Hamed Khakzad
@hamed_khakzad
Followers
299
Following
2K
Media
1
Statuses
214
Junior Professor @INRIA | PhD @UZH_en, postdoc @EPFL | Protein design | Mass Spectrometry | Deep Learning
Nancy, France
Joined November 2018
De novo design of phosphorylation-induced protein switches for synthetic signaling in cells 1. Researchers have developed a method to design synthetic proteins that can switch states in response to phosphorylation, mimicking natural cellular signaling mechanisms. This
2
27
119
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
19
167
721
🚨 Postdoc Opening 🚨 Fully funded 2-year position @Inria (Nancy, 🇫🇷) to study allosteric signaling 🧬 with graph neural networks + molecular dynamics. High-risk/high-reward project (PIQ grant). Apply 👉 https://t.co/zOuqyDJEBr
#PostdocJob #DeepLearning #MolecularDynamic
0
3
3
We were invited to write a preview about SHAPES, a great recent work from @PossuHuangLab. I really enjoyed this paper! It shows how far we still are from sampling the protein structural space without bias. Our preview just came out, check it out here: https://t.co/Pyy0AFpeI2
0
4
18
DynaRepo: The repository of macromolecular conformational dynamics 1. DynaRepo is a novel repository that addresses the critical gap in studying the dynamic behavior of macromolecules, which is essential for understanding interactions like antibody–antigen recognition and
0
31
109
Of 1,481 Iranian casualties from Israeli attacks, 90% are civilians, not military personnel. So far, 244 children, women, and men have been killed in Iran by these attacks, according to the Iranian Ministry of Health. This brutal attack must end immediately. #CeasefireNow
نتیجه تاسفبار این شعار دروغین که «دولت اسرائیل کاری به ملت ایران ندارد و اهداف فقط نظامی است!» بعد از گذشت ۶۵ ساعت از تجاوز رژیم صهیونی، بستری تعداد ۱۴۸۱ مصدوم و شهید است که ۱۲۷۷ نفر در بیمارستانهای دانشگاهی کشور بستری شده و بیش از ۹۰ درصد غیر نظامی! از این تعداد ۵۲۲ نفر ترخیص
28
262
1K
امیدوارم که خانواده هاتون سالم باشن، چشمهامون اشک آلوده برای ایران، برای کودکان و ادم های بیگناه که به خاک و خون کشیده شدن. برای همه دانشجویان ایرانی در زمینه هوش مصنوعی و بیوانفرماتیک و زیست شناسی محاسباتی که دچار مشکل شدن برای ادامه تحصیل یا تحقیقاتشون، به من ایمیل بزننین برای
2
15
88
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
1
13
95
Next Tues (4/1) at **11AM** ET we will have Anthony Marchand present "Targeting protein–ligand neosurfaces with a generalizable deep learning tool" Paper: https://t.co/Tj1eXnSc4N Sign up on our website for zoom links!
nature.com
Nature - A computational deep learning approach is used to design synthetic proteins that target the neosurfaces formed by protein–ligand interactions, with applications in the development of...
0
6
36
DynamicGT: a dynamic-aware geometric transformer model to predict protein binding interfaces in flexible and disordered regions 1. The paper introduces DynamicGT, a geometric transformer-based model designed to predict protein binding sites by incorporating conformational
0
6
16
🚨 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
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)
4
40
217
This was a nice collaboration with @grudinin and @yasaman_karami, supported by @AgenceRecherche. Many thanks to @Genci_fr for the computational resources.
0
0
1
We generated in total, 1ms MD simulations to train the model. Here, atoms can broadcast and/or listen to messages (left) considering cooperation between core and surface atoms, leading to final interface prediction (right).
1
1
10
Happy to share the first PhD work from our team developed by @A_mister_omid. We introduce DynamicGT, a dynamic-aware cooperative graph transformer to predict binding interfaces in flexible and disordered regions.
biorxiv.org
Protein-protein interactions are fundamental to cellular processes, yet existing deep learning approaches for binding site prediction often rely on static structures, limiting their performance when...
1
1
8
I think Elon Musk should be expelled from the British Royal Society. Not because he peddles conspiracy theories and makes Nazi salutes, but because of the huge damage he is doing to scientific institutions in the US. Now let's see if he really believes in free speech.
2K
3K
24K
Enhancing Protein Graph Representations through Static-Dynamic Fusion 1/ This study introduces a novel approach that combines static structural information with dynamic motion data derived from molecular dynamics simulations, improving protein modeling and property prediction.
0
16
94
Join my team! Please, tweet it. #AI #MachineLearningandAI #Artificialintelligence #MachineLearning #proteins #enzymes
0
6
11
Computationally designed stem-epitope mimetics elicit broadly reactive antibodies 1. The study introduces a novel approach to vaccine design, focusing on computationally engineered stem-epitope mimetics that aim to elicit broadly neutralizing antibodies (bnAbs) against the
0
22
76
Targeting protein–ligand neosurfaces with a generalizable deep learning tool @Nature 1. This study introduces MaSIF-neosurf, a novel deep learning framework for designing proteins that target neosurfaces—protein-ligand interfaces—using geometric deep learning and molecular
1
50
177
@EPFL_en @novonordisk @Inria_Nancy A quick update on this! The server is now available and you have free access to all the data. Please let me know if you’re interested in a particular case, so, we can provide more details.
0
0
1