当前机器学习模型在预测未表征蛋白质酶功能方面的局限性
Valérie de Crécy-Lagard1,2, Raquel Dias1, Nick Sexson1
1Department of Microbiology and Cell Science, University of Florida, Gainesville, FL 32611, USA.
G3 (Bethesda, Md.)
|July 24, 2025
概括
当前的机器学习方法难以预测新型蛋白质功能,经常犯逻辑错误. 未来的模型需要不确定性评估和可解释的AI来提高理解"unknome"的准确性.
科学领域:
- 蛋白质组学是指蛋白质组学.
- 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:
- 很大一部分称为"unknome"的蛋白质缺乏指定的功能,这代表了生物知识中的一个重大差距.
- 机器学习 (ML) 显示出从特征蛋白质推断蛋白质功能的前景,但其预测新型酶功能的能力尚不清楚.
研究的目的:
- 评估最先进的机器学习方法在预测酶委员会 (EC) 对未表征蛋白质的数量的准确性.
- 评估ML模型是否可以预测其训练数据中不存在的酶功能.
主要方法:
- 整合文献数据与各种生物信息学方法.
- 使用ML模型对超过450种埃舍里希亚大肠杆菌未知的蛋白质EC数量预测的个别评估.
- 可解释AI (XAI) 的应用,以识别预测错误的指标.
主要成果:
- 目前的ML方法在很大程度上无法为未表征的蛋白质产生新的功能预测.
- 机器学习模型在预测中表现出基本的逻辑错误,与利用更广泛知识基础的人类注释者不同.
- 预测不确定性和模型"幻觉" (逻辑失败) 被确定为关键问题.
结论:
- 需要将预测不确定性评估纳入ML模型输出.
- 对于功能基因组学中的ML模型来说,对逻辑失败 ("幻觉") 的严格评估至关重要.
- 可解释的人工智能可以帮助识别关键数据特征,以改善未来蛋白质功能的计算模型.
相关概念视频
02:34Enzymes
82.7K
Inside living organisms, enzymes act as catalysts for many biochemical reactions involved in cellular metabolism. The role of enzymes is to reduce the activation energies of biochemical reactions by forming complexes with its substrates. The lowering of activation energies favor an increase in the rates of biochemical reactions.
Enzyme deficiencies can often translate into life-threatening diseases. For example, a genetic abnormality resulting in the deficiency of the enzyme G6PD...
Enzyme deficiencies can often translate into life-threatening diseases. For example, a genetic abnormality resulting in the deficiency of the enzyme G6PD...
82.7K
01:23Mechanistic Models: Compartment Models in Individual and Population Analysis
87
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
87
02:04Protein-protein Interfaces
13.3K
Many proteins form complexes to carry out their functions, making protein-protein interactions (PPIs) essential for an organism's survival. Most PPIs are stabilized by numerous weak noncovalent chemical forces. The physical shape of the interfaces determines the way two proteins interact. Many globular proteins have closely-matching shapes on their surfaces, which form a large number of weak bonds. Additionally, many PPIs occur between two helices or between a surface cleft and a...
13.3K
02:26Protein Networks
4.1K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.1K
01:13Induced-fit Model
82.2K
Most chemical reactions in cells require enzymes—biological catalysts that speed up the reaction without being consumed or permanently changed. They reduce the activation energy needed to convert the reactants into products. Enzymes are proteins, that usually work by binding to a substrate—a reactant molecule that they act upon.
Enzymes exhibit substrate specificity, meaning that they can only bind to certain substrates. This is mainly determined by the shape and chemical...
Enzymes exhibit substrate specificity, meaning that they can only bind to certain substrates. This is mainly determined by the shape and chemical...
82.2K
01:19Allosteric Proteins-ATCase
5.9K
Binding sites linkages can regulate a protein's function. For example, enzyme activity is often regulated through a feedback mechanism where the end product of the biochemical process serves as an inhibitor.
Aspartate transcarbamoylase (ATCase) is a cytosolic enzyme that catalyzes the condensation of L-aspartate and carbamoyl phosphate to N-carbamoyl-L-aspartate. This reaction is the first step in pyrimidine biosynthesis. UTP and CTP, the end products of the pyrimidine synthesis...
Aspartate transcarbamoylase (ATCase) is a cytosolic enzyme that catalyzes the condensation of L-aspartate and carbamoyl phosphate to N-carbamoyl-L-aspartate. This reaction is the first step in pyrimidine biosynthesis. UTP and CTP, the end products of the pyrimidine synthesis...
5.9K