LABORATORY INFORMATICSSPONSORED CONTENT
Emerging software accelerates drug pipelines The rise of AI and
quantum technology are driving new methods of analysis for new drugs, finds Robert Roe
While drug discovery is an arduous and expensive process, computational chemistry software is helping researchers to streamline and accelerate that investigative pipeline. More specifically, AI-powered software algorithms and quantum chemistry are uncovering new pathways to synthesise chemical compounds and help scientists find new targets to evaluate. Recent advances in AI-based software and quantum chemistry offer unprecedented opportunities to help speed up this stage of drug discovery and get effective medicine to patients much faster than has been possible using conventional methods. This is a hugely impactful area of research
when you consider the cost of drug development. An estimated £1.15bn and up to 12 years is spent designing a new drug and the majority of these (76%) are small molecules. While it appears easy to group this collection of molecules based on their molecular weight; in reality, they are a vastly diverse set of compounds. Most pharmaceuticals are considered small molecules, with the exception of proteins, such as insulin, and other biological medical products. One advantage that small molecule drugs have over large molecule biologics is that many small molecules can be taken orally, whereas biologics generally require injection or another parenteral administration. But from a chemistry standpoint –
particularly when concerning the synthesis of new compounds – small molecules are a hugely disparate category of compounds. There are potentially millions of active compounds and so sifting through the available data and creating new drugs is arduous, however critical, and everyone is searching for ways to make this process take less time and be more efficient. At the heart of small molecule drug
24 Scientific Computing World Summer 2022
discovery is chemical synthesis, which involves medicinal chemists creating new molecules through a complex, step-by-step process. Despite decades of research, this remains a lengthy, laborious procedure – and is still a critical bottleneck for advancing new medicines to the clinic.
Applying new software approaches such
as artificial intelligence (AI) and quantum computing could open up new possibilities for researchers to accelerate drug discovery pipelines. While quantum computing may still be in its initial stages, there are some early applications on the horizon. AI-fuelled drug discovery software is much more established and is available today for a variety of different applications.
$1.2 million grant for quantum chemistry Yuan Ping, who is Associate Professor of Chemistry and Biochemistry at UC Santa Cruz, leads one of eight research projects funded by the US Department of Energy (DOE) to advance the development of modelling and simulation software for the chemical sciences. This is one example of an early-stage project that hopes to explore the use of quantum software. Ping’s group
“Recent advances in AI-based software and quantum chemistry offer unprecedented opportunities to help speed up this stage of drug discovery”
received a $1.2 million grant for the three-year project, which builds on her previous work developing
computational tools for predicting essential properties of materials and molecules based on quantum dynamics. Working with co-principal investigator Ravishankar Sundararaman at Rensselaer Polytechnic Institute, Ping’s team plans to develop computational techniques and massively- parallel software for the rapidly emerging field of ‘spin chemistry’. ‘We can apply the same theoretical
framework and computational tools in a different context to study the effects of spin dynamics on chemical reactions,’ says Ping. ‘If you can control the spin properties, you can change the products or increase the efficiency of chemical reactions, but realising the promise of spin chemistry requires a fundamental understanding of the mechanisms involved in the effects of spin on charge transfer and chemical reactivity.’ Ping’s group will develop computational chemistry techniques for predictive modelling of spin dynamics and spin- dependent charge transfer, paving the way toward a detailed mechanistic understanding of spin chemistry.
Open-source toolkit for computational chemists While this spin chemistry grant is predominantly focused on high-performance computing, there are quantum-based chemistry software tools available to the public today. For example, Quantinuum recently announced the release of its InQuanto software as a standalone platform, bringing together the latest quantum
@scwmagazine |
www.scientific-computing.com
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38
