BANMF-S:一个块式加速的非负矩阵因子化框架,具有结构网络约束,用于单单元算
Jiaying Zhao1, Wai-Ki Ching1, Chi-Wing Wong1
1Department of Mathematics, The University of Hong Kong, Pokfulam Road, Hong Kong.
Briefings in bioinformatics
|September 6, 2024
概括
本研究介绍了以结构网络约束 (BANMF-S) 的块式加速非负矩阵因数分解,以解决单细胞RNA测序 (scRNA-seq) 数据中脱落事件. BANMF-S提高了归算准确性,增强了下游分析,如集群和轨迹推断.
科学领域:
- 基因组学就是基因组学.
- 生物信息学是一种生物信息学.
- 计算生物学 计算生物学
背景情况:
- 单细胞RNA测序 (scRNA-seq) 提供了高分辨率的转录组概况,但受到技术"脱落"事件的限制.
- 这些脱落代表零计数,可以掩盖真正的生物变异,并阻碍下游分析.
研究的目的:
- 开发和验证一个新的计算框架,BANMF-S,用于在scRNA-seq数据中准确地归算掉队事件.
- 提高细胞异质性研究的可靠性和使用归算数据的轨迹推断.
主要方法:
- 拟议的以结构性网络约束 (BANMF-S) 为基础的区块化加速非负矩阵因数分解.
- 使用PPI数据构建基因-基因相似性网络,通过最小跨度树构建细胞-细胞相似性网络.
- 将这些网络集成为矩阵因子化框架内的规范化.
- 采用阻塞策略,使用分布式静态梯度下降来加速优化.
主要成果:
- 通过利用基因和细胞相似性网络,BANMF-S有效地赋予scRNA-seq数据中的技术零.
- 该方法在下游集群和伪轨迹推断任务中显示出更高的准确性.
- 在模拟和真实数据集中,BANMF-S的性能超过了现有的七种最先进的归算算法.
结论:
- BANMF-S提供了一种强大而高效的解决方案,用于解决scRNA-seq数据中脱落事件.
- 该框架通过提高数据质量来增强从scRNA-seq获得的生物见解.
- 与当前的归算技术相比,开发的方法提供了更高的性能.
更多相关视频
08:51Author Spotlight: Integrated Multi-Omics Analysis for Unveiling Multicellular Immune Signatures in Clinical Heart Attack Cohorts
Published on: September 20, 2024
1.2K
08:48Fluorescence-Guided Matrix-assisted Laser Desorption/Ionization with Laser-Induced Postionization Mass Spectrometry of Individual Rat Neural Cells
Published on: May 23, 2025
127
相关概念视频
01:18Singularity Functions for Bending Moment
Singularity functions simplify the representation of bending moments in beams subjected to discontinuous loading, allowing the use of a single mathematical expression. For a supported beam AB, with uniform loading from its midpoint M to the right side end B, the approach involves conceptual 'cuts' at specific points to determine the bending moment in each segment. By cutting the beam at a point between A and M, the bending moment for the segment before reaching midpoint M is represented using a...
01:29Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
01:22Compacting Factor test
The compacting factor test is a method used to assess the workability of concrete. It is especially suitable for concrete mixes containing aggregates up to one and a half inches in size. This test involves specialized equipment consisting of two truncated cone-shaped hoppers and a cylinder, all with polished interior surfaces to minimize friction.
The procedure begins by placing concrete into the upper hopper without any compaction. Once filled, the bottom door of this hopper is opened,...
The procedure begins by placing concrete into the upper hopper without any compaction. Once filled, the bottom door of this hopper is opened,...
01:29Application of Nonlinear Inequalities
A nonlinear inequality describes a comparison involving an expression that curves or behaves more complexly than a straight line. These inequalities often appear in forms that include squares, products, or variables in the denominator.To solve such an inequality, one starts by rewriting it so that zero appears on one side. For example, the inequality: can be factored as: This form makes it easier to identify the values that cause the expression to equal zero. In this case, the key values are 3...
01:30The Binomial Theorem
The Binomial Theorem is a foundational principle in algebra used to expand expressions raised to a power. It provides a structured approach for expanding binomials of the form (a+b)n, where a and b are variables or constants representing algebraic expressions, and n is a non-negative integer.The general form of the Binomial Theorem is:Each term in the expansion involves a binomial coefficient, which is calculated using factorials:The exponent of a in each term decreases from n to 0, while the...
01:30Binomial Expansion Using Pascal's Triangle
Expanding a binomial expression such as (a + b)n results in a predictable sequence of terms that can be systematically derived using Pascal’s Triangle. This triangular array of numbers plays a central role in understanding and computing the coefficients of binomial expansions.Pascal’s Triangle is constructed such that each row corresponds to the coefficients of a binomial raised to a power. The topmost row, known as the zeroth row, corresponds to (a + b)0, and each successive row gives the...