---
title: FolDE in Evolutionary Design
url: https://www.emergentmind.com/topics/folde
type: topic
---

# FolDE in Evolutionary Design

Searching arXiv for papers using the term “FolDE” to ground the article in relevant sources.
FolDE is a polysemous research term used in at least two distinct technical senses on arXiv. In protein engineering, it denotes **“Foldy’s Directed Evolution”**, an active-learning-assisted directed evolution workflow for **low-\(N\)** optimization campaigns in which only a small number of mutants can be assayed per round [2510.24053]. In experimental evolution, it refers to the **“fold or die”** selection regime applied to **Oli** populations, where short oligonucleotides are selected for their ability to **fold into a hairpin that self-primes** under a defined temperature [1211.4223]. A broader, looser usage also appears in active-matter research, where **FolDE-style folding design** describes the inverse design of active-force sequences that drive colloidal chains into target folded structures [2202.03890]. Across these usages, the common motif is that folding is treated not merely as a structural phenomenon but as a selectable, designable, or optimizable property.

## 1. FolDE as “Foldy’s Directed Evolution”

FolDE in the protein-engineering sense is an **active-learning-assisted directed evolution framework** designed for the **low-\(N\)** regime, where a laboratory can measure only a small number of mutants per round [2510.24053]. Its stated objective is to maximize **end-of-campaign success**, rather than simply maximize immediate per-round exploitation. The motivating problem is that many existing ALDE workflows select the highest-predicted mutants in each round, yielding **homogeneous training data** that can degrade prediction quality in later rounds.

The method is built around two identified failure modes. The first is **round-1 vs. round-2 tension**: selecting the most natural mutants in round 1 produces stronger immediate hits than random selection, but these samples are concentrated in a narrow high-naturalness region and therefore provide poor training data for the next round. The second is **homogeneous later-round batches**: top-ranked mutants in later rounds are often near-duplicates of existing winners, so the batch contributes little exploration or new information [2510.24053].

This formulation places FolDE within the broader ALDE literature, but with a specific emphasis on preserving model quality over short, measurement-limited campaigns. A plausible implication is that the framework is intended less as a single-step ranking scheme than as a sequential data-acquisition policy for rugged, epistatic protein fitness landscapes.

## 2. Methodological components of the low-\(N\) protein-engineering framework

The first major component is **naturalness-based warm-starting from protein language model outputs**. Naturalness is defined as a log-likelihood ratio between mutant and wild type at the mutated positions:

\[
\text{Naturalness}(x', x) = \sum_{i \in T} \log P(x'_i \mid x, \theta) - \log P(x_i \mid x, \theta)
\]

where \(x\) is the wild-type sequence, \(x'\) is the mutant, \(T\) is the set of mutated positions, and \(P(\cdot \mid x,\theta)\) is the PLM’s distribution over amino acids given the sequence context [2510.24053]. This quantity is computed with a **single forward pass** through the PLM. It is used both for **zero-shot round-1 selection** and for **warm-start pretraining** of the neural top layer on naturalness scores for **all possible single mutants**.

The paper identifies warm-starting as the critical mechanism preventing supervised model collapse in round 2. Without it, when round-1 data consist only of the highest-naturalness mutants, the supervised model is trained on a narrow and biased distribution. In the reported benchmarks, the paper states that round-2 Spearman correlation collapses from about **0.48** to **0.04** without warm-start [2510.24053]. The supervised model uses an **ensemble of neural networks** with a **ranking loss**; the top layer is an **MLP over PLM embeddings**, and training is based on **pairwise Bradley–Terry ranking loss** \(\mathcal{L}_{BT}\) [2510.24053].

The second major component is a **constant-liar batch selector**. After selecting a high-performing mutant, the algorithm inserts a pessimistic imagined observation and updates the covariance structure so that similar candidates are downweighted. The paper gives the covariance update as

\[
\mathbf{\Sigma}' = \mathbf{\Sigma}_{M \setminus i} - \mathbf{v}\mathbf{v}^{T}/\sigma_i^2
\]

and the mean update as

\[
y'_{M \setminus i} = y_{M \setminus i} + \mathbf{v}\,(y_i^{\text{lie} - y_i)/\sigma_i^2.
\]

The lie is pessimistic:

\[
y_i^{\text{lie} = \min(y_i),
\]

and the method adds a scaled observation noise term \(I \cdot \alpha \cdot \text{(median variance)}\) to stabilize selection [2510.24053]. The paper states that **lower \(\alpha\)** yields a more aggressive lie and more exploration, while **higher \(\alpha\)** approaches pure exploitation.

