Big data need big theory too

Artificial Intelligence Must Be Made More Scientific

The role of AI within science is growing. Here we assess its impact on research and argue that AI often lacks reproducibility, transparency, objectivity, and mechanistic understanding. To ensure AI benefits research, we need to develop forms of AI that are fully compatible with the scientific method.

Knowledge-driven learning, optimization, and experimental design under uncertainty for materials discovery

Significant acceleration of the future discovery of novel functional materials requires a fundamental shift from the current materials discovery practice, which is heavily dependent on trial-and-error campaigns and high-throughput screening, to one that builds on knowledge-driven advanced informatics techniques enabled by the latest advances in signal processing and machine learning. In this review, we discuss the major research issues that need to be addressed to expedite this transformation along with the salient challenges involved. We especially focus on Bayesian signal processing and machine learning schemes that are uncertainty aware and physics informed for knowledge-driven learning, robust optimization, and efficient objective-driven experimental design.

Is Cancer Reversible? Rethinking Carcinogenesis Models-A New Epistemological Tool

A growing number of studies shows that it is possible to induce a phenotypic transformation of cancer cells from malignant to benign. This process is currently known as "tumor reversion". However, the concept of reversibility hardly fits the current cancer models, according to which gene mutations are considered the primary cause of cancer. Indeed, if gene mutations are causative carcinogenic factors, and if gene mutations are irreversible, how long should cancer be considered as an irreversible process? In fact, there is some evidence that intrinsic plasticity of cancerous cells may be therapeutically exploited to promote a phenotypic reprogramming, both in vitro and in vivo. Not only are studies on tumor reversion highlighting a new, exciting research approach, but they are also pushing science to look for new epistemological tools capable of better modeling cancer.

New horizons in the sociology of sport

The relevance of a sociological view on the problems of society has never been as important as it is today. To quote the editors of the journal Nature in their editorial, Time for the Social Sciences, from 2015: if you want science to deliver for society, you need to support a capacity to understand that society. In other words, the technological and scientific disciplines cannot simply transfer their findings into everyday life without knowing how society works. But this realisation does not seem to have caught on everywhere. The sociology of sport is entering a critical period that will shape its development and potential transformation over the next decade. In this paper, we review key features and trends within the sociology of sport in recent times, and set out potential future challenges and ways forward for the subdiscipline. Accordingly, our discussion spans a wide range of issues concerning the sociology of sport, including theories and approaches, methods, and substantive research topics. We also discuss the potential contributions of the sociology of sport to addressing key societal challenges. To examine these issues, the paper is organized into three main parts. First, we identify three main concentric challenges, or types of peripheral status, that sociologists of sport must confront: as social scientists, as sociologists, and as sociologists of sport, respectively. Second, we consider various strengths within the positions of sociology and the sociology of sport. Third, in some detail, we set out several ways forward for the sociology of sport with respect to positioning within academe, scaling up research, embracing the glocal and cosmopolitan aspects of sociology, enhancing plurality in theory, improving transnational coordination, promoting horizontal collaborations, and building greater public engagement. The paper is underpinned by over 60 years (combined) of work within the sociology of sport, including extensive international research and teaching.

A Unified Neural Network Framework for Extended Redundancy Analysis

Component-based approaches have been regarded as a tool for dimension reduction to predict outcomes from observed variables in regression applications. Extended redundancy analysis (ERA) is one such component-based approach which reduces predictors to components explaining maximum variance in the outcome variables. In many instances, ERA can be extended to capture nonlinearity and interactions between observed and components, but only by specifying a priori functional form. Meanwhile, machine learning methods like neural networks are typically used in a data-driven manner to capture nonlinearity without specifying the exact functional form. In this paper, we introduce a new method that integrates neural networks algorithms into the framework of ERA, called NN-ERA, to capture any non-specified nonlinear relationships among multiple sets of observed variables for constructing components. Simulations and empirical datasets are used to demonstrate the usefulness of NN-ERA. The conclusion is that in social science datasets with unstructured data, where we expect nonlinear relationships that cannot be specified a priori, NN-ERA with its neural network algorithmic structure can serve as a useful tool to specify and test models otherwise not captured by the conventional component-based models.

