Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Evolutionary Algorithms Simulating Molecular Evolution: A New Field Proposal

James S. L. Browning, Daniel R. Tauritz, John Beckmann

TL;DR

This paper proposes Evolutionary Algorithms Simulating Molecular Evolution (EASME), a framework that merges evolutionary algorithms, machine learning, and bioinformatics to design completely novel, functional proteins by simulating molecular evolution at the DNA level. It argues that ML alone cannot fully capture biophysical grammar or generate true novelty, and that an EA-driven approach can reveal interpretable rules and Pareto-optimal protein variants, potentially accelerating discovery and enabling biotechnological applications. The authors outline a concrete architecture combining DNA-level evolution, grammar-based fitness, de novo folding checks, and a filtering mechanism, with wet-lab synthesis and screening to validate computational hits. They chart a path toward a general EASME toolkit, outline two use cases (reconstructing extinct variants and forward-evolving desired traits), and emphasize the potential impact on biotechnology, agriculture, and our understanding of molecular evolution.

Abstract

The genetic blueprint for the essential functions of life is encoded in DNA, which is translated into proteins -- the engines driving most of our metabolic processes. Recent advancements in genome sequencing have unveiled a vast diversity of protein families, but compared to the massive search space of all possible amino acid sequences, the set of known functional families is minimal. One could say nature has a limited protein "vocabulary." The major question for computational biologists, therefore, is whether this vocabulary can be expanded to include useful proteins that went extinct long ago, or maybe never evolved in the first place. We outline a computational approach to solving this problem. By merging evolutionary algorithms, machine learning (ML), and bioinformatics, we can facilitate the development of completely novel proteins which have never existed before. We envision this work forming a new sub-field of computational evolution we dub evolutionary algorithms simulating molecular evolution (EASME).

Evolutionary Algorithms Simulating Molecular Evolution: A New Field Proposal

TL;DR

This paper proposes Evolutionary Algorithms Simulating Molecular Evolution (EASME), a framework that merges evolutionary algorithms, machine learning, and bioinformatics to design completely novel, functional proteins by simulating molecular evolution at the DNA level. It argues that ML alone cannot fully capture biophysical grammar or generate true novelty, and that an EA-driven approach can reveal interpretable rules and Pareto-optimal protein variants, potentially accelerating discovery and enabling biotechnological applications. The authors outline a concrete architecture combining DNA-level evolution, grammar-based fitness, de novo folding checks, and a filtering mechanism, with wet-lab synthesis and screening to validate computational hits. They chart a path toward a general EASME toolkit, outline two use cases (reconstructing extinct variants and forward-evolving desired traits), and emphasize the potential impact on biotechnology, agriculture, and our understanding of molecular evolution.

Abstract

The genetic blueprint for the essential functions of life is encoded in DNA, which is translated into proteins -- the engines driving most of our metabolic processes. Recent advancements in genome sequencing have unveiled a vast diversity of protein families, but compared to the massive search space of all possible amino acid sequences, the set of known functional families is minimal. One could say nature has a limited protein "vocabulary." The major question for computational biologists, therefore, is whether this vocabulary can be expanded to include useful proteins that went extinct long ago, or maybe never evolved in the first place. We outline a computational approach to solving this problem. By merging evolutionary algorithms, machine learning (ML), and bioinformatics, we can facilitate the development of completely novel proteins which have never existed before. We envision this work forming a new sub-field of computational evolution we dub evolutionary algorithms simulating molecular evolution (EASME).
Paper Structure (12 sections, 4 figures)

This paper contains 12 sections, 4 figures.

Table of Contents

  1. Key Points
  2. Abstract
  3. Keywords
  4. Antecedents of EASME
  5. Defining the Problem
  6. Where Machine Learning Falls Short
  7. Where Evolutionary Algorithms Can Help
  8. Evolutionary Algorithms Simulating Molecular Evolution
  9. Building and Testing the EASME Algorithm
  10. EASME to Date
  11. The Path Forward: Other Use Cases for EASME
  12. What Needs to Happen Next?

Figures (4)

  • Figure 1: The search space of proteins — a vast sea of invalidity contains a handful of islands containing useful, functional proteins, only a small subset of which have likely been evolved by nature.
  • Figure 2: EASME exists at the intersection of computational evolution, computational biology, and molecular evolution, drawing on the strengths of all three to solve problems.
  • Figure 3: Intelligent application of ML can help constrain the search space of proteins.
  • Figure 4: Ways to employ EASME.