←
Debesh Mandal3,059 posts
Debesh Mandal avatar

Debesh Mandal

@debesh

Co-founder and CEO @nanograb (YC S23)

◷ Joined January 2012▧ 98 Photos and videos
Debesh Mandal avatar
Debesh Mandal@debesh·Oct 22

mRNA will be crucial to beating cancer and solving disease but only if we can deliver it to the right cells. Nanograb's AI-designed multivalent nanoparticles address a cell's unique receptor fingerprint, now proven in vivo across multiple cell types and scaling to many more.

1:38
Debesh Mandal avatar
Debesh Mandal@debesh·6h

Multivalent superselectivity is just the tip of the iceberg when it comes to designing targeted LNPs but it's an area of biophysics we are extremely excited about. Read the full piece and subscribe! superselectivity.substack.co…

Debesh Mandal avatar
Debesh Mandal@debesh·6h

When @nanograb designs peptides for delivering mRNA via targeted LNPs, we tune for the amounts of a given receptor on a cell, not just its presence. Multivalent superselectivity helps us achieve this level of targeting. Read more in our new substack! (link below)

0:22
Ned O'Leary avatar
⟳ Debesh Mandal retweeted
Ned O'Leary@nedoleary·21h

every once in a while, a company actually has a useful update that I'd like to know about, but things have been way too messy / low value in the email channel for a long time it would be useful to have a new version of the marketing newsletter / changelog / RSS feed for agents I set my AI thing to subscribe to your feed, and it decides what gets through to me / whether your information is high-quality enough to justify continued subscription would use extensively

Xinchen Wang avatar
⟳ Debesh Mandal retweeted
Xinchen Wang@xinchen_w·Nov 16

It’s getting popular to build autonomous labs to scale up biological data generation 24/7, but focusing automation on well-established in vitro assays with existing hardware risks solving the easiest least painful step, rather than the problems that matter the most for drug discovery. One analogy is like generating decades of closed-course driving data with hopes of training self-driving cars that can navigate Manhattan. I think the most valuable data from autonomous labs will come at the intersection of novel assay technologies with valuable samples - often complex animal models, organoids, primary tissue, not immortalized cancer cell lines. Not that more complexity in the assay/model system is always better, but scaling existing assays 1000x won’t overcome the fundamental limits of what they can measure. Training AI models to find drugs that existing approaches have failed to discover will probably require generating types of data that existing technologies cannot generate. Teams building the next generation of autonomous labs need to have the skillsets to (i) invent new & uniquely valuable assay technologies & (ii) invent the custom hardware to automate them.

Debesh Mandal avatar
Debesh Mandal@debesh·Nov 14

Because it's a single crystal, the blade doesn't "creep" over time at high temps. If a trad alloy was used then the blade would slowly extend over time at high temps and smash through the inside of the engine

Debesh Mandal avatar
Debesh Mandal@debesh·Nov 14

One of the coolest things in my University department was a real jet engine blade, a single crystal of nickel-based superalloy.

The gas inside a jet engine can be hotter than the melting point of its blades. Why don’t they melt?

0:39
Debesh Mandal avatar
Debesh Mandal@debesh·Nov 13

Post attachment

🙄 US is not 80% of the furniture market. We are 80% of the drug market, these comparisons aren’t relevant. No other private industry is like drugs because drug pricing is so skewed to the US market. USG controls this industry so they can get drugs developed wherever they want.

Debesh Mandal avatar
Debesh Mandal@debesh·Nov 13

Isn’t this the Ibiza final boss video?

🚨😜In this video, Nvidia CEO Jensen Huang and Nvidia VP Kimberly Powell are seen dancing in a very fun manner. Some people say that Kimberly Powell got pregnant on this day in the bedroom. @Grok Confirm it

0:08
Debesh Mandal avatar
Debesh Mandal@debesh·Nov 12

CROs literally the most obvious industry to make better, complete no brainer

ditto. many biotechs complain about time and data quality. the fact that the founders themselves don't have years of experience at CROs doesn't mean they can't hire scientists that do. execution is not a moat. the field almost univocally agrees there's need for more data. existing CROs don't seem to have the capacity to serve the entire market.

Debesh Mandal avatar
Debesh Mandal@debesh·Nov 11

Awesome founders working to solve medicine’s most important mission

Today we are launching @BioDelivera a programmable drug delivery platform that delivers therapies only to diseased cells enabling cures for every disease. 🎯🧪 Less than 3% of an injected therapy reaches diseased cells. The rest ends up in healthy organs. At @BioDelivera we want to change that, our mission is to make every therapy accessible to patients. Happy to build with @ikeda_trashi this exciting technology! Reach out at founders@biodelivera.com

2:13
Luca Springer avatar
⟳ Debesh Mandal retweeted
Luca Springer@luca_springer·Nov 10

Building @numenbio with @_tom_dot_com to engineer a future without cancer deaths. Find out more below in an interview with our partners at @TQVentures!

A cancer test that runs inside a cup. Taken at home, with results sent to your doctor in 30 minutes. Built in a San Francisco lab by a team that started in a shipping container. What it actually takes to build it: “If we spend ten, 20, 30, 40 years working on this, that’s okay. The outcome will be worth it.” @luca_springer, co-founder and CEO of @numenbio Timestamps: 00:00 Welcome to Numen 00:56 Why catch cancer early 01:24 The first lab was a shipping container 02:28 What the data unlocks next 03:23 National team MVP to founder 04:13 Why bladder cancer first 05:33 The candle prototype 06:25 Meet Atlas, a lab in a cup 06:55 NASA engineers under one roof 07:32 The Viennese café 08:08 Pipette pong 08:46 From the dungeon to Golden Gate Park 09:28 The only milestone that matters 09:59 40 years on one problem

10:40
Debesh Mandal avatar
Debesh Mandal@debesh·Nov 5

Wonder how it fares in multiplayer Catan when everyone teams up against it and refuses to trade.

We're excited to unveil VINCO, our frontier AI model trained to play and win 1v1 Catan. We've secretly deployed it on the Colonist.io global leaderboard, where it has reached both the #1 and #2 positions, consistently beating every human world champion.

1:24