Machine learning, artificial intelligence, and chemistry: how smart algorithms are reshaping simulation and the laboratory

Machine learning and artificial intelligence are increasingly gaining in prominence through image analysis, language processing, and automation, to name a few applications. Machine learning is also making profound changes in chemistry. From revisiting decades-old analytical techniques for the purpose of creating better calibration curves, to assisting and accelerating traditional in silico simulations, to automating entire scientific workflows, to being used as an approach to deduce underlying physics of unexplained chemical phenomena, machine learning and artificial intelligence are reshaping chemistry, accelerating scientific discovery, and yielding new insights. This review provides an overview of machine learning and artificial intelligence from a chemist’s perspective and focuses on a number of examples of the use of these approaches in computational chemistry and in the laboratory.

More than meets the AI: The possibilities and limits of machine learning in olfaction

Can machine learning crack the code in the nose? Over the past decade, studies tried to solve the relation between chemical structure and sensory quality with Big Data. These studies advanced computational models of the olfactory stimulus, utilizing artificial intelligence to mine for clear correlations between chemistry and psychophysics. Computational perspectives promised to solve the mystery of olfaction with more data and better data processing tools. None of them succeeded, however, and it matters as to why this is the case. This article argues that we should be deeply skeptical about the trend to black-box the sensory system's biology in our theories of perception. Instead, we need to ground both stimulus models and psychophysical data on real causal-mechanistic explanations of the olfactory system. The central question is: Would knowledge of biology lead to a better understanding of the stimulus in odor coding than the one utilized in current machine learning models? That is indeed the case. Recent studies about receptor behavior have revealed that the olfactory system operates by principles not captured in current stimulus-response models. This may require a fundamental revision of computational approaches to olfaction, including its psychological effects. To analyze the different research programs in olfaction, we draw on Lloyd's "Logic of Research Questions," a philosophical framework which assists scientists in explicating the reasoning, conceptual commitments, and problems of a modeling approach in question.

Indirect structural disconnection-symptom mapping

In vivo tracking of white matter fibres catalysed a modern perspective on the pivotal role of brain connectome disruption in neuropsychological deficits. However, the examination of white matter integrity in neurological patients by diffusion-weighted magnetic resonance imaging bears conceptual limitations and is not widely applicable, as it requires imaging-compatible patients and resources beyond the capabilities of many researchers. The indirect estimation of structural disconnection offers an elegant and economical alternative. For this approach, a patient's structural lesion information and normative connectome data are combined to estimate different measures of lesion-induced structural disconnection. Using one of several toolboxes, this method is relatively easy to implement and is even available to scientists without expertise in fibre tracking analyses. Nevertheless, the anatomo-behavioural statistical mapping of structural brain disconnection requires analysis steps that are not covered by these toolboxes. In this paper, we first review the current state of indirect lesion disconnection estimation, the different existing measures, and the available software. Second, we aim to fill the remaining methodological gap in statistical disconnection-symptom mapping by providing an overview and guide to disconnection data and the statistical mapping of their relationship to behavioural measurements using either univariate or multivariate statistical modelling. To assist in the practical implementation of statistical analyses, we have included software tutorials and analysis scripts.

Large Scale Study of Ligand-Protein Relative Binding Free Energy Calculations: Actionable Predictions from Statistically Robust Protocols

