Artificial-Intelligence Driven Discovery and Synthesis of Polyoxometalate Clusters

Periodic Reporting for period 4 - SMART-POM (Artificial-Intelligence Driven Discovery and Synthesis of Polyoxometalate Clusters)

Période du rapport: 2020-05-01 au 2022-04-30

The aim of SMART-POM, Artificial-Intelligence Driven Discovery and Synthesis of Polyoxometalate Clusters, focuses on the use of Artificial Intelligence driven chemical robots to help discover and manufacture new molecules and materials, using inorganic materials as a 'test-bed'. The key questions are: Are new molecules and materials discovered or designed? How can we discover or design to a well defined need specified by a potentail use or user? To do this we are developing a new approach to discovery in chemistry and materials science to by developing robotic platforms for the preparation, understanding, and exploitation of precisely defined nano-molecules / materials based upon the assembly of molecular metal oxide precursors (polyoxometalates) under non-equilibrium conditions with well-defined physical properties using automated intelligent feedback. Targeted properties include systems that can respond to light, help control chemical reactions, and also understanding the 'lego' building principles to make the nano-scale system.

SMART-POM is important as innovation in chemistry across the world aims to drive down costs and to create efficiency in discovery and sustainable manufacture, which are considered cornerstones for sustainable industry grown and profits. This often translates to offshoring and centralisation of supply chains, but there is a vast untapped potential for the EU to leverage existing clean technologies to reduce cost and increase value through digitization, and crucially, cutting the cost of discovery and digitization. Also, the manufacture of chemical products, whether they be bulk, fine or speciality chemicals, such as APIs, is currently based on a model whereby a central plant is exclusively designed for the manufacture of the product, or a small range of products. This results in safety issues around both the storage and transport of such materials as well as the issues inherent in the large-scale manufacture of chemicals. Transport also introduces both cost and environmental footprints, and large FMCG companies, for example, are already exploring methods for decentralizing manufacturing. Large plants are often at the mercy of complicated and global supply chains of raw materials, the failure of which at any point will reduce or halt the capacity of the plant to produce materials and deliver them effectively.

The key aim of the programme, to establish the new discipline ‘digital-chemistry’, via the use of digital systems in chemistry has been achieved through the development ofnew synthetic chemistry and engineering platforms for the discovery of molecules, clusters and nanomaterials requiring the development of several integrated hybrid system integrating wetware (chemical reagents), hardware (reactors and sensors) and software (intelligent algorithms).

Work has focussed on three areas:

i) Construct a universal building block library of POM sub-units, clusters and methods for their programmed synthesis.

We were able to design catalytically active systems or multi-functional materials that can have several roles ‘encoded’ into a single compound. The design was done by selecting wheel-shaped POMs, metal ion linkers, and we engineered the assembly in an efficient and high yielding manner. ALso, the ability to build these materials was critically limited by the obscure nature of the synthesis of many POMs. However, thanks to recent advancements during our grant regarding mechanistic control, and system automation, it is now much easier to reliably build such building blocks, whereas before this is a big barrier. This enhanced synthetic access, combined with the new building block libraries, and emerging taxonomy, has established polyoxometalate frameworks as a new class of metal oxides.

ii) Establish the concept of using algorithms, feedback control, and in-line spectroscopies to enable synthesis and explore reaction parameter-spaces.

In this area several versatile systems have been designed and implemented to serve functions ranging from chemical exploration to reproducibility. Through the development of this work, chemical synthesis has undergone a revolution in automation and control. From the development of combinatorial chemistry in big pharma, aiming to expand compound libraries, to the development of flow chemistry for manufacturing, the prospect of smart automation in chemistry has been much anticipated. Until recently, the average chemical research laboratory looks no different to that of a half a century ago, and automation has had little if any impact with limited payback. The key reason was that the assessment of chemical reactivity aiming at new chemical discoveries is a laborious problem requiring experts able to deal with the inherent complexity of chemical mixtures i.e. for humans to make decisions. This WP allowed us to build a chemical system capable of assessing chemical reactivity without any prior chemical knowledge, and using this assessment to make decisions about which reactions to perform in a sequence in real time

iii) Combine fundamental chemistry with digital control and algorithmic approaches to develop a new approach to Chemical Synthesis and discovery.

Here we have developed a fundamentally new approach to ‘automatic’ chemical synthesis. This is important if fine chemical production is to move from large volume, centralized manufacture prone to supply disruption, to a small‐scale end-user focused manufacturing approach. The current paradigm of fine chemical manufacture and distribution is based on a model whereby virtually all manufacturing is located at large plant locations. Our approach explores the digital synthesis of the desired products on‐demand, using standardised synthesis engines which have the potential to be able to perform any chemical operation. This allows the digital encoding of chemical synthesis into formats that are easily reproducible, and could ultimately allow the digitization of access to pharmaceuticals. This will lead to new supply chains, distributed manufacture, and will change the way organic synthesis and process chemistry are developed together to manufacture at small scale, but in a highly reliable and distributed manner.

This grant has allowed us to demonstrate the advantages of applying robotic synthesis techniques in conjunction with machine learning algorithms to enable new ways of exploring chemical space, and discover new molecules and materials, as well as develop applications for the discovered species. The Grant has allowed the development of a standard (XDL) for the digital description of chemical synthesis which will enable the sharing of intrinsically reproducible and validated synthesis procedures. This digital standard has been developed in sych a way that it can simultaneously control autonomous synthesis platforms. These developments have grown out of the vision of robotically enabled synthesis originally planned in SMART POM. We have been able to construct over 10 unique robotically controlled platforms, alongside establishing a new paradigm of laboratory scale synthesis automation, for chemical synthesis and discovery which leverage the approaches common in machine learning towards the standardisation and reproducibility in chemical systems.

scheme-1.jpg

Periodic Reporting for period 4 - SMART-POM (Artificial-Intelligence Driven Discovery and Synthesis of Polyoxometalate Clusters)

Partager cette page

Télécharger