## 3. Evaluation and reported performance of “Foldy’s Directed Evolution”

FolDE was evaluated **in silico** on **ProteinGym** datasets using **9 proteins** for workflow development/training, **17 single-mutation test proteins**, and **3 multi-mutation test proteins**, for **20 test protein targets** in total [2510.24053]. The simulation protocol used **3 rounds**, **16 mutants per round**, and **48 total mutants per campaign**. The primary campaign-level metrics were the **cumulative number of top 10% mutants discovered** and the **probability of finding at least one top 1% mutant within 3 rounds**.

Across all **20 test proteins**, the paper reports that FolDE discovered **23% more top 10% mutants** than the random-forest baseline and had a **55% higher likelihood of finding a top 1% mutant**. The top-10% comparison is reported as significant with **\(p = 0.005\)** by one-sided Wilcoxon signed-rank test, and the top-1% comparison with **\(p = 0.037\)** [2510.24053]. Compared with zero-shot naturalness selection, FolDE found **6% more top 10% mutants** and had a **15% higher probability of finding a top 1% mutant**, with reported significance **\(p = 0.009\)** and **\(p = 0.003\)** respectively [2510.24053].

The paper further states that zero-shot selection fails to find any top 1% mutant in **5 of 20 targets**, whereas FolDE achieves nonzero probability for **all targets**. On the **17 single-mutation targets**, FolDE found **13% more top 10% mutants** than random forest and improved the probability of finding at least one top 1% mutant by **50%**. On the **3 multi-mutation targets**, it found a median of **96% more top 10% mutants** than random forest and increased the median probability of finding a top 1% mutant by **2.25×** [2510.24053].

The ablation results identify **round-1 zero-shot prediction**, **naturalness warm-start**, and **ranking loss** as the largest contributors to performance. The **constant-liar** component had a smaller effect on the headline benchmark metrics, though the paper argues that it may matter more in larger multi-mutation campaigns where batch redundancy is more severe [2510.24053].

## 4. FolDE as “fold or die” experimental evolution

A different use of FolDE appears in **“Fold or die: experimental evolution in vitro”**, where the term denotes a **fold-or-die experimental evolution** system or selection regime acting on **Oli populations** [1211.4223]. Here the “organism” is **Oli**, short for **short oligonucleotide**. Oli is a **single-stranded DNA hairpin** designed so that, at the ancestral state, it can fold at about **45°C** into a hairpin structure that brings its \(5'\) and \(3'\) ends into proximity. Selection acts on whether the molecule can **fold into a hairpin that self-primes** under the imposed temperature.

The system is a PCR-based analog of microbial experimental evolution and is described as tractable at the **genetic, genomic, phenotypic and fitness levels** [1211.4223]. The genotype–phenotype–fitness mapping is explicit:

- **Genotype**: DNA sequence  
- **Phenotype**: predicted/folded hairpin structure and ability to self-prime  
- **Fitness**: success in subsequent PCR amplification  

The selection cycle consists of **self-priming under a defined temperature**, **qPCR-based amplification**, **restriction digestion**, and **transfer to the next round** [1211.4223]. In a single cycle, dilute Oli populations are incubated with dNTPs and polymerase at a chosen temperature, primers are added, qPCR amplification occurs, the extended \(3'\) ends are removed by **BsaI** and **HpyAV**, and a diluted subsample is transferred to the next cycle. The restriction-digestion step prevents escape by extension products that would otherwise bypass the folding requirement.

This usage of FolDE differs sharply from the protein-engineering workflow of 2025. In the 2012 system, FolDE is not a computational acquisition policy but a laboratory selection regime in which folding itself is the selectable trait [1211.4223].

