Paper List
-
Discovery of a Hematopoietic Manifold in scGPT Yields a Method for Extracting Performant Algorithms from Biological Foundation Model Internals
This work addresses the core challenge of extracting reusable, interpretable, and high-performance biological algorithms from the opaque internal repr...
-
MS2MetGAN: Latent-space adversarial training for metabolite–spectrum matching in MS/MS database search
This paper addresses the critical bottleneck in metabolite identification: the generation of high-quality negative training samples that are structura...
-
Toward Robust, Reproducible, and Widely Accessible Intracranial Language Brain-Computer Interfaces: A Comprehensive Review of Neural Mechanisms, Hardware, Algorithms, Evaluation, Clinical Pathways and Future Directions
This review addresses the core challenge of fragmented and heterogeneous evidence that hinders the clinical translation of intracranial language BCIs,...
-
Less Is More in Chemotherapy of Breast Cancer
通过纳入细胞周期时滞和竞争项，解决了现有肿瘤-免疫模型的过度简化问题，以定量比较化疗方案。
-
Fold-CP: A Context Parallelism Framework for Biomolecular Modeling
This paper addresses the critical bottleneck of GPU memory limitations that restrict AlphaFold 3-like models to processing only a few thousand residue...
-
Open Biomedical Knowledge Graphs at Scale: Construction, Federation, and AI Agent Access with Samyama Graph Database
This paper addresses the core pain point of fragmented biomedical data by constructing and federating large-scale, open knowledge graphs to enable sea...
-
Predictive Analytics for Foot Ulcers Using Time-Series Temperature and Pressure Data
This paper addresses the critical need for continuous, real-time monitoring of diabetic foot health by developing an unsupervised anomaly detection fr...
-
Hypothesis-Based Particle Detection for Accurate Nanoparticle Counting and Digital Diagnostics
This paper addresses the core challenge of achieving accurate, interpretable, and training-free nanoparticle counting in digital diagnostic assays, wh...
从部分测量中恢复稀疏神经连接：一种基于协方差的方法与格兰杰因果性精炼
Massachusetts Institute of Technology
30秒速读
IN SHORT: 通过跨多个实验会话累积协方差统计，实现从部分记录到完整神经连接性的重建。
核心创新
- Methodology Developed a covariance accumulation framework that reconstructs full connectivity matrices from partial observations across multiple recording sessions
- Methodology Introduced Granger-causality refinement via projected gradient descent to enforce biological constraints (sparsity, non-negativity, no autapses)
- Theory Discovered that linear approximation acts as implicit regularization, outperforming oracle estimators with known nonlinearity via Stein-Price identity characterization
主要结论
- 协方差估计器在N=30网络、T=1000时间步和66%测量密度下实现了中位数Frobenius误差0.053（比随机基线提升91%）
- 格兰杰因果性精炼在N=12网络中进一步降低误差6%（从0.100到0.094），同时实现了完美的边检测召回率（中位数=1.0）
- 最佳刺激水平关键取决于测量密度：在100%测量下，零刺激完全失败（误差>4.0），而适度刺激（σ≈0.5）可实现优异恢复（误差∼0.03）
摘要: 从非完整观测中推断神经回路的连接性是神经科学中的一个基本挑战。我们提出了一种基于协方差的方法，用于从多个记录会话中的稀疏、部分测量中估计循环神经网络的权重矩阵。通过在观察到不同神经元子集的会话中累积成对协方差估计，我们重建了完整的连接矩阵，而无需同时记录所有神经元。一个格兰杰因果性精炼步骤通过投影梯度下降强制执行生物学约束。通过对模拟小脑回路的合成网络进行系统实验，我们描述了一个基本的控制-估计权衡：刺激有助于可识别性但会破坏内在动力学，最佳水平取决于测量密度。我们发现“错误”的线性近似起到了隐式正则化的作用——在所有操作机制下都优于已知非线性的oracle估计器——并通过Stein-Price恒等式提供了精确的表征。