Accelerated Learning on Large Scale Screens using Generative Library Models
This work addresses data scarcity in biological ML for researchers, offering an incremental improvement in experimental design and inference methods.
The paper tackles the data bottleneck in biological machine learning by optimizing high-throughput screens to maximize information gain, showing that collecting only positive examples and correcting with a generative model yields consistent estimates of activity probabilities, demonstrated in simulations and antibody screens.
Biological machine learning is often bottlenecked by a lack of scaled data. One promising route to relieving data bottlenecks is through high throughput screens, which can experimentally test the activity of $10^6-10^{12}$ protein sequences in parallel. In this article, we introduce algorithms to optimize high throughput screens for data creation and model training. We focus on the large scale regime, where dataset sizes are limited by the cost of measurement and sequencing. We show that when active sequences are rare, we maximize information gain if we only collect positive examples of active sequences, i.e. $x$ with $y>0$. We can correct for the missing negative examples using a generative model of the library, producing a consistent and efficient estimate of the true $p(y | x)$. We demonstrate this approach in simulation and on a large scale screen of antibodies. Overall, co-design of experiments and inference lets us accelerate learning dramatically.