Paper List
-
GOPHER: Optimization-based Phenotype Randomization for Genome-Wide Association Studies with Differential Privacy
This paper addresses the core challenge of balancing rigorous privacy protection with data utility when releasing full GWAS summary statistics, overco...
-
Real-time Cricket Sorting By Sex A low-cost embedded solution using YOLOv8 and Raspberry Pi
This paper addresses the critical bottleneck in industrial insect farming: the lack of automated, real-time sex sorting systems for Acheta domesticus ...
-
Training Dynamics of Learning 3D-Rotational Equivariance
This work addresses the core dilemma of whether to use computationally expensive equivariant architectures or faster symmetry-agnostic models with dat...
-
Fast and Accurate Node-Age Estimation Under Fossil Calibration Uncertainty Using the Adjusted Pairwise Likelihood
This paper addresses the dual challenge of computational inefficiency and sensitivity to fossil calibration errors in Bayesian divergence time estimat...
-
Few-shot Protein Fitness Prediction via In-context Learning and Test-time Training
This paper addresses the core challenge of accurately predicting protein fitness with only a handful of experimental observations, where data collecti...
-
scCluBench: Comprehensive Benchmarking of Clustering Algorithms for Single-Cell RNA Sequencing
This paper addresses the critical gap of fragmented and non-standardized benchmarking in single-cell RNA-seq clustering, which hinders objective compa...
-
Simulation and inference methods for non-Markovian stochastic biochemical reaction networks
This paper addresses the computational bottleneck of simulating and performing Bayesian inference for non-Markovian biochemical systems with history-d...
-
Assessment of Simulation-based Inference Methods for Stochastic Compartmental Models
This paper addresses the core challenge of performing accurate Bayesian parameter inference for stochastic epidemic models when the likelihood functio...
用于量子退火优化的二元潜在蛋白质适应度景观
University of Alabama at Birmingham
30秒速读
IN SHORT: 通过将序列映射到二元潜在空间进行基于QUBO的适应度优化，桥接蛋白质表示学习和组合优化。
核心创新
- Methodology First framework to transform protein language model embeddings into binary latent representations for QUBO-based fitness modeling
- Methodology Enables direct compatibility with quantum annealing hardware through native QUBO formulation
- Biology Demonstrates that simple binary representations can capture meaningful structure in protein fitness landscapes
主要结论
- Q-BioLat在ProteinGym GFP数据集（10,000个样本，潜在维度32-64）上实现了0.385-0.413的Spearman相关性
- 优化后的序列始终检索到适应度百分位顶部的最近邻，模拟退火在代理分数上实现了1.529±的改进
- 遗传算法在更高维潜在空间（m=64）中优于其他方法，而局部搜索能更好地保持序列真实性
摘要: 我们提出了Q-BioLat，一个在二元潜在空间中建模和优化蛋白质适应度景观的框架。从蛋白质序列出发，我们利用预训练的蛋白质语言模型获得连续嵌入，然后将其转换为紧凑的二元潜在表示。在这个空间中，蛋白质适应度使用二次无约束二元优化（QUBO）模型进行近似，从而通过经典启发式方法（如模拟退火和遗传算法）实现高效的组合搜索。在ProteinGym基准测试中，我们证明Q-BioLat能够捕捉蛋白质适应度景观中的有意义结构，并能够识别高适应度变体。尽管使用了简单的二值化方案，我们的方法始终能检索到其最近邻位于训练适应度分布顶部的序列，特别是在最强配置下。我们进一步表明，不同的优化策略表现出不同的行为，进化搜索在更高维的潜在空间中表现更好，而局部搜索在保持真实序列方面仍具有竞争力。除了其经验性能外，Q-BioLat为蛋白质表示学习和组合优化之间提供了自然的桥梁。通过将蛋白质适应度表述为QUBO问题，我们的框架与新兴的量子退火硬件直接兼容，为量子辅助蛋白质工程开辟了新的方向。