SIMULATED ANNEALING AND BOLTZMANN MACHINES A Stochastic Approach to Combinatorial Optimization and Neural Computing

Nature-inspired meta-heuristic algorithms have dominated the scientific literature in the areas of machine learning and cognitive computing paradigm in the last three decades. Chemical reaction optimisation (CRO) is a population-based meta-heuristic algorithm based on the principles of chemical reaction. A chemical reaction is seen as a process of transforming the reactants (or molecules) through a sequence of reactions into products. This process of transformation is implemented in the CRO algorithm to solve optimisation problems. This article starts with an overview of the chemical reactions and how it is applied to the optimisation problem. A review of CRO and its variants is presented in the paper. Guidelines from the literature on the effective choice of CRO parameters for solution of optimisation problems are summarised.

/pdf/nature-inspired-chemical-reaction-optimisation-algorithms-29vdthnooe.pdf

Nature-Inspired Chemical Reaction Optimisation Algorithms.

TACAS'2011, 17th International ConferenceTools and Algorithms for the Construction and Analysis of Systems.

We discuss some motivational challenges arising from the need to model and analyse complex biological systems at multiple scales (spatial and temporal), and present a biomodel engineering framework to address some of these issues within the context of multiscale Systems Biology. Our methodology is based on a structured family of Petri net classes which enables the investigation of a given system using various modelling abstractions: qualitative, stochastic, continuous and hybrid, optionally in a spatial context. We illustrate our approach with case studies demonstrating hierarchical flattening, treatment of space, and hierarchical organisation of space.

/pdf/biomodel-engineering-for-multiscale-systems-biology-2jgpd9nwfq.pdf

BioModel engineering for multiscale Systems Biology

Clinical practice guidelines identify lithium as a first line treatment for mood stabilization and reduction of suicidality in bipolar disorders (BD); however, most individuals show sub-optimal response. Identifying biomarkers for lithium response could enable personalization of treatment and refine criteria for stratification of BD cases into treatment-relevant subgroups. Existing systematic reviews identify potential biomarkers of lithium response, but none directly address the conceptual issues that need to be addressed to enhance translation of research into precision prescribing of lithium. For example, although clinical syndrome subtyping of BD has not led to customized individual treatments, we emphasize the importance of assessing clinical response phenotypes in biomarker research. Also, we highlight the need to give greater consideration to the quality of prospective longitudinal monitoring of illness activity and the differentiation of non-response from partial or non-adherence with medication. It is unlikely that there is a single biomarker for lithium response or tolerability, so this review argues that more research should be directed toward the exploration of biosignatures. Importantly, we emphasize that an integrative science approach may improve the likelihood of discovering the optimal combination of clinical factors and multimodal biomarkers (e.g., blood omics, neuroimaging, and actigraphy derived-markers). This strategy could uncover a valid lithium response phenotype and facilitate development of a composite prediction algorithm. Lastly, this narrative review discusses how these strategies could improve eligibility criteria for lithium treatment in BD, and highlights barriers to translation to clinical practice including the often-overlooked issue of the cost-effectiveness of introducing biomarker tests in psychiatry.

/pdf/can-an-integrated-science-approach-to-precision-medicine-3tmorksy98.pdf

Can an Integrated Science Approach to Precision Medicine Research Improve Lithium Treatment in Bipolar Disorders

Computational modelling of biochemical systems based on top-down and bottom-up approaches has been well studied over the last decade. In this research, after illustrating how to generate atomic components by a set of given reactants and two user pre-defined component patterns, we propose an integrative top-down and bottom-up modelling approach for stepwise qualitative exploration of interactions among reactants in biochemical systems. Evolution strategy is applied to the top-down modelling approach to compose models, and simulated annealing is employed in the bottom-up modelling approach to explore potential interactions based on models constructed from the top-down modelling process. Both the top-down and bottom-up approaches support stepwise modular addition or subtraction for the model evolution. Experimental results indicate that our modelling approach is feasible to learn the relationships among biochemical reactants qualitatively. In addition, hidden reactants of the target biochemical system can be obtained by generating complex reactants in corresponding composed models. Moreover, qualitatively learned models with inferred reactants and alternative topologies can be used for further web-lab experimental investigations by biologists of interest, which may result in a better understanding of the system.

