# Protein Counterfactuals via Diffusion-Guided Latent Optimization

arXiv: https://arxiv.org/abs/2603.10811 · HTML: https://mlsanity.com/paper/2603.10811/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 44 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Builds on (most cited first, 22 of 22)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Evaluating Protein Transfer Learning with TAPE](https://mlsanity.com/paper/1906.08230/) (2019)
- [Protein structure generation via folding diffusion](https://mlsanity.com/paper/2209.15611/) (2022)
- [Efficient Search for Diverse Coherent Explanations](https://mlsanity.com/paper/1901.04909/) (2019)
- [Diffusion Visual Counterfactual Explanations](https://mlsanity.com/paper/2210.11841/) (2022)
- [Improving DNN Robustness to Adversarial Attacks using Jacobian Regularization](https://mlsanity.com/paper/1803.08680/) (2018)
- [BERTology Meets Biology: Interpreting Attention in Protein Language Models](https://mlsanity.com/paper/2006.15222/) (2020)
- [Diffusion Models for Counterfactual Explanations](https://mlsanity.com/paper/2203.15636/) (2022)
- [Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations](https://mlsanity.com/paper/2103.10226/) (2021)
- [Adversarial Counterfactual Visual Explanations](https://mlsanity.com/paper/2303.09962/) (2023)
- [Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation](https://mlsanity.com/paper/2312.14223/) (2023)
- [Diffeomorphic Counterfactuals with Generative Models](https://mlsanity.com/paper/2206.05075/) (2022)
- [Diffusion-based Iterative Counterfactual Explanations for Fetal Ultrasound Image Quality Assessment](https://mlsanity.com/paper/2403.08700/) (2024)
- [Diffusion on language model encodings for protein sequence generation](https://mlsanity.com/paper/2403.03726/) (2024)
- [Large Language Models Cannot Explain Themselves](https://mlsanity.com/paper/2405.04382/) (2024)
- [Towards Desiderata-Driven Design of Visual Counterfactual Explainers](https://mlsanity.com/paper/2506.14698/) (2025)
- [ReLSO: A Transformer-based Model for Latent Space Optimization and Generation of Proteins](https://mlsanity.com/paper/2201.09948/) (2022)
- [ExplainableFold: Understanding AlphaFold Prediction with Explainable AI](https://mlsanity.com/paper/2301.11765/) (2023)
- [Graph Diffusion Counterfactual Explanation](https://mlsanity.com/paper/2511.16287/) (2025)

## Built on by (most cited first, 3 of 3)

- [SCE-LITE-HQ: Smooth visual counterfactual explanations with generative foundation models](https://mlsanity.com/paper/2603.17048/) (2026)
- [Faithful, Sufficient and Understandable: Rethinking Graph Counterfactual Explanations via Discrete Diffusion Inversion](https://mlsanity.com/paper/2608.12083/) (2026)
- [Towards Fast and Disentangled Counterfactuals for Visual Foundation Models](https://mlsanity.com/paper/2610.00895/) (2026)

## Abstract (arXiv)

Deep learning models can predict protein properties with unprecedented accuracy but rarely offer mechanistic insight or actionable guidance for engineering improved variants. When a model flags an antibody as unstable, the protein engineer is left without recourse: which mutations would rescue stability while preserving function? We introduce Manifold-Constrained Counterfactual Optimization for Proteins (MCCOP), a framework that computes minimal, biologically plausible sequence edits that flip a model's prediction to a desired target state. MCCOP operates in a continuous joint sequence-structure latent space and employs a pretrained diffusion model as a manifold prior, balancing three objectives: validity (achieving the target property), proximity (minimizing mutations), and plausibility (producing foldable proteins). We evaluate MCCOP on three protein engineering tasks - GFP fluorescence rescue, thermodynamic stability enhancement, and E3 ligase activity recovery - and show that it generates sparser, more plausible counterfactuals than both discrete and continuous baselines. The recovered mutations align with known biophysical mechanisms, including chromophore packing and hydrophobic core consolidation, establishing MCCOP as a tool for both model interpretation and hypothesis-driven protein design. Our code is publicly available at github.com/weroks/mccop.