Department of Chemistry course timetable

This graduate-level course gives an overview of machine learning (ML) techniques that are useful for solving problems in Chemistry, and particularly for the computational understanding and predictions of materials and molecules at the atomic level.

In the first part of the course, after taking a quick refresher of the basic concepts in probabilities and statistics, students will learn about basic and advanced ML methods including supervised learning and unsupervised learning.

During the second part, the connection between chemistry and mathematical tools of ML will be made and the concepts on the construction of loss functions, representations, descriptors and kernels will be introduced.

For the last part, experts who are actively using research methods to solve research problems in chemistry and materials will be invited to give real-world examples on how ML methods have transformed the way they perform research.

Drug discovery is a complex multidisciplinary process with chemistry as the core discipline. A small molecule New Chemical Entity (NCE) (80% of drugs marketed) has had its genesis in the mind of a chemist. A successful drug is not only biologically active (the easy bit), but is also therapeutically effective in the clinic – it has the correct pharmacokinetics, lack of toxicity, is stable and can be synthesised in bulk, selective and can be patented. Increasingly, it must act at a genetically defined sub-population of patients. Medicinal chemists therefore work at the centre of a web of disciplines – biology, pharmacology, molecular biology, toxicology, materials science, intellectual property and medicine. This fascinating interplay of disciplines is the intellectual space within which a chemist has to make the key compound that will become an effective medicine. It happens rarely, despite enormous investment in time, money and effort. What factors make a program successful? I would like to briefly outline the process, but importantly to offer some key with examples of success

This graduate-level course gives an overview of machine learning (ML) techniques that are useful for solving problems in Chemistry, and particularly for the computational understanding and predictions of materials and molecules at the atomic level.

In the first part of the course, after taking a quick refresher of the basic concepts in probabilities and statistics, students will learn about basic and advanced ML methods including supervised learning and unsupervised learning.

During the second part, the connection between chemistry and mathematical tools of ML will be made and the concepts on the construction of loss functions, representations, descriptors and kernels will be introduced.

For the last part, experts who are actively using research methods to solve research problems in chemistry and materials will be invited to give real-world examples on how ML methods have transformed the way they perform research.

Drug discovery is a complex multidisciplinary process with chemistry as the core discipline. A small molecule New Chemical Entity (NCE) (80% of drugs marketed) has had its genesis in the mind of a chemist. A successful drug is not only biologically active (the easy bit), but is also therapeutically effective in the clinic – it has the correct pharmacokinetics, lack of toxicity, is stable and can be synthesised in bulk, selective and can be patented. Increasingly, it must act at a genetically defined sub-population of patients. Medicinal chemists therefore work at the centre of a web of disciplines – biology, pharmacology, molecular biology, toxicology, materials science, intellectual property and medicine. This fascinating interplay of disciplines is the intellectual space within which a chemist has to make the key compound that will become an effective medicine. It happens rarely, despite enormous investment in time, money and effort. What factors make a program successful? I would like to briefly outline the process, but importantly to offer some key with examples of success

This course is made up of 8 sessions which will be based around the topics below: unlike other courses in the Graduate Lecture Series, it is essential to attend all 8 sessions to benefit from this training. Places are limited so please be absolutely certain upon booking that you will commit to the entire course.

This graduate-level course gives an overview of machine learning (ML) techniques that are useful for solving problems in Chemistry, and particularly for the computational understanding and predictions of materials and molecules at the atomic level.

In the first part of the course, after taking a quick refresher of the basic concepts in probabilities and statistics, students will learn about basic and advanced ML methods including supervised learning and unsupervised learning.

During the second part, the connection between chemistry and mathematical tools of ML will be made and the concepts on the construction of loss functions, representations, descriptors and kernels will be introduced.

For the last part, experts who are actively using research methods to solve research problems in chemistry and materials will be invited to give real-world examples on how ML methods have transformed the way they perform research.

This graduate-level course gives an overview of machine learning (ML) techniques that are useful for solving problems in Chemistry, and particularly for the computational understanding and predictions of materials and molecules at the atomic level.

In the first part of the course, after taking a quick refresher of the basic concepts in probabilities and statistics, students will learn about basic and advanced ML methods including supervised learning and unsupervised learning.

During the second part, the connection between chemistry and mathematical tools of ML will be made and the concepts on the construction of loss functions, representations, descriptors and kernels will be introduced.

For the last part, experts who are actively using research methods to solve research problems in chemistry and materials will be invited to give real-world examples on how ML methods have transformed the way they perform research.

