# Forecasting labels under distribution-shift for machine-guided sequence design

arXiv: https://arxiv.org/abs/2211.10422 · HTML: https://mlsanity.com/paper/2211.10422/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 35 references that are in the map.
- First posted on arXiv 18 Nov 2022.

## Builds on (most cited first, 7 of 7)

- [Detecting and Correcting for Label Shift with Black Box Predictors](https://mlsanity.com/paper/1802.03916/) (2018)
- [ProGen2: Exploring the Boundaries of Protein Language Models](https://mlsanity.com/paper/2206.13517/) (2022)
- [Conditioning by adaptive sampling for robust design](https://mlsanity.com/paper/1901.10060/) (2019)
- [Model Inversion Networks for Model-Based Optimization](https://mlsanity.com/paper/1912.13464/) (2019)
- [AdaLead: A simple and robust adaptive greedy search algorithm for sequence design](https://mlsanity.com/paper/2010.02141/) (2020)
- [Population-Based Black-Box Optimization for Biological Sequence Design](https://mlsanity.com/paper/2006.03227/) (2020)
- [Designing Biological Sequences via Meta-Reinforcement Learning and Bayesian Optimization](https://mlsanity.com/paper/2209.06259/) (2022)

## Built on by (most cited first, 4 of 4)

- [Beyond the training set: an intuitive method for detecting distribution shift in model-based optimization](https://mlsanity.com/paper/2311.05363/) (2023)
- [Is novelty predictable?](https://mlsanity.com/paper/2306.00872/) (2023)
- [Reliable algorithm selection for machine learning-guided design](https://mlsanity.com/paper/2503.20767/) (2025)
- [Generalization within in silico screening](https://mlsanity.com/paper/2307.09379/) (2023)

## Abstract (arXiv)

The ability to design and optimize biological sequences with specific functionalities would unlock enormous value in technology and healthcare. In recent years, machine learning-guided sequence design has progressed this goal significantly, though validating designed sequences in the lab or clinic takes many months and substantial labor. It is therefore valuable to assess the likelihood that a designed set contains sequences of the desired quality (which often lies outside the label distribution in our training data) before committing resources to an experiment. Forecasting, a prominent concept in many domains where feedback can be delayed (e.g. elections), has not been used or studied in the context of sequence design. Here we propose a method to guide decision-making that forecasts the performance of high-throughput libraries (e.g. containing 105 unique variants) based on estimates provided by models, providing a posterior for the distribution of labels in the library. We show that our method outperforms baselines that naively use model scores to estimate library performance, which are the only tool available today for this purpose.