Leo Zang
@LeoTZ03
Followers
3K
Following
2K
Statuses
1K
Protein Designer | Share Reading Notes (AI+Protein/RNA/DNA) | @harvardmed @DeboraMarksLab | Hosting @ml4proteins
Boston, MA
Joined March 2024
RT @owl_posting: How do you make a 250x better vaccine at 1/10 the cost? Develop it in India. (Soham Sankaran, Ep #2) There's a lot of di…
0
22
0
RT @bartoszcyw: 🔥 New Paper! How can sparse autoencoders (SAEs) applied to diffusion models help us solve real-world challenges? 🚀 Introd…
0
47
0
🤔
BREAKING NEWS ( Columbia University proposes cutting incoming PhD cohorts in the Graduate School of Arts and Sciences by up to 65%, according to faculty sources.
0
0
0
The initial work was finished during 2022-23. Happy to see that generated peptides have been successfully tested in mice
As you can probably tell from our work, we're now all in on diffusion and flow matching models for protein/peptide sequence generation! 🌟 These models are just way better for tightly controlling generation (vs. say autoregressive models, which we've found are poorly set up for biological tasks). As such, while, we have recently moved to discrete diffusion architectures to operate purely in sequence-space (i.e. PepTune, MeMDLM, etc.), you may remember that we got our start early in 2024 by doing continuous diffusion on pLM latents with our AMP-Diffusion paper ( to generate antimicrobial peptides! 🦠 It was beautiful work by my (now graduated!) Masters student, @LeoTZ03! 🎓 AMP-Diffusion was the first example of performing latent diffusion for protein/peptide sequence generation, and we got pretty good quality peptides with AMP-like sequence composition and physicochemical properties and strong predicted inhibitory potential! While we saw this as proving to ourselves that diffusion could work (we are definitely convinced!), we didn't think to go much further. 🙃 I then met @delafuentelab (who specializes at screening AMPs!) at @pennbioeng who offered to experimentally test out our peptides! 🤗 Through a really fun collaboration over the past year with, they've shown that AMP-Diffusion-generated AMPs demonstrate bacterial killing in vitro, and the peptides showed favorable physicochemical profiles. 🦠 In preclinical mouse models of infection, our lead peptides reduced bacterial burdens, and showed really strong efficacy comparable to polymyxin B and levofloxacin, with no detectable adverse effects! 🐁 Take a read of our collaborative preprint, where we describe these exciting results!! 🙌 I hope our work convinces you that diffusion for protein/peptide sequence generation can have meaningful translational impact! ⚕️ 📜:
2
1
38
RT @BrandesNadav: New preprint claims that most existing DNA language models perform just as well with random weights, suggesting that pret…
0
65
0
RT @JonasKoeppel: I’m delighted to share our work on scrambling the human genome using prime editing, repetitive elements, and recombinases…
0
86
0
RT @SchmidhuberAI: DeepSeek [1] uses elements of the 2015 reinforcement learning prompt engineer [2] and its 2018 refinement [3] which coll…
0
842
0
RT @CRISPR_LuCas: 📢Excited to introduce NanoCas -our new mini CRISPR system that can reach tissues previously out of reach! By shrinking…
0
392
0
RT @Patrick18287926: We are going through applications as they come in - apply now! We will expand the wet lab work significantly with this…
0
14
0
Protein-Based Degraders: From Chemical Biology Tools to Neo-Therapeutics | @ACSChemRev - "we provide a comprehensive and critical review of studies that have used proteins and peptides to mediate the degradation and hence the functional control of otherwise challenging disease-relevant protein targets. We describe existing platforms for protein/peptide-based ligand identification and the drug delivery systems that might be exploited for the delivery of biologic-based degraders." Link:
0
4
40
Ligand interaction landscape of transcription factors and essential enzymes in E. coli Antibody Library Design by Seeding Linear Programming with Inverse Folding and Protein Language Models Structure-guided discovery of viral proteins that inhibit host immunity Rational multienzyme architecture design with iMARS Deep learning enhances the prediction of HLA class I-presented CD8+ T cell epitopes in foreign pathogens A unified cross-attention model for predicting antigen binding specificity to both HLA and TCR molecules deepNGS Navigator: Exploring antibody NGS datasets using deep contrastive learning Combining Directed Evolution with Machine Learning Enables Accurate Genotype-to-Phenotype Predictions
Collection of Papers and Posts
0
8
31
Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Review - "We review these methods from a unified perspective, demonstrating that current techniques -- such as Sequential Monte Carlo (SMC)-based guidance, value-based sampling, and classifier guidance -- aim to approximate soft optimal denoising processes (a.k.a. policies in RL) that combine pre-trained denoising processes with value functions serving as look-ahead functions that predict from intermediate states to terminal rewards. "
1
1
19
RT @chaitjo: Excited about co-organising the first ** AI for Nucleic Acids Workshop ** at ICLR 2025 in Singapore! @ai4na_workshop We have…
0
8
0
Join us at 4!
Next Tuesday, 1/21 @ 4 pm EST, @ElanaPearl will present "InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders" Paper: Sign up on our website to receive Zoom links!
0
0
3