Roger Sayle

The global COVID-19 pandemic has been a rich source of therapeutic non-standard nucleic acid biopolymers…

NameRxn was developed to recognise and categorise reactions from their connection tables. NameRxn usages include analysing corporate Electronic Laboratory Notebooks (ELN), journal or patent data…

The chemistry community relies on IUPAC's standardization of chemical nomenclature to describe and convey descriptions of chemical structures between researchers…

The automated processing and extraction of chemical data from technical documents is an important part of the field of patent informatics. The data gathered from these processes are vital to emerging big data techniques such as reaction synthesis planning and high-throughput virtual screening…

A significant challenge to the field of cheminformatics is the encoding and representation of organometallic and inorganic structures…

The availability of large reaction databases automatically text-mined from chemical patents has catalyzed a flurry of scientific interest in the use of machine learning and AI methods for retrosynthesis and synthetic accessibility prediction…

Patent data tend to be noisy, so extracting chemical information from patents can be challenging. For most new drugs, patents contain information not just on how they are made, but also how the process have changed over time…

In the field of cheminformatics, chemical similarity is almost universally expressed using the Tanimoto coefficient between two binary fingerprints…

In the field of cheminformatics, chemical similarity is almost universally expressed using the Tanimoto coefficient between two binary fingerprints…

: [CINF] Division of Chemical Information

In the field of cheminformatics, chemical similarity is almost universally expressed using the Tanimoto coefficient between two binary fingerprints…

: [CINF] Division of Chemical Information

In the field of cheminformatics, chemical similarity is almost universally expressed using the Tanimoto coefficient between two binary fingerprints…

: [CINF] Division of Chemical Information

In the field of cheminformatics, chemical similarity is almost universally expressed using the Tanimoto coefficient between two binary fingerprints…

The state-of-the-art in software development systems during the mid to late 1980s was Borland International's Turbo Pascal. Turbo Pascal was both an IDE (editor) and compiler for the Pascal programming language, designed by Niklaus Wirth, targeting the IBM PC hardware of the era running MS-DOS…

SMILES, SMARTS, and SMIRKS are a family of line-notation formats created by Daylight for storing, querying, and transforming chemical molecules or reactions…

Standardising molecular structures can help in several situations, though which standard to follow may depend on what the task at hand is. We will look at the standardisation rules the we use for reaction classification…

This presentation describes the recent improvements to NextMove Software's Sugar & Splice, a suite of algorithms for informatics processing of oligopeptides, oligonucleotides, oligosaccharides and lipids…

Pistachio is a database containing more than 15 million reactions extracted from USPTO, EPO, and WIPO PCT patent documents. The data is widely used in in training AI retro synthesis tools and other reaction informatics analysis tasks such as classification and clustering…

The state-of-the-art in software development systems during the mid to late 1980s was Borland International's Turbo Pascal. Turbo Pascal was both an IDE (editor) and compiler for the Pascal programming language, designed by Niklaus Wirth, targeting the IBM PC hardware of the era running MS-DOS…

Performing virtual screening calculations on large chemical databases of many tens of billions of (make-on-demand) compounds poses performance challenges that expose inefficiencies in algorithms and workflows that are statisfactory for much smaller data sets…