Reconstruction of biological networks by supervised machine learning approaches

We review a recent trend in computational systems biology which aims at using pattern recognition algorithms to infer the structure of large-scale biological networks from heterogeneous genomic data. We present several strategies that have been proposed and that lead to different pattern recognition problems and algorithms. The strenght of these approaches is illustrated on the reconstruction of metabolic, protein-protein and regulatory networks of model organisms. In all cases, state-of-the-art performance is reported.

Inference and reconstruction of biological networks from heterogeneous data is currently an active research subject with several important applications in systems biology. The problem has been attacked from many different points of view with varying degrees of success. In particular, predicting new edges with a reasonable false discovery rate is highly demanded for practical applications, but remains extremely challenging due to the sparsity of the networks of interest. While most previous approaches based on the partial knowledge of the network to be inferred build global models to predict new edges over the network, we introduce here a novel method which predicts whether there is an edge from a newly added vertex to each of the vertices of a known network using local models. This involves learning individually a certain subnetwork associated with each vertex of the known network, then using the discovered classification rule associated with only that vertex to predict the edge to the new vertex. Excellent experimental results are shown in the case of metabolic and protein-protein interaction network reconstruction from a variety of genomic data. An implementation of the proposed algorithm is available upon request from the authors.

Fine-Grained Parallel and Distributed Spatial Stochastic Simulation of Biological Reactions

BackgroundOne central goal of computational systems biology is the mathematical modelling of complex metabolic reaction networks. The first and most time-consuming step in the development of such models consists in the stoichiometric reconstruction of the network, i. e. compilation of all metabolites, reactions and transport processes relevant to the considered network and their assignment to the various cellular compartments. Therefore an information system is required to collect and manage data from different databases and scientific literature in order to generate a metabolic network of biochemical reactions that can be subjected to further computational analyses.ResultsThe computer program METANNOGEN facilitates the reconstruction of metabolic networks. It uses the well-known database of biochemical reactions KEGG of biochemical reactions as primary information source from which biochemical reactions relevant to the considered network can be selected, edited and stored in a separate, user-defined database. Reactions not contained in KEGG can be entered manually into the system. To aid the decision whether or not a reaction selected from KEGG belongs to the considered network METANNOGEN contains information of SWISSPROT and ENSEMBL and provides Web links to a number of important information sources like METACYC, BRENDA, NIST, and REACTOME. If a reaction is reported to occur in more than one cellular compartment, a corresponding number of reactions is generated each referring to one specific compartment. Transport processes of metabolites are entered like chemical reactions where reactants and products have different compartment attributes. The list of compartmentalized biochemical reactions and membrane transport processes compiled by means of METANNOGEN can be exported as an SBML file for further computational analysis. METANNOGEN is highly customizable with respect to the content of the SBML output file, additional data-fields, the graphical input form, highlighting of project specific search terms and dynamically generated Web-links.ConclusionMETANNOGEN is a flexible tool to manage information for the design of metabolic networks. The program requires Java Runtime Environment 1.4 or higher and about 100 MB of free RAM and about 200 MB of free HD space. It does not require installation and can be directly Java-webstarted from .

Uncertainty in the structure and parameters of networks is ubiquitous across computational biology. In constraint-based reconstruction and analysis of metabolic networks, this uncertainty is present both during the reconstruction of networks and in simulations performed with them. Here, we present Medusa, a Python package for the generation and analysis of ensembles of genome-scale metabolic network reconstructions. Medusa builds on the COBRApy package for constraint-based reconstruction and analysis by compressing a set of models into a compact ensemble object, providing functions for the generation of ensembles using experimental data, and extending constraint-based analyses to ensemble scale. We demonstrate how Medusa can be used to generate ensembles and perform ensemble simulations, and how machine learning can be used in conjunction with Medusa to guide the curation of genome-scale metabolic network reconstructions. Medusa is available under the permissive MIT license from the Python Packaging Index (https://pypi.org) and from github (https://github.com/opencobra/Medusa), and comprehensive documentation is available at https://medusa.readthedocs.io/en/latest.

