Search

Bent Boolean functions are important objects in cryptography and coding theory, and there are several general approaches for constructing such functions. Metaheuristics proved to be a strong choice as they can provide many bent functions, even when the size of the Boolean function is large (e.g., more than 20 inputs). While bent Boolean functions represent only a small part of all Boolean functions, there are several subclasses of bent functions providing specific properties and challenges. One of the more interesting subclasses comprises (anti-)self-dual bent Boolean functions.This paper provides a detailed experimentation with evolutionary algorithms with the goal of evolving (anti-)self-dual bent Boolean functions. We experiment with two encodings and two fitness functions to evolve self-dual bent Boolean functions. Our experiments consider Boolean functions with sizes of up to 16 inputs, and we successfully construct self-dual bent functions for each dimension. Moreover, we notice that the difficulty of evolving self-dual bent functions is similar to evolving bent Boolean functions, despite self-dual bent functions being much rarer.

Contains fulltext : 306262.pdf (Publisher’s version ) (Closed access), EuroGP 2024

EvoApplications 2022, Item does not contain fulltext

Background: The ability to accurately classify cancer patients into risk classes, i.e. to predict the outcome of the pathology on an individual basis, is a key ingredient in making therapeutic decisions. In recent years gene expression data have been successfully used to complement the clinical and histological criteria traditionally used in such prediction. Many “gene expression signatures” have been developed, i.e. sets of genes whose expression values in a tumor can be used to predict the outcome of the pathology. Here we investigate the use of several machine learning techniques to classify breast cancer patients using one of such signatures, the well established 70-gene signature. Results: We show that Genetic Programming performs significantly better than Support Vector Machines, Multilayered Perceptrons and Random Forests in classifying patients from the NKI breast cancer dataset, and comparably to the scoring-based method originally proposed by the authors of the 70-gene signature. Furthermore, Genetic Programming is able to perform an automatic feature selection. Conclusions: Since the performance of Genetic Programming is likely to be improvable compared to the out-of-the-box approach used here, and given the biological insight potentially provided by the Genetic Programming solutions, we conclude that Genetic Programming methods are worth further investigation as a tool for cancer patient classification based on gene expression data.

We present a new reverse-engineering framework for gene regulatory network reconstruction. It works on temporal series of gene activation data and, using genetic programming, it extracts the activation functions of the different genes from those data. Successively, the gene regulatory network is reconstructed exploiting the automatic feature selection performed by genetic programming and its dynamics can be simulated using the previously extracted activation functions. The framework was tested on the well-known IRMA gene regulatory network, a simple network composed by five genes in the yeast Saccharomyces cerevisiae, defined in 2009 as a simplified biological model to benchmark reverse-engineering approaches. We show that the performances of the proposed framework on this benchmark network are encouraging

The inference of gene regulatory networks from expression data is an important area of research that provides insight to the inner workings of a biological system. In this paper we present a new reverse-engineering framework for gene regulatory network reconstruction. It exploits some interesting characteristics of genetic programming, like the ability of solving complex regression problems with little or no information about the underlying data and the ability of performing an automatic selection of features at learning time. Our framework not only reconstructs the topology of the network, but it is also able to simulate its dynamic behaviour, forecasting the gene expression values in the timepoints subsequent to the initial one. In this paper, we test the proposed framework on the well-known IRMA gene regulatory network, and we show that its performances are promising.

The study presents neuropsychiatric profiles of children aged 11 with autism spectrum disorder, assessed before 4.5 years, and after interventions. The original group comprised a community sample of 208 children with ASD. Parents of 128 participated-34 with average intellectual function, 36 with borderline intellectual function and 58 with intellectual disability. They were interviewed using the Autism-Tics, AD/HD and other Comorbidities interview. Criteria for a clinical/subclinical proxy of ASD were met by 71, 89 and 95 %, respectively. Criteria for at least one of ASD, AD/HD, Learning disorder or Developmental Coordination Disorder were met by 82, 94 and 97 %. More than 90 % of children with a preschool diagnosis of ASD have remaining neuropsychiatric problems at 11, despite early intervention.

Risk stratification of cancer patients, that is the prediction of the outcome of the pathology on an individual basis, is a key ingredient in making therapeutic decisions. In recent years the use of gene expression profiling in combination with the clinical and histological criteria traditionally used in such a prediction has been successfully introduced. Sets of genes whose expression values in a tumor can be used to predict the outcome of the pathology (gene expression signatures) were introduced and tested by many research groups. A well-known such signature is the 70-gene signature, on which we recently tested several machine learning techniques in order to maximize its predictive power. Genetic Programming (GP) was shown to perform significantly better than other techniques including Support Vector Machines, Multilayered Perceptrons and Random Forests in classifying patients. Genetic Programming has the further advantage, with respect to other methods, of performing an automatic feature selection. Importantly, by using a weighted average between false positives and false negatives in the definition of the fitness, we showed that GP can outperform all the other methods in minimizing false negatives (one of the main goals in clinical applications) without compromising the overall minimization of incorrectly classified instances. The solutions returned by GP are appealing also from a clinical point of view, being simple, easy to understand, and built out of a rather limited subset of the available features.

