飞行:从杂的高通量实验数据推断健身景观
Vikram Sundar1, Boqiang Tu2, Lindsey Guan1
1Computational and Systems Biology Program, Massachusetts Institute of Technology, Cambridge, MA, USA.
bioRxiv : the preprint server for biology
|April 8, 2024
概括
飞行,贝叶斯方法,解释了蛋白质适应性数据中的实验噪声. 这提高了机器学习模型的性能,并揭示了数据大小,而不是模型规模,限制了当前的蛋白质设计模型.
科学领域:
- 计算生物学是一种计算生物学.
- 机器学习 机器学习
- 蛋白质工程是一种蛋白质工程.
背景情况:
- 蛋白质设计的机器学习 (ML) 依赖于高通量实验数据.
- 现有的ML模型经常忽略实验噪声,从而对性能和基准测试产生负面影响.
- 不确定性量化对于强大的蛋白质健身建模至关重要.
研究的目的:
- 介绍FLIGHTED,这是一个贝叶斯方法,用于从杂的实验数据中建模蛋白质健身景观.
- 通过考虑实验不确定性来提高蛋白质设计中的ML模型的性能和可靠性.
- 在蛋白质适应性预测中重新评估限制ML模型性能的因素.
主要方法:
- 开发了FLIGHTED,这是一个贝叶斯的方法,可以从杂的实验数据中生成概率性健身景观.
- 应用于FLIGHTED的单步选择试验 (体显示,SELEX) 和DHARMA试验.
- 基于基准标准的ML模型使用与FLIGHTED生成和不生成的健身景观.
主要成果:
- FLIGHTED显著提高了ML模型的性能,特别是在卷积神经网络 (CNN) 架构中.
- 对实验噪声的计算改变了对比研究中的模型排名.
- 基准测试表明数据大小,而不是模型规模,是主要的性能限制;模型架构比蛋白质语言模型嵌入更为关键.
结论:
- FLIGHTED提供了一种直接的方法,将实验噪音纳入蛋白质健身建模中.
- 该方法广泛适用于各种高通量测定和ML模型.
- FLIGHTED通过解决数据不确定性,促进了更准确,更可靠的蛋白质设计.
相关概念视频
Evolutionary Relationships through Genome Comparisons
5.7K
Genome comparison is one of the excellent ways to interpret the evolutionary relationships between organisms. The basic principle of genome comparison is that if two species share a common feature, it is likely encoded by the DNA sequence conserved between both species. The advent of genome sequencing technologies in the late 20th century enabled scientists to understand the concept of conservation of domains between species and helped them to deduce evolutionary relationships across diverse...
5.7K
Gene Evolution - Fast or Slow?
7.1K
The genomes of eukaryotes are punctuated by long stretches of sequence which do not code for proteins or RNAs. Although some of these regions do contain crucial regulatory sequences, the vast majority of this DNA serves no known function. Typically, these regions of the genome are the ones in which the fastest change, in evolutionary terms, is observed, because there is typically little to no selection pressure acting on these regions to preserve their sequences.
In contrast, regions which code...
In contrast, regions which code...
7.1K