The accurate and reliable prediction of protein-ligand binding affinities can play a central role in the drug discovery process as well as in personalized medicine. Of considerable importance during lead optimization are the alchemical free energy methods that furnish an estimation of relative binding free energies (RBFE) of similar molecules. Recent advances in these methods have increased their speed, accuracy, and precision. This is evident from the increasing number of retrospective as well as prospective studies employing them. However, such methods still have limited applicability in real-world scenarios due to a number of important yet unresolved issues. Here, we report the findings from a large data set comprising over 500 ligand transformations spanning over 300 ligands binding to a diverse set of 14 different protein targets which furnish statistically robust results on the accuracy, precision, and reproducibility of RBFE calculations. We use ensemble-based methods which are the only way to provide reliable uncertainty quantification given that the underlying molecular dynamics is chaotic. These are implemented using TIES (Thermodynamic Integration with Enhanced Sampling). Results achieve chemical accuracy in all cases. Ensemble simulations also furnish information on the statistical distributions of the free energy calculations which exhibit non-normal behavior. We find that the "enhanced sampling" method known as replica exchange with solute tempering degrades RBFE predictions. We also report definitively on numerous associated alchemical factors including the choice of ligand charge method, flexibility in ligand structure, and the size of the alchemical region including the number of atoms involved in transforming one ligand into another. Our findings provide a key set of recommendations that should be adopted for the reliable application of RBFE methods.

Artificial intelligence in the field of economics

The history of AI in economics is long and winding, much the same as the evolving field of AI itself. Economists have engaged with AI since its beginnings, albeit in varying degrees and with changing focus across time and places. In this study, we have explored the diffusion of AI and different AI methods (e.g., machine learning, deep learning, neural networks, expert systems, knowledge-based systems) through and within economic subfields, taking a scientometrics approach. In particular, we centre our accompanying discussion of AI in economics around the problems of economic calculation and social planning as proposed by Hayek. To map the history of AI within and between economic sub-fields, we construct two datasets containing bibliometrics information of economics papers based on search query results from the Scopus database and the EconPapers (and IDEAs/RePEc) repository. We present descriptive results that map the use and discussion of AI in economics over time, place, and subfield. In doing so, we also characterise the authors and affiliations of those engaging with AI in economics. Additionally, we find positive correlations between quality of institutional affiliation and engagement with or focus on AI in economics and negative correlations between the Human Development Index and share of learning-based AI papers.

Zero Sales Resistance: The Dark Side of Big Data and Artificial Intelligence

Big data (BD) is the hue and cry of modern science and society. The impact of such data deluge is huge and far reaching for both science and society. Moreover, given the effort required for collecting and analyzing these data, artificial intelligence (AI) has replaced the human mind in accomplishing the enormous task of deriving insight out of the information. In this article, we analyze the role of BD and AI in steering the world population toward the state of Zero Sales Resistance (ZSR): the inability to exert critical judgment over the most seductive aspects of the aforementioned data deluge. Moreover, we discuss the alarming consequences of presenting the merging of BD and AI as a universal panacea even if, to date, they have proven far more efficient for predicting human decisions and behaviors (predictive analytics) than for solving the most critical problems in science and society. Why? Our answer is simple. The causal structures associated with such challenges command a detailed understanding of the underlying mechanisms (causal explanation), typically acting nonlinearly and on a broad range of scales in space and time. In contrast, personality and behavior can be predicted with no need of a microscopic theory and understanding of the brain-mind system (empirical prediction). This is a direct consequence of the fact that our mind, at least for the intuitive level, uses the same prediction techniques applied by AI (bayesian predictions based on our experience). However, prediction is not explanation, and without joining them it will be impossible to achieve a major advance in our understanding of complex systems.

Statistical Physics through the Lens of Real-Space Mutual Information

Identifying the relevant degrees of freedom in a complex physical system is a key stage in developing effective theories in and out of equilibrium. The celebrated renormalization group provides a framework for this, but its practical execution in unfamiliar systems is fraught with ad hoc choices, whereas machine learning approaches, though promising, lack formal interpretability. Here we present an algorithm employing state-of-the-art results in machine-learning-based estimation of information-theoretic quantities, overcoming these challenges, and use this advance to develop a new paradigm in identifying the most relevant operators describing properties of the system. We demonstrate this on an interacting model, where the emergent degrees of freedom are qualitatively different from the microscopic constituents. Our results push the boundary of formally interpretable applications of machine learning, conceptually paving the way toward automated theory building.