Contains fulltext : 93791.pdf (preprint version ) (Closed access)

Parameter estimation (PE) of biological systems is one of the most challenging problems in Systems Biology. Here we present a PE method that integrates particle swarm optimization (PSO) to estimate the value of kinetic constants, and a stochastic simulation algorithm to reconstruct the dynamics of the system. The fitness of candidate solutions, corresponding to vectors of reaction constants, is defined as the point-to-point distance between a simulated dynamics and a set of experimental measures, carried out using discrete-time sampling and various initial conditions. A multi-swarm PSO topology with different modalities of particles migration is used to account for the different laboratory conditions in which the experimental data are usually sampled. The whole method has been specifically designed and entirely executed on the GPU to provide a reduction of computational costs.We show the effectiveness of our method and discuss its performances on an enzymatic kinetics and a prokaryotic gene expression network.

In most theories concerning the origin of life autocatalytic sets are supposed to play an important role in the phase transition between non-living and living matter. Although several theoretical models describe this phase transition, it is very hard to recreate the experimental conditions in wet lab. We here introduce a stochastic model of catalytic reaction networks with energy constraints, devoted to the study of the emergence of autocatalytic sets, in which some of the assumptions of the already existing model are relaxed in order to explore the possible reasons which make the emergence of autocatalytic cycles difficult or which make them unstable. Moreover, since living systems operate with a continuous exchange of matter and energy with the environment, we investigate the effects on the model behavior of changes in the rate of the energy intake.

The classification of cancer patients into risk classes is a very active field of research, with direct clinical applications. We have recently compared several machine learning methods on the well known 70-genes signature dataset. In that study, genetic programming showed promising results, given that it outperformed all the other techniques. Nevertheless, the study was preliminary, mainly because the validation dataset was preprocessed and all its features binarized in order to use logical operators for the genetic programming functional nodes. If this choice allowed simple interpretation of the solutions from the biological viewpoint, on the other hand the binarization of data was limiting, since it amounts to a sizable loss of information. The goal of this paper is to overcome this limitation, using the 70-genes signature dataset with real-valued expression data. The results we present show that genetic programming using the number of incorrectly classified instances as fitness function is not able to outperform the other machine learning methods. However, when a weighted average between false positives and false negatives is used to calculate fitness values, genetic programming obtains performances that are comparable with the other methods in the minimization of incorrectly classified instances and outperforms all the other methods in the minimization of false negatives, which is one of the main goals in breast cancer clinical applications. Also in this case, the solutions returned by genetic programming are simple, easy to understand, and they use a rather limited subset of the available features.

The ability to accurately classify cancer patients into risk classes, i.e. to predict the outcome of the pathology on an individual basis, is a key ingredient in making therapeutic decisions. In recent years gene expression data have been successfully used to complement the clinical and histological criteria traditionally used in such prediction. Many "gene expression signatures" have been developed, i.e. sets of genes whose expression values in a tumor can be used to predict the outcome of the pathology. Here we investigate the use of several machine learning techniques to classify breast cancer patients using one of such signatures, the well established 70-gene signature. We show that Genetic Programming performs significantly better than Support Vector Machines, Multilayered Perceptron and Random Forest in classifying patients from the NKI breast cancer dataset, and slightly better than the scoring-based method originally proposed by the authors of the seventy-gene signature. Furthermore, Genetic Programming is able to perform an automatic feature selection. Since the performance of Genetic Programming is likely to be improvable compared to the out-of-the-box approach used here, and given the biological insight potentially provided by the Genetic Programming solutions, we conclude that Genetic Programming methods are worth further investigation as a tool for cancer patient classification based on gene expression data. © 2010 Springer-Verlag Berlin Heidelberg.

7th European Conference, EvoBIO 2009 Tübingen, Germany, 15 april 2009, Contains fulltext : 75322.pdf (preprint version ) (Open Access)

The modelling of biochemical systems requires the knowledge of several quantitative parameters (e.g. reaction rates) which are often hard to measure in laboratory experiments. Furthermore, when the system involves small numbers of molecules, the modelling approach should also take into account the effects of randomness on the system dynamics. In this paper, we tackle the problem of estimating the unknown parameters of stochastic biochemical systems by means of two optimization heuristics, genetic algorithms and particle swarm optimization. Their performances are tested and compared on two basic kinetics schemes: the Michaelis-Menten equation and the Brussellator. The experimental results suggest that particle swarm optimization is a suitable method for this problem. The set of parameters estimated by particle swarm optimization allows us to reliably reconstruct the dynamics of the Michaelis-Menten system and of the Brussellator in the oscillating regime. © Springer-Verlag Berlin Heidelberg 2009.

Negative Slope Coefficient is an indicator of problem hardness that has been introduced in 2004 and that has returned promising results on a large set of problems. It is based on the concept of fitness cloud and works by partitioning the cloud into a number of bins representing as many different regions of the fitness landscape. The measure is calculated by joining the bins centroids by segments and summing all their negative slopes. In this paper, for the first time, we point out a potential problem of the Negative Slope Coefficient: we study its value for different instances of the well known NK-landscapes and we show how this indicator is dramatically influenced by the minimum number of points contained in a bin. Successively, we formally justify this behavior of the Negative Slope Coefficient and we discuss pros and cons of this measure. ©Springer-Verlag Berlin Heidelberg 2009.

This paper proposes a novel Ant Colony Optimisation algorithm for the hierarchical problem of predicting protein functions using the Gene Ontology (GO). The GO structure represents a challenging case of hierarchical classification, since its terms are organised in a direct acyclic graph fashion where a term can have more than one parent in contrast to only one parent in tree structures. The proposed method discovers an ordered list of classification rules which is able to predict all GO terms independently of their level. We have compared the proposed method against a baseline method, which consists of training classifiers for each GO terms individually, in five different ion-channel data sets and the results obtained are promising.