Ilia Igashov

PhD student at LPDI, EPFL 🇨🇭 Artificial Intelligence & Structural Biology

[Ilia Igashov @igashov]

🚨 Check out DrugFlow, our new generative model for structure-based drug design. DrugFlow provides an atom-level confidence score for each designed molecule, and can adjust molecular size on the fly!

Additional details in thread 🧵

#ICLR2025

[Arne Schneuing @rneschneuing]

The code & camera-ready version of our #ICLR2025 paper on "Multi-domain Distribution Learning for De Novo Drug Design" are now available

📚 Paper: https://t.co/NCeHVltqm8

💻 Code: https://t.co/0GGMiOODla

(1/4)

[Rebecca Neeser @RebeccaNeeser]

We’re excited to announce the speakers for “AI & the Molecular World” at #AMLD2026 in Lausanne 🇨🇭 on Feb 10! 🧬🤖
The track explores generative modelling, new molecular representations, and more across scales from small molecules to proteins.
See below 👇

[Max Welling @wellingmax]

I am proud to announce that today @cusp_ai has closed a $100M Series A fundraise, co-led by @NEA and @Temasek, with participation from @nvidia’s NVentures, @SamsungVentures and @Hyundai_Worldwide.

[Martin Pacesa @MartinPacesa]

Exciting to see our protein binder design pipeline BindCraft published in its final form in @Nature ! This has been an amazing collaborative effort with Lennart, @csche11h, @sokrypton, @befcorreia and many other amazing lab members and collaborators.

https://t.co/PTMoqQqwcU

[Martin Pacesa @MartinPacesa]

I am super excited to announce that I will be starting my lab at the Department of Pharmacology of the University of Zurich in Switzerland next year!

[Science Magazine @ScienceMagazine]

New research in Science greatly expands the potential target scope of molecular glues and should stimulate the development of new small molecules that can selectively target therapeutically relevant proteins for degradation.

Learn more in this week's issue: https://t.co/t9bwqHLkOz

[Western Bioinformatics @WesternBioinfo1]

Join us for the Western Bioinformatics Seminar on Thursday, May 22, 2025, from 11:00 AM to 12:00PM ET. Scan the QR code to access the Zoom link.
@igashov,@WesternU, @SchulichMedDent, @westernuBiochem, @WesternU_CTCR, @westernuScience, @westernuepibio, @befcorreia, @mmbronstein

[Adrian Dobbelstein @AdrDobbel]

Just returned from an inspiring week at #ICLR2025 in Singapore!​ I presented two posters (DrugFlow and LDDM) together with @igashov & @rneschneuing.
I am very grateful for the engaging discussions and feedback. Looking forward to continued collaborations and future conferences!

[Ricky T. Q. Chen @RickyTQChen]

This ICLR is the best conference ever. Attendees are extremely friendly and cuddly.
..What do you mean this is the wrong hall?

[Arne Schneuing @rneschneuing]

You'll find us at the SynFlowNet poster today between 10:00 and 12:30 in Hall 3 + 2B (poster #15)

#ICLR2025

[Rebecca Neeser @RebeccaNeeser]

Hello from Singapore 🇸🇬! Thrilled to be at #ICLR2025 presenting our work on fragment-based drug discovery 🧩. We go beyond virtual screening with a generative, structure-aware approach.
📃 https://t.co/rH6SkSCPIY
🔗 https://t.co/H8BTPGLZp8
A thread 🧵👇

[Arne Schneuing @rneschneuing]

We'll be presenting the poster tomorrow (Thu 24/04) at 10am #ICLR2025. Please come and say hi :)
https://t.co/PjfLcPZh8J

@igashov @AdrDobbel

[Ilia Igashov @igashov]

Excited to be at #ICLR2025 and happy to chat about ML and drug discovery! 🇸🇬
Come find me at one of our posters or feel free to reach out directly!

1. DrugFlow: #9 Thu 24/04 10am
2. SynFlowNet: #15 Fri 25/04 10am
3. LDDM: @gembioworkshop 27/04
4. LatentFrag: #AI4MAT 28/04

[Damiano Sgarbossa @damiano_sga]

📢 Our new preprint is out on bioRxiv! We introduce RAG-ESM, a retrieval-augmented framework that improves pretrained protein language models like ESM2 by making them homology-aware with minimal additional training costs.
💻 https://t.co/Ka0nqpHmyo
🔗 https://t.co/flmXpvytvg

1/7

[Institut de Biologie Structurale @IBS_Grenoble]

#IBSevents: Friday 28/03 at 11am, seminar by @igashov @EPFL, entitled 'Generative drug design : the next paradigm shift in therapeutic development?': https://t.co/lvlsOlNrPR
#DrugDesign

[Ilia Igashov @igashov]

While DrugFlow is really good in distribution learning, we also show that it can be easily tuned to generate molecules with optimised target properties. For example, we can boost docking efficiency and synthetic accessibility, or reduce the level of swill in samples @wpwalters

[Ilia Igashov @igashov]

🚨 Check out DrugFlow, our new generative model for structure-based drug design. DrugFlow provides an atom-level confidence score for each designed molecule, and can adjust molecular size on the fly!

Additional details in thread 🧵

#ICLR2025

[Arne Schneuing @rneschneuing]

The code & camera-ready version of our #ICLR2025 paper on "Multi-domain Distribution Learning for De Novo Drug Design" are now available

📚 Paper: https://t.co/NCeHVltqm8

💻 Code: https://t.co/0GGMiOODla

(1/4)

[Ilia Igashov @igashov]

Our adaptive size mechanism allows DrugFlow to remove excessive atoms on the fly, adjusting the molecular size to the provided pocket constraints. In our experiments, we demonstrate that DrugFlow can avoid steric clashes if the provided molecular size is too big.

[Chaitanya K. Joshi @chaitjo]

Introducing All-atom Diffusion Transformers

— towards Foundation Models for generative chemistry, from my internship with the FAIR Chemistry team @OpenCatalyst @AIatMeta

There are a couple ML ideas which I think are new and exciting in here 👇

[Ilia Igashov @igashov]

(2/2) SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraints https://t.co/uhtjfuujVu

[Ilia Igashov @igashov]

Really excited: 2/2 our papers got accepted to @iclr_conf! Thanks to all amazing co-authors and hope to see you in Singapore! 🇸🇬

If you're interested in generative models and RL agents for drug design check our papers in the thread 🧵

[Ilia Igashov @igashov]

(1/2) Multi-domain Distribution Learning for De Novo Drug Design https://t.co/2wERDumL0Q