During the last three decades, the research area of systems engineering has emerged as a domain of fundamental importance and major impact within chemical engineering, as well as a cornerstone area in interdisciplinary research initiatives with computer science, operations research, applied mathematics, materials and life sciences. This is attributed to the unique characteristics of systems engineering which are the combination of analysis and synthesis for the design, optimization, and operation of processes and products. The product and process discovery research efforts are founded on fundamental advances in mathematical modeling, optimization theory and algorithms, and insights derived either from existing operations and/or from biology, chemistry, and physics. The fundamental advances are epitomized through new theoretical, algorithmic, and modeling frameworks for (a) mixed-integer linear and nonlinear optimization, (b) deterministic global optimization, and (c) dynamic simulation and optimization. The proposed modeling and optimization approaches have multiscale applications ranging from macroscopic to mesoscopic to microscopic systems, and which provide a natural and fundamental link between systems engineering, computational chemistry, computational biology and systems biology. Approaches based on mixed-integer linear and nonlinear optimization which were typically identified with process synthesis, scheduling and planning applications, have entered the domains of gene regulatory networks, metabolic networks, signal transduction networks, beta-sheet topology prediction in proteins, de novo peptide and protein design, DNA recombination, phase problem in X-ray crystallography, side chain optimization in protein prediction, peptide identification via tandem mass spectroscopy. Approaches based on deterministic global optimization associated with process design, synthesis, scheduling, and pooling/blending applications, are now in the main stream of product design, structure prediction in protein folding, dynamics of protein folding, NMR protein structure refinement, and de novo protein design. Approaches based on dynamic models and large scale optimization which were identified with process models and their applications, are suited for metabolic and signal transduction networks. As a result, a synergism between systems engineering, computational biology, and systems biology has evolved gradually, opened new research avenues and has reached the stage where fascinating research contributions address important questions in computational biology with methods and tools from systems engineering which combine mathematical rigor with key biological insights. This article provides a perspective on the challenges and opportunities that emerge from the fundamental developments in the research fields of systems engineering and computational biology. The advances in the areas of deterministic global optimization and process scheduling are introduced first, followed by their respective research opportunities. The revolution of genomics is discussed next with a particular focus on the advances and challenges in the areas of structure prediction in protein folding, de novo peptide and protein design, and peptide and protein identification via tandem mass spectroscopy. This article is based on material presented as an invited talk at the session on “The Future of Chemical Engineering Research III” during the 2004 annual AIChE meeting.

The exploding number of computational models produced by Systems Biologists over the last years is an invitation to structure and exploit this new wealth of information. Researchers would like to trace models relevant to specific scientific questions, to explore their biological content, to align and combine them, and to match them with experimental data. To automate these processes, it is essential to consider semantic annotations, which describe their biological meaning. As a prerequisite for a wide range of computational methods, we propose general and flexible similarity measures for Systems Biology models computed from semantic annotations. By using these measures and a large extensible ontology, we implement a platform that can retrieve, cluster, and align Systems Biology models and experimental data sets. At present, its major application is the search for relevant models in the BioModels Database, starting from initial models, data sets, or lists of biological concepts. Beyond similarity searches, the representation of models by semantic feature vectors may pave the way for visualisation, exploration, and statistical analysis of large collections of models and corresponding data.

Calcific aortic valve disease (CAVD) arises from coupled interactions between blood flow, tissue mechanics, and cellular signaling. Hemodynamic forces influence endothelial and interstitial cell behavior, while the resulting tissue remodeling alters valve motion and flow patterns. Capturing this two-way feedback requires models that integrate fluid-structure mechanics with biochemical regulation, yet such multiscale coupling remains technically challenging. Previous computational models have focused on isolated aspects of the disease: fluid-structure interaction (FSI) simulations reproduce valve deformation and flow, and systems biology (SB) models describe molecular signaling that drives fibrosis and calcification. However, without coupling, these approaches cannot predict how mechanical dysfunction initiates biochemical remodeling or how biochemical changes feed back on mechanics. Here, we present a multi-physics computational framework that couples three-dimensional FSI simulations of aortic valve dynamics with a mechanistic SB model of calcification signaling. The FSI module resolves pulsatile blood flow and leaflet deformation, yielding local wall shear stresses and tissue strains throughout the cardiac cycle. These mechanical quantities are used as inputs to the SB module, which represents key biochemical pathways governing inflammation, TGF- β /SMAD signaling, and nitric-oxide (NO)-mediated inhibition within valvular cells. Simulations predict long-term calcification trajectories for valves of varying thickness, showing that fibrosis-induced stiffening lowers shear stress, reduces NO synthesis, and enhances TGF- β activation, thereby accelerating calcification. The framework is modular and extensible, allowing future incorporation of additional pathways, as well as implementation of full two-way coupling between the FSI and SB models. By integrating physics-based hemodynamics with systems-level biochemistry, this study provides a proof-of-principle demonstration of a next-generation, multi-scale modeling platform for studying cardiovascular disease that unites blood flow dynamics and biochemical signaling.

