没有偏见的回归合成语言模型与断开提示
Amol Thakkar1,2, Alain C Vaucher1,2, Andrea Byekwaso1
1IBM Research Europe, Saümerstrasse 4, 8803 Rüschlikon, Switzerland.
化学家现在可以通过断开提示指导逆合成,从而产生更加多样化和创造性的前体建议. 这种人工智能方法克服了数据偏差,并提高了39%的预测.
科学领域:
- 计算化学的计算化学
- 化学中的人工智能.
背景情况:
- 目前的数据驱动回复合成方法缺乏用户控制和多样性.
- 现有的模型经常推非直观的断开连接策略,受到训练数据偏差的限制.
研究的目的:
- 在数据驱动的回复合成中增强用户交互和预测多样性.
- 引入基于提示的化学语言建模方法,以改进反合成建议.
主要方法:
- 扩展自然语言处理基于提示的推断到化学语言建模.
- 开发了一个两阶段的方案:自动断开连接点的识别,然后进行反应剂集预测.
- 利用断开连接提示以引导模型预测.
主要成果:
- 与基线逆合成建议相比,实现了39%的性能改善.
- 与基线方法相比,证明了类多样性的显著增加.
- 成功地减轻了来自训练数据的预测偏差.
结论:
- 基于提示的化学语言建模使化学家能够更好地控制反合成.
- 这种方法产生了更多的多样化,创造性和可用的构建块,增强了数字用户体验.
- 适用于各种化学领域,包括传统和酶反应.
更多相关视频
05:22Dissociation of the Confounding Influences of Expectancy and Integrative Difficulty Residing in Anomalous Sentences in Event-related Potential Studies
Published on: May 9, 2019
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
相关概念视频
Woodward–Hoffmann Selection Rules and Microscopic Reversibility
Synthesis and Decomposition Reactions
Lagging Strand Synthesis
Biasing of P-N Junction
In equilibrium, no external voltage is applied across the p-n junction. The depletion region is formed at the junction interface due to the diffusion of carriers, which leaves behind charged dopants, acceptors on the p-side, and donors on the n-side. These immobile charges create an electric field that prevents further diffusion of carriers. The related energy band...
Biasing of Metal-Semiconductor Junctions
In Schottky junctions, where the semiconductor is n-type, applying a positive voltage to the metal relative to the semiconductor reduces its Fermi...
Diels–Alder Reaction Forming Bridged Bicyclic Products: Stereochemistry
