AI Learns to Predict Outcomes of Complex Chemical Reactions

| September 4, 2019

article image
An AI system capable of predicting the outcomes of chemical reactions has been developed. A feat that could improve current drug recovery processes. The researchers at the University of Cambridge have created an algorithm that can predict the outcomes of complex chemical reactions with over 90 percent accuracy. Using the algorithm, scientists can conveniently make target compounds, leading to a potential breakthrough in drug discovery. Chemists have always had a problem combining simple building blocks into complicated organic molecules. That’s because these building blocks often react in unexpected ways. By handling chemical reaction prediction as a machine translation problem, the model was able to produce more accurate results. Think of the reacting molecules as a language, and the product as another language. In this case, the model uses patterns in the texts to learn how to translate between the two languages.

Spotlight

The Reynolds Company Adhesives and Coatings

The Reynolds Company is a custom adhesive compounder. We specialize in hot melt and water based adhesives and coatings, as well as dry adhesives. Establishing trust with clients since 1978 we serve such industries as: Packaging, Wood-Working, Graphic Arts & Textile.

OTHER ARTICLES

Global polyethylene demand boom likely, increasing the sustainability challenge

Article | June 15, 2021

IT FEELS LIKE several lifetimes ago. If you recall, way back in November-December 2019 Asian variable cost integrated naphtha-based polyethylene (PE) margins turned negative because of the increase in US capacity. Then in January the following year, deep Asian and Middle East operating rate cuts returned some order to the market. Then, bang, as we all know, the pandemic arrived and turned everything on its head. The pandemic has, in my view, accentuated trends that were already well underway. I believe this means that the supply-driven downturn that started in late 2019 will not return.Long before coronavirus upended everyone’s lives, PE demand was becoming increasingly divorced from GDP growth because of the shifting nature of end-use demand. Booming internet sales was, I believe, a major factor behind the split between the growth of the overall economies in the developed world plus China and PE demand.The average product bought online is dropped 17 times because of the large number of people involved in the logistics chain, according to Forbes. This had led to a surge in demand for protective packaging made not from PE and other polymers such as polypropylene, expandable polystyrene and PET films (I will look at their demand growth prospects in later posts).Despite sustainability pressures, the scale of demand for stuff bought online translated to a lot more consumption of virgin polymers.

Read More

Transporting biological and chemical materials - what you need to know

Article | February 13, 2020

The landscape of biological and chemical logistics has changed rapidly - as have the regulatory frameworks around it. What has not necessarily kept pace is the end-user understanding of the nature of these logistical processes, their opportunities and their constraints. Twenty years ago, the transmission of biological and chemical materials was limited to a small range of organisations: usually national and international research companies, hospitals, major university departments, police and military departments with forensic responsibilities.

Read More

6 APPLICATIONS OF MACHINE LEARNING IN OIL AND GAS

Article | March 4, 2020

The issue of environmental sustainability is a major concern for governments and players from the oil and gas industry worldwide. The negative impacts as a result of activities carried out by oil and gas companies have been a major tool not only for the livelihood and health of people but more so to the environment, such as pollution. The risk of environmental pollution, hazards and severity can be and will be reduced with the use of machine learning and deep learning in the years to come. There has been an amazing application in chemical engineering, process safety, process control tuning, advanced dynamic and process optimization. We can see that the Oil and Gas industry when we talk about software especially machine learning solutions didn’t have any innovation in the last 15 years.

Read More

Energy portfolio restructuring: Charting the future

Article | June 17, 2021

Consumer needs and preferences in the energy industry are evolving. Environmental, social and governance (ESG) concerns are becoming more acute—inspiring action and shifting value towards low-carbon solutions. These trends accelerated in 2020 and for the first time, market capitalization of leading low-carbon solutions companies began to overtake those of oil and gas (O&G) majors. This is despite the majors laying out energy transition strategies, setting low carbon energy targets and generating higher revenues by an order of magnitude.1 In response to this radically changing landscape, energy companies are charting divergent courses for their futures. Some continue to bet on their ability to generate returns from the O&G value chain. They are focusing on growing margins and lowering carbon intensity. Others are supplementing their capabilities with low-carbon energy solutions or exiting hydrocarbons altogether. This blog focuses on the path forward for the energy majors in Europe who are betting big on diversification.

Read More

Spotlight

The Reynolds Company Adhesives and Coatings

The Reynolds Company is a custom adhesive compounder. We specialize in hot melt and water based adhesives and coatings, as well as dry adhesives. Establishing trust with clients since 1978 we serve such industries as: Packaging, Wood-Working, Graphic Arts & Textile.

Events