An Application of Conditional Robust Calibration (CRC) to The Lotka-Volterra Predator-Prey model in computational systems biology: a comparison of two sampling strategies

To better understand the complexity of biological systems, research has shifted from a reductionist to a holistic approach, expanding the focus from single genes to a genome-scale view of gene activity and regulation. This is known as transcriptomics, a continuously growing field generating gene expression signatures from different technologies. A comparable paradigm shift has occurred in computational systems biology with the implementation of Artificial Intelligence (AI) learning models for gene expression analysis and integration. These models enable transcriptome-based profiling to address challenges of data heterogeneity, integration, and updating, assisting human intelligence and enhancing their ability to retrieve, analyze, integrate, and generate data recursively, thanks to their intrinsic predictive, inferential, reinforcement, and generative capabilities. Additionally, while scientists worldwide are still learning how to leverage AI methods that can maintain the human-in-the-loop, a new fundamental change is emerging: agentic AI, which can autonomously act and employ other AI methods to pursue its objectives. As a futuristic perspective, the proposed data analysis pipeline imagines agentic AI systems allowing the automated retrieval and pre-processing of heterogeneous transcriptomics data, analysis and integration with other omics datasets, performed with an incremental updating and recurrent analysis (IURA) model that could allow the detection of guideline updates (e.g., disease reclassification) and the generation of new hypotheses, such as candidate biomarkers or transcriptome-phenotype correlations. Since personalized medicine could derive profound benefits from its use, this scenario also raises important considerations regarding the advantages and concerns associated with the use of scientific AI agents in research and clinical practice.

SummaryDetailed investigation of socially important diseases with modern experimental methods has resulted in the generation of large volume of valuable data. However, analysis and interpretation of this data needs application of efficient computational techniques and systems biology approaches. In particular, the techniques allowing the reconstruction of associative networks of various biological objects and events can be useful. In this publication, the combination of different techniques to create such a network associated with an abstract cell environment is discussed in order to gain insights into the functional as well as spatial interrelationships. It is shown that experimentally gained knowledge enriched with data warehouse content and text mining data can be used for the reconstruction and localization of a cardiovascular disease developing network beginning with MUPP1/MPDZ (multi-PDZ domain protein).

Praise for Computational Systems BiologyApproaches in Cancer Research: "Complex concepts are written clearly and with informative illustrations and useful links. The book is enjoyable to read yet provides sufficient depth to serve as a valuable resource for both students and faculty." — Trey Ideker, Professor of Medicine, UC Xan Diego, School of Medicine "This volume is attractive because it addresses important and timely topics for research and teaching on computational methods in cancer research. It covers a broad variety of approaches, exposes recent innovations in computational methods, and provides acces to source code and to dedicated interactive web sites." — Yves Moreau, Department of Electrical Engineering, SysBioSys Centre for Computational Systems Biology, University of Leuven With the availability of massive amounts of data in biology, the need for advanced computational tools and techniques is becoming increasingly important and key in understanding biology in disease and healthy states. This book focuses on computational systems biology approaches, with a particular lens on tackling one of the most challenging diseases - cancer. The book provides an important reference and teaching material in the field of computational biology in general and cancer systems biology in particular. The book presents a list of modern approaches in systems biology with application to cancer research and beyond. It is structured in a didactic form such that the idea of each approach can easily be grasped from the short text and self-explanatory figures. The coverage of topics is diverse: from pathway resources, through methods for data analysis and single data analysis to drug response predictors, classifiers and image analysis using machine learning and artificial intelligence approaches. Features Up to date using a wide range of approaches Applicationexample in each chapter Online resources with useful applications'

