We can now customize cancer cures, tumor by tumor | MIT Technology Review
Genentech is now pursuing an approach that requires scientists to fully characterize an individual cancer tumor, identify the most attackable mutations, and then design a personalized vaccine that would provoke the immune system to target them.
Functional genomic landscape of acute myeloid leukaemia | Nature
The implementation of targeted therapies for acute myeloid leukaemia (AML) has been challenging because of the complex mutational patterns within and across patients as well as a dearth of pharmacologic agents for most mutational events. Scientists report initial findings from the Beat AML programme on a cohort of 672 tumour specimens collected from 562 patients. Their data reveal mutational events that have not previously been detected in AML. They show that the response to drugs is associated with mutational status, including instances of drug sensitivity that are specific to combinatorial mutational events. Integration with RNA sequencing also revealed gene expression signatures, which predict a role for specific gene networks in the drug response.
Open sourcing TRFL: a library of reinforcement learning building blocks | DeepMind Blog
DeepMind has open sourced a new library of useful building blocks for writing reinforcement learning (RL) agents in TensorFlow. Named TRFL (pronounced ‘truffle’), it represents a collection of key algorithmic components that researchers at DeepMind have used internally for a large number of their most successful agents such as DQN, DDPG and the Importance Weighted Actor Learner Architecture.