> ## Documentation Index
> Fetch the complete documentation index at: https://instance.bio/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Release Notes

> What's new

## 26.3 (2026-06-30)

This release focuses on optimizing the antigen expression process, binding process, and sequencing analysis to improve the ability to characterize weaker binders with greater sensitivity.

### Dataset Improvements

* Data labeling task metadata and UMI aligned-reads data provenance datasets are included alongside the primary datasets.
  * `labeling_task_candidates`
  * `dim_samples`
  * `aligned_reads`
* The binding score now takes into account the bind and wash process noise, measured using the negative control samples.
* Updated UMI clustering to increase the accuracy of unique molecule counts.
* Updated aligned reads filtering to only include perfect coding regions.

### Process Improvements

* Several optimizations to the binding process to reduce process noise, variability, and better reflect binding equilibrium.
  * Binding incubation process parameters have been adjusted to allow weaker binders to reach equilibrium more consistently.
  * Implemented a new flash-wash protocol that minimizes bead binding time and end-to-end wash time to reduce the potential for disturbing the binding equilibrium state.
* Updated the default antigen dose process parameters to improve sensitivity over a broader range of candidate binding strengths.
* Negative controls have been expanded to include a null-antigen sample of expressed candidates that otherwise still undergoes the identical binding process.
* Minor optimization to the binder expression process conditions to improve yield uniformity.

## 26.2 (2026-06-12)

Minor update addressing usability issues with the exposed data and schemas.

* Exposed internal replicate details including UMI counts as standard datasets:
  * `expression_replicates`
  * `binding_replicates`
  * `specificity_replicates`

## 26.1 (2026-05-29)

The initial production-ready release of instance Data Lab.

* Initial production release of protein experimental ground truth generation harness.
* Baselined and benchmarked against open-source datasets.
* Support for the SinoBiological Recombinant Protein soluble antigens.
* Support for candidate binders with a total size of 175 amino acid residues, flexible framework, and internal variable payload of 104 amino acids; ideal for mini-protiens and VHH designs.
* Support for `expression`, `binding`, and `specificity` data labels.
* Native support for replicates, multiple antigen doses, unique molecular identifiers (UMIs).