# Accelerated Learning on Large Scale Screens using Generative Library Models

arXiv: https://arxiv.org/abs/2510.16612 · HTML: https://mlsanity.com/paper/2510.16612/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 32 references that are in the map.
- First posted on arXiv 18 Oct 2025.

## Builds on (most cited first, 11 of 11)

- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Positive-Unlabeled Learning with Non-Negative Risk Estimator](https://mlsanity.com/paper/1703.00593/) (2017)
- [Evaluating model calibration in classification](https://mlsanity.com/paper/1902.06977/) (2019)
- [Modern Bayesian Experimental Design](https://mlsanity.com/paper/2302.14545/) (2023)
- [On Nesting Monte Carlo Estimators](https://mlsanity.com/paper/1709.06181/) (2017)
- [Prediction-Oriented Bayesian Active Learning](https://mlsanity.com/paper/2304.08151/) (2023)
- [On the consistency of supervised learning with missing values](https://mlsanity.com/paper/1902.06931/) (2019)
- [Optimal experimental design: Formulations and computations](https://mlsanity.com/paper/2407.16212/) (2024)
- [Unbiased MLMC stochastic gradient-based optimization of Bayesian experimental designs](https://mlsanity.com/paper/2005.08414/) (2020)
- [Learning from negative feedback, or positive feedback or both](https://mlsanity.com/paper/2410.04166/) (2024)
- [Bayesian Optimal Experimental Design for Inferring Causal Structure](https://mlsanity.com/paper/2103.15229/) (2021)

## Built on by (most cited first, 2 of 2)

- [Lifting Biomolecular Data Acquisition](https://mlsanity.com/paper/2512.15984/) (2025)
- [Continuous Variational Synthesis](https://mlsanity.com/paper/2609.35083/) (2026)

## Abstract (arXiv)

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 106-1012 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.