Tensor network machine learning system
The invention is machine learning based method of, or system configured for, identifying candidate, small, drug-like molecules, in which a tensor network representation of molecular quantum states of a dataset of small, drug-like molecules is provided as an input to a machine learning system, such as a neural network system. The machine learning method or system may is itself configured as a tensor network. A training dataset may be used to train the machine learning system, and the training dataset is a tensor network representation of the molecular quantum states of small drug-like molecules.
1. A machine learning based method of identifying candidate, small, drug-like molecules, comprising the step of providing molecular orbital representations of drug-like molecules and/or parts of proteins relevant to an interaction with the molecules, as an input to a machine learning system, to predict molecular properties and identify candidate drug-like molecules, in which molecular orbital representations of drug-like molecules and/or parts of proteins relevant to an interaction with the molecules are represented as tensor networks in which the tensor network representations include networks describing states with volume law entanglement that allow for tensor networks describing density matrices, including both those that obey the area law, and those that do not, and arbitrary superpositions of tensor networks, containing elements in general from distinct types of architectures.
2. The method of claim 1 in which a tensor network is any mathematical object in an exponentially large Hilbert Space.
3. The method of claim 1 in which the tensor networks are one or more of the following: matrix product state (MPS), tensor train, multi-scale entanglement renormalization ansatz (MERA), projected entangled-pair states (PEPS), correlator product states, tree tensor networks, complete graph network states, tensor network states.
4. The method of claim 1 in which a type of architecture is a superposition of two MPS tensor networks with a MERA network.
5. The method of claim 1 in which tensorial networks are used to decompose high rank structures appearing in graph models, hence enabling quantum featurisation and modelling in the context of graph models.
6. The method of claim 1 in which a feature map is applied to input data to transform that input into a high dimensional tensor network structure.
7. The method of claim 1 in which the tensor network represents a set of simple descriptions of a whole dataset of molecules.
8. The method of claim 1 in which the tensor network representations include a training data set of small drug-like molecules and a target, in which the small drug-like molecules are known to bind to the target.
9. The method of claim 1 in which the training dataset is a tensor network representation of the molecular quantum states of small drug-like molecules and also a tensor network representation of the molecular quantum states of one or more targets, such as a protein to which a drug-like molecule may potentially bind.
10. A system for identifying candidate, small, drug-like molecules, the system comprising a computation engine comprising processing circuitry for executing a machine learning based method comprising the step of providing molecular orbital representations of drug-like molecules and/or parts of proteins relevant to an interaction with the molecules, as an input to a machine learning system, to predict molecular properties and identify candidate drug-like molecules, in which molecular orbital representations of drug-like molecules and/or parts of proteins relevant to an interaction with the molecules are represented as tensor networks;
in which the tensor network representations include networks describing states with volume law entanglement that allow for tensor networks describing density matrices, including both those that obey the area law, and those that do not, and arbitrary superpositions of tensor networks, containing elements in general from distinct types of architectures.
11. A molecule or class of molecules identified using a machine learning based method of identifying candidate, small, drug-like molecules,
the method comprising the step of providing molecular orbital representations of drug-like molecules and/or parts of proteins relevant to an interaction with the molecules, as an input to a machine learning system, to predict molecular properties and identify candidate drug-like molecules, in which molecular orbital representations of drug-like molecules and/or parts of proteins relevant to an interaction with the molecules are represented as tensor networks;
in which the tensor network representations include networks describing states with volume law entanglement that allow for tensor networks describing density matrices, including both those that obey the area law, and those that do not, and arbitrary superpositions of tensor networks, containing elements in general from distinct types of architectures.