2024年7月5日 · We introduce multiple implementations of molecular set representation architectures, including the single-set atom-based MSR1, the dual-set atom and bond-based MSR2, and the graph invariant ...

2020年9月17日 · We present here some of the most popular electronic molecular and macromolecular representations used in drug discovery, many of which are based on graph representations. Furthermore, we describe applications of …

2024年7月20日 · In this section, we introduce various molecular representations that are classified into six groups: string-based, property-based, molecular fingerprints, language model-based, graph-based, and others based on their characteristics.

2022年2月18日 · A wide range of molecular representations has been introduced across four categories: string, chemical table, feature-based, and computer-learned representations.

2022年2月7日 · Effective molecular representation learning is of great importance to facilitate molecular property prediction. Recent advances for molecular representation learning have shown great promise in...

2024年6月17日 · We introduce the Information Alignment (InfoAlign) approach to learn molecular representations through the information bottleneck method in cells. We integrate molecules and cellular response data as nodes into a context graph, connecting them with weighted edges based on chemical, biological, and computational criteria.

6 天之前 · Different molecular representations exist to provide visual and mathematical means to depict complex structures. However, the detailing required for algorithmic applications remains a challenge. This study presents a methodology that uses two matrices to obtain a detailed molecular description. The proposed matrices are Molecule as a Graph (MAG), which …

2022年12月1日 · In this review, we summarize contemporary applications of deep learning (DL) methods for molecular representation and property prediction. We categorize DL methods according to the format of molecular data (1D, 2D, and 3D).

2022年7月8日 · In this survey, we systematically review these graph-based molecular representation techniques, especially the methods incorporating chemical domain knowledge. Specifically, we first introduce the features of 2D and 3D molecular graphs.

2025年1月6日 · In the self-supervised setting, machine learning models are pre-trained to learn generic molecular representations by optimizing the performance on pre-defined tasks on large-scale unannotated...