CLinNET:一个可解释和不确定性意识的深度学习框架,用于多模式临床基因组学.
Ivan Bakhshayeshi1, Mohammad Mahdi Hosseini2, Ahmadreza Argha3,4
1UNSW BioMedical Machine Learning Lab (BML), School of Biomedical Engineering, UNSW Sydney, Sydney, NSW, 2052, Australia.
Advanced science (Weinheim, Baden-Wurttemberg, Germany)
|January 28, 2026
概括
一个人工智能工具CLinNET通过解释具有不确定的意义的变异来改善神经认知障碍基因识别. 这种可解释的深度学习模型提高了诊断的准确性,并识别了与疾病相关的新型基因.
科学领域:
- 基因组学就是基因组学.
- 人工智能的人工智能
- 神经科学是一个神经科学.
背景情况:
- 鉴定神经认知障碍 (NDs) 的分子驱动因素是具有挑战性的,因为不确定的意义 (VUS) 的变体和诊断平台的限制.
- 现有的人工智能 (AI) 模型往往缺乏解释性,无法解决不确定性,阻碍了临床应用.
研究的目的:
- 引入CLinNET,一个多模态深度神经网络,旨在增强NDs的基因修复和VUS解释.
- 提高基因预测的准确性和生物相关性,使用生物知情架构和基于信心的不确定性量化.
主要方法:
- CLinNET使用双分支深度神经网络,集成测序数据,基因表达,生物途径和基因本体学 (GO).
- 采用分层的SHapley添加式扩展 (SHAP) 进行强大的解释性和稀疏网络,以路径/GO数据进行丰富.
- 优先考虑组织表达的基因,以提高预测准确性和生物相关性.
主要成果:
- 在ND数据集上,CLinNET获得了76.4%的F1分数和77.2%的准确性,超过了现有方法.
- 不确定性过提高了准确度至87%,同时保持了73%的高可信度预测.
- 鉴定出与ND相关的基因明显多于随机变异的基因,顶部十分位数中的78个基因与ND相关 (p值=1.2e-11).
结论:
- CLinNET是一个强大的,可解释的AI工具,用于基因修复和神经认知障碍中的VUS解释.
- 该模型显示了识别新型诊断基因和推进个性化医学的巨大潜力.
- 通过在前列腺癌数据集中的成功验证,CLinNET的适应性得到了强调.
相关概念视频
The Uncertainty Principle
31.8K
Werner Heisenberg considered the limits of how accurately one can measure properties of an electron or other microscopic particles. He determined that there is a fundamental limit to how accurately one can measure both a particle’s position and its momentum simultaneously. The more accurate the measurement of the momentum of a particle is known, the less accurate the position at that time is known and vice versa. This is what is now called the Heisenberg uncertainty principle. He...
31.8K
Self-Awareness and Its Effects
310
Self-awareness is a psychological state in which the individual becomes the focal point of their attention. This inward focus transforms the self into an object of contemplation and assessment, influencing how individuals perceive their actions and their alignment with personal and societal standards.Triggers and Contexts for Self-AwarenessSelf-awareness can be activated by external stimuli that make individuals visually or audibly aware of themselves, such as mirrors, cameras, or recordings.
310
Uncertainty in Measurement: Reading Instruments
51.6K
Counting is the type of measurement that is free from uncertainty, provided the number of objects being counted does not change during the process. Such measurements result in exact numbers. By counting the eggs in a carton, for instance, one can determine exactly how many eggs are there in the carton. Similarly, the numbers of defined quantities are also exact. For example, 1 foot is exactly 12 inches, 1 inch is exactly 2.54 centimeters, and 1 gram is exactly 0.001 kilograms. Quantities...
51.6K
Altered States of Awareness
1.1K
Altered states of consciousness represent significant deviations from one's normal mental state. These deviations can range from subtle changes in awareness to profound transformations in perception, thought processes, and sensory experiences. Altered states of consciousness can be triggered by various factors, including drug use, meditation, hypnosis, illness, or even intense fatigue.
The ingestion of substances like stimulants or hallucinogens leads to chemical alterations in the brain...
The ingestion of substances like stimulants or hallucinogens leads to chemical alterations in the brain...
1.1K
Subconsciousness and No Awareness
707
The concept of subconscious awareness refers to the processing of information below the level of conscious thought, which significantly influences both behaviors and decisions. It is also known as waking subconscious awareness. This complex level of cognition operates without the direct awareness of the individual, facilitating rapid and simultaneous handling of multiple information streams.
An illustrative example of subconscious processing is its role in problem-solving. Often, individuals...
An illustrative example of subconscious processing is its role in problem-solving. Often, individuals...
707
Uncertainty: Overview
1.7K
In analytical chemistry, we often perform repetitive measurements to detect and minimize inaccuracies caused by both determinate and indeterminate errors. Despite the cares we take, the presence of random errors means that repeated measurements almost never have exactly the same magnitude. The collective difference between these measurements - observed values - and the estimated or expected value is called uncertainty. Uncertainty is conventionally written after the estimated or expected value.
1.7K


