Batch equalization with a generative adversarial network.

Motivation: Advances in automation and imaging have made it possible to capture a large image dataset that spans multiple experimental batches of data. However, accurate biological comparison across the batches is challenged by batch-to-batch variation (i.e.

Snorkel DryBell: A Case Study in Deploying Weak Supervision at Industrial Scale.

Labeling training data is one of the most costly bottlenecks in developing machine learning-based applications. We present a first-of-its-kind study showing how existing knowledge resources from across an organization can be used as weak supervision in order to bring development time and cost down by an order of magnitude, and introduce Snorkel DryBell, a new weak supervision management system for this setting. Snorkel DryBell builds on the Snorkel framework, extending it in three critical aspects: flexible, template-based ingestion of diverse organizational knowledge, cross-feature production serving, and scalable, sampling-free execution.

Smart hydrogel particles: biomarker harvesting: one-step affinity purification, size exclusion, and protection against degradation.

Disease-associated blood biomarkers exist in exceedingly low concentrations within complex mixtures of high-abundance proteins such as albumin. We have introduced an affinity bait molecule into N-isopropylacrylamide to produce a particle that will perform three independent functions within minutes, in one step, in solution: (a) molecular size sieving, (b) affinity capture of all solution-phase target molecules, and (c) complete protection of harvested proteins from enzymatic degradation. The captured analytes can be readily electroeluted for analysis.