# US 2026/0099710 A1 · Machine learning for directed evolution

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0099710 A1
- Document ID: US20260099710A1
- Status: Published application
- Kind: A1
- Application number: 19/349,237
- Filed: 2025-10-03
- Published: 2026-04-09
- Earliest claimed: 2024-10-03
- Assignees: Solugen, Inc.
- Applicants: Solugen, Inc.
- Inventors: Carlos Gomez Uribe; Japheth Gado
- Web page: https://patentgrep.com/patent/US20260099710A1

## CPC

- G06N 3/08: Learning methods
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method for protein engineering includes generating a fitness library by performing protein language model (PLM)-guided site selection to identify favorable mutagenesis sites and creating protein variants, training a machine learning model to predict protein fitness from sequence data, wherein the machine learning model comprises a convolutional neural network (CNN); and optimizing protein sequences using a phase transition-based algorithm that dynamically updates a score matrix A of dimensions L×20 using cumulative statistics from sampled sequences and implements heating and cooling cycles to maintain system criticality. The CNN has a three-component sequence representation comprising a latent embedding matrix of shape L×1280, a probability matrix of shape L×20, and a feature vector containing 7 values including normalized zero-shot scores, where L represents the number of residues in the protein, wildtype subtraction normalization applied to the latent embedding matrix, dual parallel convolution processing paths, and percentile-based pooling.

## Claims

### Claim 1

A computer-implemented method for protein engineering comprising:
generating a fitness library by performing protein language model (PLM)-guided site selection to identify favorable mutagenesis sites and creating protein variants having 2 to 5 mutations relative to a parent protein sequence;
training a machine learning model to predict protein fitness from sequence data, wherein the machine learning model comprises a convolutional neural network (CNN) having:
(i) a three-component sequence representation comprising a latent embedding matrix of shape L×1280, a probability matrix of shape L×20, and a feature vector containing 7 values including normalized zero-shot scores, where L represents the number of residues in the protein,
(ii) wildtype subtraction normalization applied to the latent embedding matrix,
(iii) dual parallel convolution processing paths, and
(iv) percentile-based pooling across eleven specific percentiles: 0.01, 0.025, 0.125, 0.25, 0.375, 0.5, 0.625, 0.75, 0.875, 0.975, and 0.99; and
optimizing protein sequences using a phase transition-based algorithm that dynamically updates a score matrix A of dimensions L×20 using cumulative statistics from sampled sequences and implements heating and cooling cycles to maintain system criticality.

### Claim 2 (depends on 1)

The method of claim 1, wherein the fitness library generation comprises site-saturated mutagenesis at selected sites to produce single mutations and random mutagenesis to generate variants with multiple mutations.

### Claim 3 (depends on 1)

The method of claim 1, wherein the three-component sequence representation further comprises normalizing the zero-shot scores by dividing by the number of mutations in each variant.

### Claim 4 (depends on 1)

The method of claim 1, wherein the dual parallel convolution processing paths comprise:
a first path applying convolution followed by dropout, then computing statistics across the sequence dimension to generate vectors for the eleven specified percentiles; and
a second path computing statistical summaries before applying convolution, followed by flattening the output.

### Claim 5 (depends on 1)

The method of claim 1, wherein the machine learning model implements multi-task learning with an output regression layer that simultaneously predicts across multiple experimental conditions using shared activations.

### Claim 6 (depends on 1)

The method of claim 1, wherein the phase transition-based optimization algorithm comprises:
initializing the score matrix A using scores for all single mutants;
sampling N sequences from a Boltzmann distribution based on the score matrix A and temperature T, with mutations selected according to probabilities proportional to e(Aij/T);
evaluating the N sequences using the trained machine learning model; and
updating the score matrix A using update rules:
sum
⁢
of
⁢
scores
ij
=
∑
k
f
⁡
(
S
k
)
×
δ
k
,
i
,
j
observation
⁢
counts
ij
=
∑
k
δ
k
,
i
,
j
A
i
⁢
j
=
A
ij
+
γ
×
std
⁢
err
ij
where δk,i,j is an indicator function and γ is typically set to 1.0.

### Claim 7 (depends on 6)

The method of claim 6, wherein the heating and cooling cycles comprise increasing temperature T by 50% when fewer than 500 high-scoring sequences are identified to prevent sampler collapse.