Pandemic drugs at pandemic speed: infrastructure for accelerating COVID-19 drug discovery with hybrid machine learning- and physics-based simulations on high-performance computers

The race to meet the challenges of the global pandemic has served as a reminder that the existing drug discovery process is expensive, inefficient and slow. There is a major bottleneck screening the vast number of potential small molecules to shortlist lead compounds for antiviral drug development. New opportunities to accelerate drug discovery lie at the interface between machine learning methods, in this case, developed for linear accelerators, and physics-based methods. The two in silico methods, each have their own advantages and limitations which, interestingly, complement each other. Here, we present an innovative infrastructural development that combines both approaches to accelerate drug discovery. The scale of the potential resulting workflow is such that it is dependent on supercomputing to achieve extremely high throughput. We have demonstrated the viability of this workflow for the study of inhibitors for four COVID-19 target proteins and our ability to perform the required large-scale calculations to identify lead antiviral compounds through repurposing on a variety of supercomputers.

Miasmas, mental models and preventive public health: some philosophical reflections on science in the COVID-19 pandemic

When the history of the COVID-19 pandemic is written, it is likely to show that the mental models held by scientists sometimes facilitated their thinking, thereby leading to lives saved, and at other times constrained their thinking, thereby leading to lives lost. This paper explores some competing mental models of how infectious diseases spread and shows how these models influenced the scientific process and the kinds of facts that were generated, legitimized and used to support policy. A central theme in the paper is the relative weight given by dominant scientific voices to probabilistic arguments based on experimental measurements versus mechanistic arguments based on theory. Two examples are explored: the cholera epidemic in nineteenth century London-in which the story of John Snow and the Broad Street pump is retold-and the unfolding of the COVID-19 pandemic in 2020 and early 2021-in which the evidence-based medicine movement and its hierarchy of evidence features prominently. In each case, it is shown that prevailing mental models-which were assumed by some to transcend theory but were actually heavily theory-laden-powerfully shaped both science and policy, with fatal consequences for some.

Snapshot Wisconsin: networking community scientists and remote sensing to improve ecological monitoring and management

Biological data collection is entering a new era. Community science, satellite remote sensing (SRS), and local forms of remote sensing (e.g., camera traps and acoustic recordings) have enabled biological data to be collected at unprecedented spatial and temporal scales and resolution. There is growing interest in developing observation networks to collect and synthesize data to improve broad-scale ecological monitoring, but no examples of such networks have emerged to inform decision-making by agencies. Here, we present the implementation of one such jurisdictional observation network (JON), Snapshot Wisconsin, which links synoptic environmental data derived from SRS to biodiversity observations collected continuously from a trail camera network to support management decision-making. We use several examples to illustrate that Snapshot Wisconsin improves the spatial, temporal, and biological resolution and extent of information available to support management, filling gaps associated with traditional monitoring and enabling consideration of new management strategies. JONs like Snapshot Wisconsin further strengthen monitoring inference by contributing novel lines of evidence useful for corroboration or integration. SRS provides environmental context that facilitates inference, prediction, and forecasting, and ultimately helps managers formulate, test, and refine conceptual models for the monitored systems. Although these approaches pose challenges, Snapshot Wisconsin demonstrates that expansive observation networks can be tractably managed by agencies to support decision making, providing a powerful new tool for agencies to better achieve their missions and reshape the nature of environmental decision-making.

Snapshot Wisconsin: networking community scientists and remote sensing to improve ecological monitoring and management

Biological data collection is entering a new era. Community science, satellite remote sensing (SRS), and local forms of remote sensing (e.g., camera traps and acoustic recordings) have enabled biological data to be collected at unprecedented spatial and temporal scales and resolution. There is growing interest in developing observation networks to collect and synthesize data to improve broad-scale ecological monitoring, but no examples of such networks have emerged to inform decision-making by agencies. Here, we present the implementation of one such jurisdictional observation network (JON), Snapshot Wisconsin, which links synoptic environmental data derived from SRS to biodiversity observations collected continuously from a trail camera network to support management decision-making. We use several examples to illustrate that Snapshot Wisconsin improves the spatial, temporal, and biological resolution and extent of information available to support management, filling gaps associated with traditional monitoring and enabling consideration of new management strategies. JONs like Snapshot Wisconsin further strengthen monitoring inference by contributing novel lines of evidence useful for corroboration or integration. SRS provides environmental context that facilitates inference, prediction, and forecasting, and ultimately helps managers formulate, test, and refine conceptual models for the monitored systems. Although these approaches pose challenges, Snapshot Wisconsin demonstrates that expansive observation networks can be tractably managed by agencies to support decision making, providing a powerful new tool for agencies to better achieve their missions and reshape the nature of environmental decision-making.