Pectinolytic enzymes are a variety of enzymes involved in breaking down pectin, a complex and abundant plant cell-wall polysaccharide. In nature, pectinolytic enzymes play an essential role in allowing bacteria and fungi to depolymerize and utilize pectin. In addition, pectinases have been widely applied in various industries, such as the food, wine, textile, paper and pulp industries. Due to their important biological function and increasing industrial potential, discovery of novel pectinolytic enzymes has received global interest. However, traditional enzyme characterization relies heavily on biochemical experiments, which are time consuming, laborious and expensive. To accelerate identification of novel pectinolytic enzymes, an automatic approach is needed. We developed a machine learning (ML) approach for predicting pectinases in the industrial workhorse fungus, Aspergillus niger. The prediction integrated a diverse range of features, including evolutionary profile, gene expression, transcriptional regulation and biochemical characteristics. Results on both the training and the independent testing dataset showed that our method achieved over 90 % accuracy, and recalled over 60 % of pectinolytic genes. Application of the ML model on the A. niger genome led to the identification of 83 pectinases, covering both previously described pectinases and novel pectinases that do not belong to any known pectinolytic enzyme family. Our study demonstrated the tremendous potential of ML in discovery of new industrial enzymes through integrating heterogeneous (post-) genomimcs data.

The 12 papers in this special issue focus on computational systems biology. The papers are summarized here.

A selection of papers prepared by participants of 7th Young Scientists School SBB’15 is presented in three Supplementary Issues to the journals of BMC series, namely, BMC Genomics, BMC Genetics and BMC Microbiology. SBB’15 took place June 22nd-25th in Novosibirsk, Russia (http://conf.nsc.ru/sbb2015). The series of Young Scientists Schools in Systems Biology and Bioinformatics (SBB) started several years ago, in 2008, as educational workshop associated with the large international conference series on bioinformatics known as BGRS\SB (Bioinformatics of Genome Regulation and Structure\Systems Biology) (http://conf.bionet.nsc.ru/bgrssb2016). After its inauguration year of 1998, BGRS/SBB held biannually at the Institute of Cytology and Genetics SB RAS in Novosibirsk. In a recent decade, it became a prime meeting venue for biologists, computer scientists, physicists, mathematicians and biochemists working in an interdisciplinary field of systems biology and computer genomics. Being the largest system biology meeting series in Russia, BGRS\SB-14 attracted participants from 27 countries. In the past BioMedCentral had published series of special issues based on best materials presented at the conference in BMC Genomics (http://www.biomedcentral.com/bmcgenomics/supplements/15/S12), BMC Evolutionary Biology (http://www.biomedcentral.com/bmcevolbiol/supplements/15/S1), BMC Genetics (http://www.biomedcentral.com/bmcgenet/supplements/16/S1) and BMC Systems biology (http://www.biomedcentral.com/bmcsystbiol/supplements/9/S2). In addition, the protein structure related studies presented by BGRS/SBB participants were collated as special issues in Journal of Bioinformatics and Computational Biology (http://www.worldscientific.com/toc/jbcb/4113/01; http://www.worldscientific.com/toc/jbcb/11/01). [1] In addition, the SBB School series has its own history to be proud of. The first generation of its participants already matured enough to substantially advance in the field. A majority of the participants graduated with PhDs, and now are contributing to the school as the lecturers and to a number of world universities as professors. For some students, the conference became instrumental in obtaining their post-doc or first independent position in academic world. In many cases, the informal atmosphere of the school helped to spark a collaboration that later led to publications in leading journals or the dramatic changes in their science career. The Program Committee of the conference and SBB Schools series includes data analysis, bioinformatics and computational biology professionals from different countries. For the last decade, the SBB conference was co-chaired by Academician Prof. Nikolay A. Kolchanov of the Institute of Cytology and Genetics SB RAS, Russia and Prof. Dr. Ralf Hofestadt of Bielefeld University, Germany. System biology and bioinformatics are rapidly developing and wide fields of science knowledge. For Young Scientists Schools, every year is different as it comprises the topics for the trainings that are the hottest at the time of the event. In 2015, the SBB School concentrated on the modern genomics and an analysis of high-throughput sequencing data. The materials presented in the current special issue provide examples of seamless integration of experimental studies performed in the lab and the computer-assisted inquiries into in the complex patterns of the organization and the functioning of biologic systems at the molecular, cell, tissue, organ, and body levels. The scientific topics discussed in 2015 were presented at the following sections: Next generation sequencing (NGS) and data analysis Evolutionary bioinformatics Systems biology and gene network modeling In SBB’15 Supplements to BMC journals Genomics, we collected the best studies presented at the conference. Due to the general breadth of the field of Systems Biology and Bioinformatic, the manuscripts were accepted into three separate tracks, thus forming three Supplementary Issues, BMC Genomics, BMC Genetics and BMC Microbiology. Below we will describe contents of these issues.