This graduate-level course gives an overview of machine learning (ML) techniques that are useful for solving problems in Chemistry, and particularly for the computational understanding and predictions of materials and molecules at the atomic level.

In the first part of the course, after taking a quick refresher of the basic concepts in probabilities and statistics, students will learn about basic and advanced ML methods including supervised learning and unsupervised learning.

During the second part, the connection between chemistry and mathematical tools of ML will be made and the concepts on the construction of loss functions, representations, descriptors and kernels will be introduced.

For the last part, experts who are actively using research methods to solve research problems in chemistry and materials will be invited to give real-world examples on how ML methods have transformed the way they perform research.

When you have 1000s of possible compounds you could make from any one start point what do you make first? This lecture will cover some general basic principles on designing more potent molecules, as well as some practical tips on how to run an optimization program and how to focus synthetic efforts. Binding modalities (reversible, covalent) will be briefly covered, as well as some newer non-traditional modalities. This lecture will also serve as an introduction to the medicinal chemistry game.

This course is made up of 8 sessions which will be based around the topics below: unlike other courses in the Graduate Lecture Series, it is essential to attend all 8 sessions to benefit from this training. Places are limited so please be absolutely certain upon booking that you will commit to the entire course.

This graduate-level course gives an overview of machine learning (ML) techniques that are useful for solving problems in Chemistry, and particularly for the computational understanding and predictions of materials and molecules at the atomic level.

In the first part of the course, after taking a quick refresher of the basic concepts in probabilities and statistics, students will learn about basic and advanced ML methods including supervised learning and unsupervised learning.

During the second part, the connection between chemistry and mathematical tools of ML will be made and the concepts on the construction of loss functions, representations, descriptors and kernels will be introduced.

For the last part, experts who are actively using research methods to solve research problems in chemistry and materials will be invited to give real-world examples on how ML methods have transformed the way they perform research.

Predicting and controlling how a chemical molecule will be processed by the body is vital to developing a successful drug. This lecture will discuss the path a molecule takes from initial dose through to elimination, describe the ADME (Absorption, Distribution, Metabolism and Excretion) processes that take place and how these are related to compound structure and physicochemical properties. In addition to standard small molecule PK some other new modalities will be also be introduced to illustrate how methods such as PEGylation and lipoparticle encapsulation can be employed to modulate compound pharmacokinetic properties.

This graduate-level course gives an overview of machine learning (ML) techniques that are useful for solving problems in Chemistry, and particularly for the computational understanding and predictions of materials and molecules at the atomic level.

In the first part of the course, after taking a quick refresher of the basic concepts in probabilities and statistics, students will learn about basic and advanced ML methods including supervised learning and unsupervised learning.

During the second part, the connection between chemistry and mathematical tools of ML will be made and the concepts on the construction of loss functions, representations, descriptors and kernels will be introduced.

For the last part, experts who are actively using research methods to solve research problems in chemistry and materials will be invited to give real-world examples on how ML methods have transformed the way they perform research.

This is a compulsory session which introduces new graduate students to the Department of Chemistry Library and its place within the wider Cambridge University Library system. It provides general information on what is available, where it is, and how to get it. Print and online resources are included.

You must choose one session out of the 9 sessions available.

This course is made up of 8 sessions which will be based around the topics below: unlike other courses in the Graduate Lecture Series, it is essential to attend all 8 sessions to benefit from this training. Places are limited so please be absolutely certain upon booking that you will commit to the entire course.

A real drug discovery example will be used. After a brief introduction to the task and the chemical startpoint, we will split into teams and iteratively try to design improved analogues. Molecules will be marked “in real time” during the session to recreate the design-make-test-analysis cycle, then teams can compare their optimized molecules, and we can compare them to what happened in real life.

Please note: To take part in this session you will need to have attended DD1-DD4.

This course is made up of 8 sessions which will be based around the topics below: unlike other courses in the Graduate Lecture Series, it is essential to attend all 8 sessions to benefit from this training. Places are limited so please be absolutely certain upon booking that you will commit to the entire course.

This compulsory session introduces Research Data Management (RDM) to Chemistry PhD students. It is highly interactive and utilises practical activities throughout.

Key topics covered are:

• Research Data Management (RDM) - what it is and what problems can occur with managing and sharing your data.
• Data backup and file sharing - possible consequences of not backing up your data, strategies for backing up your data and sharing your data safely.
• Data organisation - how to organise your files and folders, what is best practice.
• Data sharing - obstacles to sharing your data, benefits and importance of sharing your data, the funder policy landscape, resources available in the University to help you share your data.
• Data management planning - creating a roadmap for how not to get lost in your data!