Digital medicine and the curse of dimensionality

Digital health data are multimodal and high-dimensional. A patient's health state can be characterized by a multitude of signals including medical imaging, clinical variables, genome sequencing, conversations between clinicians and patients, and continuous signals from wearables, among others. This high volume, personalized data stream aggregated over patients' lives has spurred interest in developing new artificial intelligence (AI) models for higher-precision diagnosis, prognosis, and tracking. While the promise of these algorithms is undeniable, their dissemination and adoption have been slow, owing partially to unpredictable AI model performance once deployed in the real world. We posit that one of the rate-limiting factors in developing algorithms that generalize to real-world scenarios is the very attribute that makes the data exciting-their high-dimensional nature. This paper considers how the large number of features in vast digital health data can challenge the development of robust AI models-a phenomenon known as "the curse of dimensionality" in statistical learning theory. We provide an overview of the curse of dimensionality in the context of digital health, demonstrate how it can negatively impact out-of-sample performance, and highlight important considerations for researchers and algorithm designers.

A fast and efficient deep learning procedure for tracking droplet motion in dense microfluidic emulsions

We present a deep learning-based object detection and object tracking algorithm to study droplet motion in dense microfluidic emulsions. The deep learning procedure is shown to correctly predict the droplets' shape and track their motion at competitive rates as compared to standard clustering algorithms, even in the presence of significant deformations. The deep learning technique and tool developed in this work could be used for the general study of the dynamics of biological agents in fluid systems, such as moving cells and self-propelled microorganisms in complex biological flows. This article is part of the theme issue 'Progress in mesoscale methods for fluid dynamics simulation'.

Personalization of medical treatments in oncology: time for rethinking the disease concept to improve individual outcomes

The agenda of pharmacology discovery in the field of personalized oncology was dictated by the search of molecular targets assumed to deterministically drive tumor development. In this perspective, genes play a fundamental "causal" role while cells simply act as causal proxies, i.e., an intermediate between the molecular input and the organismal output. However, the ceaseless genomic change occurring across time within the same primary and metastatic tumor has broken the hope of a personalized treatment based only upon genomic fingerprint. Indeed, current models are unable in capturing the unfathomable complexity behind the outbreak of a disease, as they discard the contribution of non-genetic factors, environment constraints, and the interplay among different tiers of organization. Herein, we posit that a comprehensive personalized model should view at the disease as a "historical" process, in which different spatially and timely distributed factors interact with each other across multiple levels of organization, which collectively interact with a dynamic gene-expression pattern. Given that a disease is a dynamic, non-linear process - and not a static-stable condition - treatments should be tailored according to the "timing-frame" of each condition. This approach can help in detecting those critical transitions through which the system can access different attractors leading ultimately to diverse outcomes - from a pre-disease state to an overt illness or, alternatively, to recovery. Identification of such tipping points can substantiate the predictive and the preventive ambition of the Predictive, Preventive and Personalized Medicine (PPPM/3PM). However, an unusual effort is required to conjugate multi-omics approaches, data collection, and network analysis reconstruction (eventually involving innovative Artificial Intelligent tools) to recognize the critical phases and the relevant targets, which could help in patient stratification and therapy personalization.

