Protein design with guided discrete diffusion
A popular approach to protein design is to combine a generative model with a discriminative
model for conditional sampling. The generative model samples plausible sequences while …
model for conditional sampling. The generative model samples plausible sequences while …
<? sty\usepackage {wasysym}?> Bilingual language model for protein sequence and structure
M Heinzinger, K Weissenow… - NAR Genomics and …, 2024 - academic.oup.com
Adapting language models to protein sequences spawned the development of powerful
protein language models (pLMs). Concurrently, AlphaFold2 broke through in protein …
protein language models (pLMs). Concurrently, AlphaFold2 broke through in protein …
[HTML][HTML] Deep generative models for detector signature simulation: A taxonomic review
B Hashemi, C Krause - Reviews in Physics, 2024 - Elsevier
In modern collider experiments, the quest to explore fundamental interactions between
elementary particles has reached unparalleled levels of precision. Signatures from particle …
elementary particles has reached unparalleled levels of precision. Signatures from particle …
Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
B Hashemi, C Krause - arxiv preprint arxiv:2312.09597, 2023 - arxiv.org
In modern collider experiments, the quest to explore fundamental interactions between
elementary particles has reached unparalleled levels of precision. Signatures from particle …
elementary particles has reached unparalleled levels of precision. Signatures from particle …
Improving protein optimization with smoothed fitness landscapes
The ability to engineer novel proteins with higher fitness for a desired property would be
revolutionary for biotechnology and medicine. Modeling the combinatorially large space of …
revolutionary for biotechnology and medicine. Modeling the combinatorially large space of …
LLMs are highly-constrained biophysical sequence optimizers
Large language models (LLMs) have recently shown significant potential in various
biological tasks such as protein engineering and molecule design. These tasks typically …
biological tasks such as protein engineering and molecule design. These tasks typically …
Optimizing protein fitness using Gibbs sampling with Graph-based Smoothing
The ability to design novel proteins with higher fitness on a given task would be
revolutionary for many fields of medicine. However, brute-force search through the …
revolutionary for many fields of medicine. However, brute-force search through the …
Advances of Deep Learning in Protein Science: A Comprehensive Survey
Protein representation learning plays a crucial role in understanding the structure and
function of proteins, which are essential biomolecules involved in various biological …
function of proteins, which are essential biomolecules involved in various biological …
Multi-Attribute Constraint Satisfaction via Language Model Rewriting
Obeying precise constraints on top of multiple external attributes is a common computational
problem underlying seemingly different domains, from controlled text generation to protein …
problem underlying seemingly different domains, from controlled text generation to protein …
Deep Generative Models for Ultra-High Granularity Particle Physics Detector Simulation: A Voyage From Emulation to Extrapolation
B Hashemi - arxiv preprint arxiv:2403.13825, 2024 - arxiv.org
Simulating ultra-high-granularity detector responses in Particle Physics represents a critical
yet computationally demanding task. This thesis aims to overcome this challenge for the …
yet computationally demanding task. This thesis aims to overcome this challenge for the …