Iterated local search with partition crossover for computational protein design.

Structure-based computational protein design (CPD) refers to the problem of finding a sequence of amino acids which folds into a specific desired protein structure, and possibly fulfills some targeted biochemical properties. Recent studies point out the particularly rugged CPD energy landscape, suggesting that local search optimization methods should be designed and tuned to easily escape local minima attraction basins. In this article, we analyze the performance and search dynamics of an iterated local search (ILS) algorithm enhanced with partition crossover. Our algorithm, PILS, quickly finds local minima and escapes their basins of attraction by solution perturbation. Additionally, the partition crossover operator exploits the structure of the residue interaction graph in order to efficiently mix solutions and find new unexplored basins. Our results on a benchmark of 30 proteins of various topology and size show that PILS consistently finds lower energy solutions compared to Rosetta fixbb and a classic ILS, and that the corresponding sequences are mostly closer to the native.

Inferring Future Landscapes: Sampling the Local Optima Level.

Connection patterns among Local Optima Networks (LONs) can inform heuristic design for optimisation. LON research has predominantly required complete enumeration of a fitness landscape, thereby restricting analysis to problems diminutive in size compared to real-life situations. LON sampling algorithms are therefore important. In this article, we study LON construction algorithms for the Quadratic Assignment Problem (QAP). Using machine learning, we use estimated LON features to predict search performance for competitive heuristics used in the QAP domain. The results show that by using random forest regression, LON construction algorithms produce fitness landscape features which can explain almost all search variance. We find that LON samples better relate to search than enumerated LONs do. The importance of fitness levels of sampled LONs in search predictions is crystallised. Features from LONs produced by different algorithms are combined in predictions for the first time, with promising results for this "super-sampling": a model to predict tabu search success explained 99% of variance. Arguments are made for the use-case of each LON algorithm and for combining the exploitative process of one with the exploratory optimisation of the other.

Problem Features versus Algorithm Performance on Rugged Multiobjective Combinatorial Fitness Landscapes.

In this article, we attempt to understand and to contrast the impact of problem features on the performance of randomized search heuristics for black-box multiobjective combinatorial optimization problems. At first, we measure the performance of two conventional dominance-based approaches with unbounded archive on a benchmark of enumerable binary optimization problems with tunable ruggedness, objective space dimension, and objective correlation ([Formula: see text]MNK-landscapes). Precisely, we investigate the expected runtime required by a global evolutionary optimization algorithm with an ergodic variation operator (GSEMO) and by a neighborhood-based local search heuristic (PLS), to identify a ([Formula: see text]approximation of the Pareto set. Then, we define a number of problem features characterizing the fitness landscape, and we study their intercorrelation and their association with algorithm runtime on the benchmark instances. At last, with a mixed-effects multilinear regression we assess the individual and joint effect of problem features on the performance of both algorithms, within and across the instance classes defined by benchmark parameters. Our analysis reveals further insights into the importance of ruggedness and multimodality to characterize instance hardness for this family of multiobjective optimization problems and algorithms.

Complete Combinatorial Mutational Enumeration of a protein functional site enables sequence-landscape mapping and identifies highly-mutated variants that retain activity.

Understanding how proteins evolve under selective pressure is a longstanding challenge. The immensity of the search space has limited efforts to systematically evaluate the impact of multiple simultaneous mutations, so mutations have typically been assessed individually. However, epistasis, or the way in which mutations interact, prevents accurate prediction of combinatorial mutations based on measurements of individual mutations. Here, we use artificial intelligence to define the entire functional sequence landscape of a protein binding site in silico, and we call this approach Complete Combinatorial Mutational Enumeration (CCME). By leveraging CCME, we are able to construct a comprehensive map of the evolutionary connectivity within this functional sequence landscape. As a proof of concept, we applied CCME to the ACE2 binding site of the SARS-CoV-2 spike protein receptor binding domain. We selected representative variants from across the functional sequence landscape for testing in the laboratory. We identified variants that retained functionality to bind ACE2 despite changing over 40% of evaluated residue positions, and the variants now escape binding and neutralization by monoclonal antibodies. This work represents a crucial initial stride towards achieving precise predictions of pathogen evolution, opening avenues for proactive mitigation.

Complex-network analysis of combinatorial spaces: the NK landscape case.

We propose a network characterization of combinatorial fitness landscapes by adapting the notion of inherent networks proposed for energy surfaces. We use the well-known family of NK landscapes as an example. In our case the inherent network is the graph whose vertices represent the local maxima in the landscape, and the edges account for the transition probabilities between their corresponding basins of attraction. We exhaustively extracted such networks on representative NK landscape instances, and performed a statistical characterization of their properties. We found that most of these network properties are related to the search difficulty on the underlying NK landscapes with varying values of K .