Machine learning is a fast growing area of active research within structural science and it is particularly effective in the crystallographic structural sciences due to the wealth of highly accurate structural data available. A key part of machine learning though is having effective molecular descriptors to represent complex chemical information about molecules and structures into easily machine-interpretable vectors of numbers to feed into machine learning algorithms.
We live in exciting times for Artificial Intelligence (AI) - with the rise of new and easy to implement Machine Learning (ML) algorithms. Many of us would sooner trust a GPS to take us from point A to point B than consult a map ourselves, and robots are already being used to perform medical procedures. But what do all of these advanced techniques and algorithms mean for us as scientists and how can we use them to advance science? Presumably, many would ask if AI approaches can help, or even replace scientific experiments?
A few months ago, watching the news of COVID-19 spreading, we knew it would not be safe to hold our user group meeting at a hotel in Cambridge, MA as planned. Rather than cancelling, we moved this to become a virtual event which went ahead on the same date, 24th April 2020.
Our survey on chemical sketching tools ran in March and April 2020 - here we present some of the results.
The way that we use version numbers in our software applications is changing - and this should now be much simpler! This blog explains what's changed, and how you can make sure you have the most up to date version.
In recent years, the Njarðarson research group at the University of Arizona have created posters of the top 200 drugs by sales for education, research purposes and scientific communication.1 When the latest poster based on 2018 data became available for download on their website, I was interested in finding out how many of the top-selling drugs have crystal structures in the Cambridge Structural Database (CSD).2
Since my last article almost 2 weeks ago progress has been made on several projects, so I wanted to provide a quick update.
We are delighted to announce that the first data update of 2020 is now available to users. In the March 2020 data update there are 23,006 new entries and 22,089 new unique structures. This brings the total of the Cambridge Structural Database (CSD) to 1,057,180 entries and 1,038,250 unique structures.
The CCDC is actively seeking areas where we can assist in the fight against the nefarious SARS-Cov2 disease currently taking hold around the world.
We’ve already started committing to research time and have noted several collaborative efforts.
At the CCDC we have been deeply saddened by the devastating impact that COVID-19 has had around the world. During these difficult times it has, however, been heart-warming to see the scientific community coming together to try to find a cure and a vaccine.