื›ื•ืœืœ ืžื” ื–ื” ื‘ื›ืœืœ?) - ืกื™ืคื•ืจ ื”ื”ืงืžื” ืฉืœ Converge Bio ื•ืื™ื–ื• ื‘ืขื™ื” ื›ื•ืื‘ืช ื”ื ืคื•ืชืจื™ื ื‘ืขื•ืœืžื•ืช ื”ื’ื ื˜ื™ืงื” ื‘ืขื–ืจืช GenAI? - ืœืžื” ื”ื•ื ืื’ื ื•ืกื˜ื™ ืœื•ืจื˜ื™ืงืœ ืฉื”ื ืคื•ืขืœื™ื ื‘ื•? (ืชืจื•ืคื•ืช, ืื’ืจื•ื˜ืง, ื‘ื™ื•ื˜ืง ื•ื›ื•ืณ). -

OdedK (@oded_k) 's Twitter Profile Photo

At Converge Bio we are building AI-powered solutions across the entire drug life cycle, from R&D to production, such as binder design, transcript optimization target discovery, and drug MoC with RNA single-cell sequencing

OdedK (@oded_k) 's Twitter Profile Photo

FDA shifts from animal testing for mAbs & drugs! New roadmap embraces AI models & human-based NAMs for safety. Huge step for ethics & faster dev! But what if GenAI could generate antibodies too, not just test them? Combine FDA's move + AI design = skip animal use entirely!

OdedK (@oded_k) 's Twitter Profile Photo

Converge Bio uses #GenerativeAI for de novo & guided antibody generation, optimizing binding, developability & specificity. We're building the future of ethical, efficient antibody discovery. Wondering how to leverage this for your org? Let's talk! Reach out to us. #Pharma

Dov Gertz (@dovgertz) 's Twitter Profile Photo

๐ŸŽ™๏ธ Excited to share my recent conversation with Ben from Ben | The SaaS CFO on his podcast! We dive into the future of biotech and our work at Converge Bio . Tune in here: ๐Ÿ Apple Podcasts:podcasts.apple.com/us/podcast/conโ€ฆ ๐ŸŽง Spotify: open.spotify.com/episode/75wtySโ€ฆ

๐ŸŽ™๏ธ Excited to share my recent conversation with Ben from <a href="/TheSaaSCFO/">Ben | The SaaS CFO</a>   on his podcast! We dive into the future of biotech and our work at <a href="/Converge_Bio/">Converge Bio</a> .

Tune in here:
 ๐Ÿ Apple Podcasts:podcasts.apple.com/us/podcast/conโ€ฆ
 ๐ŸŽง Spotify: open.spotify.com/episode/75wtySโ€ฆ
OdedK (@oded_k) 's Twitter Profile Photo

I'll be heading out today to showcase Converge Bio at #biotools. Looking forward to connecting with judges, investors, and fellow entrepreneurs. See you there! #BTIRoadTour2025 #StartupPitch #StartupInnovation #Innovation #LifeSciences

I'll be heading out today to showcase <a href="/Converge_Bio/">Converge Bio</a> at #biotools.
Looking forward to connecting with judges, investors, and fellow entrepreneurs. See you there!
#BTIRoadTour2025 #StartupPitch #StartupInnovation #Innovation #LifeSciences
OdedK (@oded_k) 's Twitter Profile Photo

I refuse to mix Shakespeare with amino acids. โ€œChattyโ€ bioโ€‘LLMs waste model weights on English tokens or bolt giant chat heads onto protein models. Use lean tools like ESMโ€‘2 for folds and ProtGPTโ€‘2 for design, then add a tiny LLM to use the output. Stop paying for bloated prose.

I refuse to mix Shakespeare with amino acids. โ€œChattyโ€ bioโ€‘LLMs waste model weights on English tokens or bolt giant chat heads onto protein models. Use lean tools like ESMโ€‘2 for folds and ProtGPTโ€‘2 for design, then add a tiny LLM to use the output. Stop paying for bloated prose.