Dept. of Biomedical Informatics, Harvard University; Broad Institute
Meeting: Actionable machine learning for drug discovery and development
The success of machine learning depends heavily on the choice of features on which the algorithms are applied. For that reason, much of the efforts go into engineering of informative features. In this talk, I describe our efforts in learning deep representations that are actionable and allow endpoint users to ask what-if questions and receive robust predictions that can be interpreted meaningfully. These methods specify deep graph neural functions that map entities from a rich, interconnected dataset to points in a compact vector space, termed embeddings. Importantly, these graph neural methods are optimized to embed entities such that performing algebraic operations in the embedding space reflects the structure of the data. I will describe how these methods enabled repurposing of drugs for an emerging disease where our predictions were experimentally verified in human cells (Gysi et al., 2021). The methods also enabled discovering dozens of drug combinations safe for patients with considerably fewer unwanted side effects than today's treatments. The graph neural network approach can successfully prioritize ultra high-order combinations of drugs despite extreme scarcity of labeled data instances (Huang et al., 2020). Last, I will highlight Therapeutics Data Commons (https://tdcommons.ai), a platform with AI/ML-ready datasets and tasks for therapeutics together with an ecosystem of tools, libraries, leaderboards, and community resources.
Bioinformatics and Integrative Genomics Program, Zitnik Lab, Harvard Medical School
Primer: Deep learning for biomedical networks: Methods, challenges, and frontiers
Biomedical networks are universal descriptors of systems of interacting elements, from protein interactions to disease networks, all the way to healthcare systems and scientific knowledge. Long-standing principles of network biology and medicine, while often unspoken in machine learning research, can provide the conceptual grounding for deep graph representation learning, explain its current successes and limitations, and inform future advances (Li et al. 2021). In this talk, I first synthesize a spectrum of algorithmic approaches that, at their core, leverage topological features to embed networks into compact vector spaces. I then highlight how deep graph representation learning techniques have become essential for studying molecules, genomics, therapeutics, and entire healthcare systems. I conclude with two vignettes where we develop graph neural networks for predicting disease outcomes (Alsentzer et al. 2020) and disentangling single cell behaviors.