Chemoinformatics for Data Scientists

Alsenan, Shrooq; Al-Turaiki, Isra; Hafez, Alaaeldin M.

doi:10.1145/3428757.3429147

Cited by 1 publication

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The chemical structure is characterized in connection tables as a list of all non-hydrogen atoms in the molecule, along with details on how they are related to one another. Basically, a connection table is comprised of two parts: a list of the molecule atoms' atomic numbers and a list of the bonds represented as pairs based on the connected atoms [24][25][26]. Hydrogen atoms are not usually represented in the connection tables because they can be deduced from the bond orders and atom types, and more detailed tables consist of the bonding angles information for plotting the bonds.…”

Section: Connection Tablesmentioning

confidence: 99%

“…Figure 1 shows a simple connection table for Aspirin structure [26]. It consists of 13 atoms that are connected to each other by 13 bonds.…”

Section: Connection Tablesmentioning

confidence: 99%

“…It uses alphanumeric characters to encode the molecules in a more compact way than connection tables. Because of that, the use of linear notations is effective for storing vast numbers of molecules [24,26]. Therefore, the simplified molecular input line entry specification (SMILES) notation is the most acceptable and common linear notation because it has fewer rules and is easier to use than other notations.…”

Section: Line Notationsmentioning

confidence: 99%

“…There are numerous molecular descriptors used for various reasons in the literature, all of which differ in terms of the complexity of encoded information and the time needed to generate them. Furthermore, some descriptors include an experimental component, while others are generated solely by computational algorithms (e.g., 2D fingerprints) [26].…”

Section: Molecular Descriptorsmentioning

confidence: 99%

See 3 more Smart Citations

Deep Learning Based Methods for Molecular Similarity Searching: A Systematic Review

2023

View full text Add to dashboard Cite

In rational drug design, the concept of molecular similarity searching is frequently used to identify molecules with similar functionalities by looking up structurally related molecules in chemical databases. Different methods have been developed to measure the similarity of molecules to a target query. Although the approaches perform effectively, particularly when dealing with molecules with homogenous active structures, they fall short when dealing with compounds that have heterogeneous structural compounds. In recent times, deep learning methods have been exploited for improving the performance of molecule searching due to their feature extraction power and generalization capabilities. However, despite numerous research studies on deep-learning-based molecular similarity searches, relatively few secondary research was carried out in the area. This research aims to provide a systematic literature review (SLR) on deep-learning-based molecular similarity searches to enable researchers and practitioners to better understand the current trends and issues in the field. The study accesses 875 distinctive papers from the selected journals and conferences, which were published over the last thirteen years (2010–2023). After the full-text eligibility analysis and careful screening of the abstract, 65 studies were selected for our SLR. The review’s findings showed that the multilayer perceptrons (MLPs) and autoencoders (AEs) are the most frequently used deep learning models for molecular similarity searching; next are the models based on convolutional neural networks (CNNs) techniques. The ChEMBL dataset and DrugBank standard dataset are the two datasets that are most frequently used for the evaluation of deep learning methods for molecular similarity searching based on the results. In addition, the results show that the most popular methods for optimizing the performance of molecular similarity searching are new representation approaches and reweighing features techniques, and, for evaluating the efficiency of deep-learning-based molecular similarity searching, the most widely used metrics are the area under the curve (AUC) and precision measures.

show abstract

Section: Connection Tablesmentioning

confidence: 99%

“…Figure 1 shows a simple connection table for Aspirin structure [26]. It consists of 13 atoms that are connected to each other by 13 bonds.…”

Section: Connection Tablesmentioning

confidence: 99%

Section: Line Notationsmentioning

confidence: 99%

Section: Molecular Descriptorsmentioning

confidence: 99%

See 2 more Smart Citations