/pdf/an-integrative-top-down-and-bottom-up-qualitative-model-1s038vuo68.pdf

An integrative top-down and bottom-up qualitative model construction framework for exploration of biochemical systems

Modelling biochemical systems has received considerable attention over the last decade from scientists and engineers across a number of fields, including biochemistry, computer science, and mathematics. Due to the complexity of biochemical systems, it is natural to construct models of the biochemical systems incrementally in a piecewise manner. This paper proposes a hybrid approach which applies an evolutionary algorithm to select and compose pre-defined building blocks from a library of atomic models, mutating their products, thus generating complex systems in terms of topology, and employs a global optimization algorithm to fit the kinetic rates. Experiments using two signalling pathways show that given target behaviours it is feasible to explore the model space by this hybrid approach, generating a set of synthetic models with alternative structures and similar behaviours to the desired ones.

/pdf/a-hybrid-approach-to-piecewise-modelling-of-biochemical-3fbm5u4pch.pdf

A hybrid approach to piecewise modelling of biochemical systems

In this paper we describe a method and an associated computational tool to modify and piecewise enlarge the topology of a biological network model, using a set of biochemical components, in order to generate one or more models whose behaviours simulate that of a target biological system. These components are defined as continuous Petri nets and stored in a library for ease of reuse. An optimization algorithm is proposed which exploits Simulated Annealing in order to alter an initial model by reference to the desired behaviour of the target model.Simulation results on a realistic illustrative example signalling pathway show that the proposed method performs well in terms of exploiting the characteristics of simulated annealing in order to generate interesting models with behaviours close to that of the target biochemical system without any pre-knowledge on the target topology itself. In future work we plan to use the generated topologies as population candidates when using an evolutionary approach to further tune the network structure and kinetic parameters.

Target driven biochemical network reconstruction based on petri nets and simulated annealing

Both qualitative and quantitative model learning frameworks for biochemical systems have been studied in computational systems biology. In this research, after introducing two forms of pre-defined component patterns to represent biochemical models, we propose an integrative qualitative and quantitative modelling framework for inferring biochemical systems. In the proposed framework, interactions between reactants in the candidate models for a target biochemical system are evolved and eventually identified by the application of a qualitative model learning approach with an evolution strategy. Kinetic rates of the models generated from qualitative model learning are then further optimised by employing a quantitative approach with simulated annealing. Experimental results indicate that our proposed integrative framework is feasible to learn the relationships between biochemical reactants qualitatively and to make the model replicate the behaviours of the target system by optimising the kinetic rates quantitatively. Moreover, potential reactants of a target biochemical system can be discovered by hypothesising complex reactants in the synthetic models. Based on the biochemical models learned from the proposed framework, biologists can further perform experimental study in wet laboratory. In this way, natural biochemical systems can be better understood.

/pdf/an-integrated-qualitative-and-quantitative-biochemical-model-szuymi3ltq.pdf

An Integrated Qualitative and Quantitative Biochemical Model Learning Framework Using Evolutionary Strategy and Simulated Annealing

Modelling biochemical networks can be achieved by iteratively analyzing parts of the systems via top-down or bottom-up approaches It is feasible to piece-wise model the biochemical networks from scratch by employing strategies able to assemble reusable components In this paper, we investigate a set of strategies that can be employed in a bottom-up piece-wise modelling framework, to obtain synthetic models with similar behaviour to the target systems A combination of evolution strategies and simulated annealing is employed to optimize the structure of the system and its kinetic rates Simulation results of different variants of those computational methods on a standard signaling pathway show that it is feasible to obtain a tradeoff between the generation of desired behaviour and similar and alternative topologies

/pdf/empirical-study-of-computational-intelligence-strategies-for-1znhopqazw.pdf

Zujian Wu

Papers

An integrative top-down and bottom-up qualitative model construction framework for exploration of biochemical systems

A hybrid approach to piecewise modelling of biochemical systems

Target driven biochemical network reconstruction based on petri nets and simulated annealing

An Integrated Qualitative and Quantitative Biochemical Model Learning Framework Using Evolutionary Strategy and Simulated Annealing

Empirical Study of Computational Intelligence Strategies for Biochemical Systems Modelling