### Claim 8 (depends on 1)

The method of claim 1, wherein the phase transition-based algorithm exhibits behavior characterized by sudden transitions from low-score states to high-score states, with the optimization behavior modeled using a mixture of two Gaussian distributions representing high-scoring and low-scoring sequence populations.

### Claim 9 (depends on 1)

The method of claim 1, wherein the method reduces required screening campaigns from 5-10 to approximately 2 campaigns while identifying high-fitness protein variants within 500 optimization iterations.

### Claim 10 (depends on 1)

A computing system for protein engineering comprising:
a processor;
a memory coupled to the processor; and
a machine learning model stored in the memory and executable by the processor to perform the method of claim 1.

### Claim 11 (depends on 10)

The computing system of claim 10, further comprising a server system communicably coupled to one or more clients through a network, wherein the server system hosts the machine learning model and processes protein sequence optimization requests.

### Claim 12

A convolutional neural network (CNN) for predicting protein of fitness stored on a non-transitory computer-readable medium configured to implement a series steps comprising:
a three-component sequence representation system comprising:
(i) a latent embedding matrix derived from a protein language model,
(ii) a probability matrix derived from computed probabilities of amino acids from ESM model output logits, and
(iii) a feature vector containing zero-shot scores normalized by mutation count;
wildtype subtraction normalization applied to the latent embedding matrix to indicate mutated residues;
dual parallel convolution processing paths applied separately to embedding and probability matrix representations;
percentile-based pooling configured to extract statistical summaries across eleven specific percentiles: 0.01, 0.025, 0.125, 0.25, 0.375, 0.5, 0.625, 0.75, 0.875, 0.975, and 0.99; and
a multi-layer perceptron with two hidden layers receiving concatenated outputs from the dual convolution paths and the feature vector.

### Claim 13 (depends on 12)

The CNN of claim 12, wherein the percentile-based pooling replaces traditional mean pooling to provide a richer statistical representation of convolved output.

### Claim 14 (depends on 12)

The CNN of claim 12, further comprising multi-task learning implementation with an output regression layer that simultaneously predicts across different experimental conditions using shared activations.

### Claim 15 (depends on 12)

The CNN of claim 12, wherein training employs an optimizer with cosine annealing scheduler over approximately 1,500 epochs using 80% training and 20% validation data splits.

### Claim 16

A sequence optimization algorithm for protein engineering stored on a non-transitory computer-readable medium configured to implement a series steps comprising:
initializing a score matrix A of dimensions L×20 using scores for all single mutants, where L represents sequence length;
sampling N sequences from a Boltzmann distribution based on the score matrix A and temperature T;
evaluating the N sequences using a trained machine learning model;
dynamically updating the score matrix A using cumulative scores and observation counts according to:
A
i
⁢
j
=
A
ij
+
γ
×
std
⁢
err
ij
where the std errij is computed from tracked statistics of sampled sequences; and
implementing heating and cooling cycles to maintain system criticality and prevent sampler collapse.

### Claim 17 (depends on 16)

The algorithm of claim 16, wherein the algorithm exhibits phase transition behavior characterized by sudden transitions from low-score states to high-score states.

### Claim 18 (depends on 16)

The algorithm of claim 16, wherein the optimization behavior is modeled using a theoretical framework based on a mixture of two Gaussian distributions with proportion a of sequences from a high-scoring mode defined as:
α
=
ϵ
⁢
e
-
βμ
1
+
β
2
⁢
σ
1
2
2
ϵ
⁢
e
-
βμ
1
+
β
2
⁢
σ
1
2
2
+
(
1
-
ϵ
)
-
βμ
2
+
β
2
⁢
σ
2
2
2
.

### Claim 19 (depends on 16)

The algorithm of claim 16, wherein the algorithm is configured to identify high-fitness protein variants within computational budgets of 1 million to 100 million sequence evaluations.

### Claim 20

A method for protein language model selection comprising:
evaluating multiple ESM protein language models for zero-shot prediction of experimental fitness measurements on a training dataset of protein sequences;
comparing Spearman correlation coefficients achieved by the multiple ESM models;
selecting a model; and
using the selected model to generate multi-component sequence representations for protein fitness prediction.
