Understanding Similarities and Differences between Two Prominent Web-Based Chemical Information and Data Retrieval Tools: Comments on Searches for Research Topics, Substances, and Reactions

Mutton, Troy; Ridley, Damon D.

doi:10.1021/acs.jchemed.9b00268

Cited by 13 publications

(9 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) Add the segmentation method to the feature point set In the process of web page text information extraction, it is necessary to calculate the distance between feature vectors in web page text information feature space to measure the similarity between web page text information features [36]. The Euclidean distance method can extract web page text information.…”

Section: Feature Point Extraction Of Web Page Text Informationmentioning

confidence: 99%

Automatic Extraction of Web Page Text Information Based on Network Topology Coincidence Degree

Shu

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

In order to effectively solve the above problems, an automatic extraction method of web text information based on network topology coincidence degree is proposed. Search engine, web crawler, and hypertext tag are used to classify web text information, and then, dimensionality reduction is carried out. After processing, the similarity of different features of web page text information is calculated, the similarity is sorted, and the similar text information is extracted according to the correlation based on segment estimation. The experimental results show that the designed method can simplify the complexity of the associated information of the data set and improve the amount of data collection and the success rate of information collection.

show abstract

Section: Feature Point Extraction Of Web Page Text Informationmentioning

confidence: 99%

Automatic Extraction of Web Page Text Information Based on Network Topology Coincidence Degree

Shu

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…In addition, a 2019 scaffold diversity analysis stringently filtered the CAS collection down to only ≈30 million compounds with direct links to literature and patents [13]. Since its first release in 2009 Elsevier Reaxys has emerged as another large-scale D-C capture endeavour, the statistics and search characteristics of which have recently been compared with SciFinder [14]. It has reached 31 million structures but also subsumes PubChem which brings it up to 105 million.…”

Section: Commercial Capturementioning

confidence: 99%

Opening up connectivity between documents, structures and bioactivity

Southan

2020

Beilstein J. Org. Chem.

View full text Add to dashboard Cite

Bioscientists reading papers or patents strive to discern the key relationships reported within a document “D“ where a bioactivity “A” with a quantitative result “R” (e.g., an IC50) is reported for chemical structure “C” that modulates (e.g., inhibits) a protein target “P”. A useful shorthand for this connectivity thus becomes DARCP. The problem at the core of this article is that the community has spent millions effectively burying these relationships in PDFs over many decades but must now spend millions more trying to get them back out. The key imperative for this is to increase the flow into structured open databases. The positive impacts will include expanded data mining opportunities for drug discovery and chemical biology. Over the last decade commercial sources have manually extracted DARCP from ≈300,000 documents encompassing ≈7 million compounds interacting with ≈10,000 targets. Over a similar time, the Guide to Pharmacology, BindingDB and ChEMBL have carried out analogues DARCP extractions. Although their expert-curated numbers are lower (i.e., ≈2 million compounds against ≈3700 human proteins), these open sources have the great advantage of being merged within PubChem. Parallel efforts have focused on the extraction of document-to-compound (D-C-only) connectivity. In the absence of molecular mechanism of action (mmoa) annotation, this is of less value but can be automatically extracted. This has been significantly accomplished for patents, (e.g., by IBM, SureChEMBL and WIPO) for over 30 million compounds in PubChem. These have recently been joined by 1.4 million D-C submissions from three major chemistry publishers. In addition, both the European and US PubMed Central portals now add chemistry look-ups from abstracts and full-text papers. However, the fully automated extraction of DARCLP has not yet been achieved. This stands in contrast to the ability of biocurators to discern these relationships in minutes. Unfortunately, no journals have yet instigated a flow of author-specified DARCP directly into open databases. Progress may come from trends such as open science, open access (OA), findable, accessible, interoperable and reusable (FAIR), resource description framework (RDF) and WikiData. However, we will need to await the technical applicability in respect to DARCP capture to see if this opens up connectivity.

show abstract

“…Moreover, chemists often require retrosynthetic analysis based on unknown reaction rules. This is especially significant due to our incomplete knowledge of chemical reactions; e.g., 29 million reactions were regularly recorded between 2009 and 2019 in Reaxys 1 (Mutton & Ridley, 2019).…”

Section: Introductionmentioning

confidence: 99%

RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning

Lee¹,

Ahn²,

Seo

et al. 2021

Preprint

View full text Add to dashboard Cite

Retrosynthesis, of which the goal is to find a set of reactants for synthesizing a target product, is an emerging research area of deep learning. While the existing approaches have shown promising results, they currently lack the ability to consider availability (e.g., stability or purchasability) of the reactants or generalize to unseen reaction templates (i.e., chemical reaction rules). In this paper, we propose a new approach that mitigates the issues by reformulating retrosynthesis into a selection problem of reactants from a candidate set of commercially available molecules. To this end, we design an efficient reactant selection framework, named RetCL (retrosynthesis via contrastive learning), for enumerating all of the candidate molecules based on selection scores computed by graph neural networks. For learning the score functions, we also propose a novel contrastive training scheme with hard negative mining. Extensive experiments demonstrate the benefits of the proposed selection-based approach. For example, when all 671k reactants in the USPTO database are given as candidates, our RetCL achieves top-1 exact match accuracy of 71.3% for the USPTO-50k benchmark, while a recent transformer-based approach achieves 59.6%. We also demonstrate that RetCL generalizes well to unseen templates in various settings in contrast to template-based approaches.

show abstract

Understanding Similarities and Differences between Two Prominent Web-Based Chemical Information and Data Retrieval Tools: Comments on Searches for Research Topics, Substances, and Reactions

Cited by 13 publications

References 15 publications

Automatic Extraction of Web Page Text Information Based on Network Topology Coincidence Degree

Automatic Extraction of Web Page Text Information Based on Network Topology Coincidence Degree

Opening up connectivity between documents, structures and bioactivity

RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning

Contact Info

Product

Resources

About