## 5. Fitness, dynamics, and findings in the Oli/FolDE system

Fitness in the Oli system is measured from the **qPCR growth curve**. The paper defines **population-level fitness** as the **rate at which the population increases**, operationalized as the **slope of the qPCR curve during the log-linear phase**, referred to in the Results as the **relative slope** [1211.4223]. The narrative gives the usual PCR growth form

\[
N_t \approx N_0 (1+E)^t
\]

and the fitness proxy

\[
\text{fitness} \propto \frac{d \log N_t}{dt}.
\]

The ancestral Oli molecule is a **107 bp** single-stranded DNA sequence derived from a published **HIV-1 hairpin**. The experiment started from roughly **30,000 molecules** per population and used **56 independent replicate populations** under four regimes: **Control**, **Sudden change**, **Rapid change**, and **Slow change**. All temperature treatments total the same environmental shift of **15°C**, from **55°C to 70°C**, but differ in the rate of change [1211.4223].

The proof-of-principle experiment showed that **adaptation occurs under rising temperature**. All three temperature-increase treatments evolved **higher fitness** than the control, and **slower environmental change led to higher final fitness** [1211.4223]. The study also reports visible **phenotypic evolution in secondary structure**, fluctuating **self-priming ability** across populations, and **lineage diversification and extinction** inferred from lineage-network analysis. Another notable finding is the evolution of **genome length**, including insertions, deletions, and apparent concatamerization or recombination effects, producing what the paper calls the **“tyranny of short motifs”** [1211.4223].

The authors frame the system as a model for building empirical **genotype–phenotype–fitness maps** and emphasize its tractability for studying mutation, epistasis, genome-length effects, and lineage success. This suggests that the fold-or-die meaning of FolDE is best understood as a deliberately minimal experimental platform in which folding is the object of selection rather than the target of prediction.

## 6. Broader and adjacent uses of the term

A broader, more analogical use appears in **“Designing active colloidal folders”**, which describes a **FolDE-style folding design** problem in active matter [2202.03890]. There the task is to choose a binary sequence of propulsion directions in a semiflexible colloidal chain so that the chain reliably collapses into a target folded structure. The model uses monomer self-propulsion **perpendicular to the chain backbone**, with sequence variables \(s_i = \pm 1\), and dynamics

\[
\frac{d\mathbf{r}_i(t)}{dt} = \frac{1}{\gamma}\mathbf{F}(\{r_{ij}\}) + v_p s_i\,\mathbf{n}_i + \sqrt{2D}\,\mathbf{\xi}_i(t)
\]

[2202.03890]. The paper reports a **direct correspondence between the sequence of propulsion directions and the folded structure**, and shows that target folds can be designed using a bias potential

\[
U_f=\frac{b_0}{N-1}\sum_{i=1}^{N-1} \omega_i (\theta_i-\theta^{R}_i)^2
\]

during sequence optimization [2202.03890]. This usage is conceptually aligned with the 2025 protein-engineering FolDE only in the broad sense that both treat folding as a design objective under data or control constraints.

Because these papers do not share a single common formalism, treating FolDE as a unitary term would be misleading. The evidence instead supports a **context-dependent nomenclature**: in 2012, FolDE denotes a **fold-or-die experimental evolution system**; in 2025, it denotes a **low-\(N\) ALDE framework for protein activity optimization**; and in 2022 it appears only as a looser descriptor for a folding-design problem in active colloids [1211.4223; 2510.24053; 2202.03890].

## 7. Conceptual commonalities and distinctions

Despite their different domains, the main FolDE usages share a common structural theme: folding is coupled to a measurable outcome. In the Oli system, the coupling is between **hairpin self-priming** and **qPCR amplification** [1211.4223]. In Foldy’s Directed Evolution, the coupling is between **sequence priors**, **activity prediction**, and **batch selection** under a limited assay budget [2510.24053]. In active colloidal folders, the coupling is between **active-force sequence** and **emergent folded conformation** [2202.03890].

The distinctions are at least as important as the similarities. The 2012 FolDE/Oli system is an **in vitro experimental evolution platform** centered on DNA folding phenotypes. The 2025 FolDE framework is a **computational–experimental protein optimization workflow** centered on active learning and PLM priors. The 2022 active-colloid usage is neither an evolutionary protocol nor a protein-engineering benchmark, but a nonequilibrium sequence-to-shape design problem [1211.4223; 2510.24053; 2202.03890].

This suggests that “FolDE” is best understood not as a single established technical object across disciplines, but as a recurring label attached to research programs that make folding operational: as a criterion for survival, as a target for optimization, or as a programmable design outcome.

Source: https://www.emergentmind.com/topics/folde