Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

Molecular Synthesis Planning: Transformer Models and Atom Mapping

Related concepts (25)

Reaction intermediate

In chemistry, a reaction intermediate or an intermediate is a molecular entity that is formed from the reactants (or preceding intermediates) but is consumed in further reactions in stepwise chemical reactions that contain multiple elementary steps. Intermediates are the reaction product of one elementary step, but do not appear in the chemical equation for an overall chemical equation. For example, consider this hypothetical stepwise reaction: A + B -> C + D The reaction includes two elementary steps: A + B -> X X -> C + D In this example, X is a reaction intermediate.

Danishefsky Taxol total synthesis

The Danishefsky Taxol total synthesis in organic chemistry is an important third Taxol synthesis published by the group of Samuel Danishefsky in 1996 two years after the first two efforts described in the Holton Taxol total synthesis and the Nicolaou Taxol total synthesis. Combined they provide a good insight in the application of organic chemistry in total synthesis. Danishefsky's route to Taxol has many similarities with that of Nicolaou. Both are examples of convergent synthesis with a coupling of the A and the C ring from two precursors.

Organic chemistry

Organic chemistry is a subdiscipline within chemistry involving the scientific study of the structure, properties, and reactions of organic compounds and organic materials, i.e., matter in its various forms that contain carbon atoms. Study of structure determines their structural formula. Study of properties includes physical and chemical properties, and evaluation of chemical reactivity to understand their behavior.

Deep learning

Deep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.

Convolutional neural network

Convolutional neural network (CNN) is a regularized type of feed-forward neural network that learns feature engineering by itself via filters (or kernel) optimization. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections. For example, for each neuron in the fully-connected layer 10,000 weights would be required for processing an image sized 100 × 100 pixels.