Ensembles Are Required to Handle Aleatoric and Parametric Uncertainty in Molecular Dynamics Simulation

Classical molecular dynamics is a computer simulation technique that is in widespread use across many areas of science, from physics and chemistry to materials, biology, and medicine. The method continues to attract criticism due its oft-reported lack of reproducibility which is in part due to a failure to submit it to reliable uncertainty quantification (UQ). Here we show that the uncertainty arises from a combination of (i) the input parameters and (ii) the intrinsic stochasticity of the method controlled by the random seeds. To illustrate the situation, we make a systematic UQ analysis of a widely used molecular dynamics code (NAMD), applied to estimate binding free energy of a ligand-bound to a protein. In particular, we replace the usually fixed input parameters with random variables, systematically distributed about their mean values, and study the resulting distribution of the simulation output. We also perform a sensitivity analysis, which reveals that, out of a total of 175 parameters, just six dominate the variance in the code output. Furthermore, we show that binding energy calculations dampen the input uncertainty, in the sense that the variation around the mean output free energy is less than the variation around the mean of the assumed input distributions, if the output is ensemble-averaged over the random seeds. Without such ensemble averaging, the predicted free energy is five times more uncertain. The distribution of the predicted properties is thus strongly dependent upon the random seed. Owing to this substantial uncertainty, robust statistical measures of uncertainty in molecular dynamics simulation require the use of ensembles in all contexts.

Data Analysis will not Result in Knowledge Production about Sepsis

How to cite this article: Sampath S. Data Analysis will not Result in Knowledge Production about Sepsis. Indian J Crit Care Med 2021;25(7):750-751.

Integrating explanation and prediction in computational social science

Computational social science is more than just large repositories of digital data and the computational methods needed to construct and analyse them. It also represents a convergence of different fields with different ways of thinking about and doing science. The goal of this Perspective is to provide some clarity around how these approaches differ from one another and to propose how they might be productively integrated. Towards this end we make two contributions. The first is a schema for thinking about research activities along two dimensions-the extent to which work is explanatory, focusing on identifying and estimating causal effects, and the degree of consideration given to testing predictions of outcomes-and how these two priorities can complement, rather than compete with, one another. Our second contribution is to advocate that computational social scientists devote more attention to combining prediction and explanation, which we call integrative modelling, and to outline some practical suggestions for realizing this goal.

Relevance in the Renormalization Group and in Information Theory

The analysis of complex physical systems hinges on the ability to extract the relevant degrees of freedom from among the many others. Though much hope is placed in machine learning, it also brings challenges, chief of which is interpretability. It is often unclear what relation, if any, the architecture- and training-dependent learned "relevant" features bear to standard objects of physical theory. Here we report on theoretical results which may help to systematically address this issue: we establish equivalence between the field-theoretic relevance of the renormalization group, and an information-theoretic notion of relevance we define using the information bottleneck (IB) formalism of compression theory. We show analytically that for statistical physical systems described by a field theory the relevant degrees of freedom found using IB compression indeed correspond to operators with the lowest scaling dimensions. We confirm our field theoretic predictions numerically. We study dependence of the IB solutions on the physical symmetries of the data. Our findings provide a dictionary connecting two distinct theoretical toolboxes, and an example of constructively incorporating physical interpretability in applications of deep learning in physics.

When we can trust computers (and when we can't)

With the relentless rise of computer power, there is a widespread expectation that computers can solve the most pressing problems of science, and even more besides. We explore the limits of computational modelling and conclude that, in the domains of science and engineering which are relatively simple and firmly grounded in theory, these methods are indeed powerful. Even so, the availability of code, data and documentation, along with a range of techniques for validation, verification and uncertainty quantification, are essential for building trust in computer-generated findings. When it comes to complex systems in domains of science that are less firmly grounded in theory, notably biology and medicine, to say nothing of the social sciences and humanities, computers can create the illusion of objectivity, not least because the rise of big data and machine-learning pose new challenges to reproducibility, while lacking true explanatory power. We also discuss important aspects of the natural world which cannot be solved by digital means. In the long term, renewed emphasis on analogue methods will be necessary to temper the excessive faith currently placed in digital computation. This article is part of the theme issue 'Reliability and reproducibility in computational science: implementing verification, validation and uncertainty quantification in silico'.

Scaling digital twins from the artisanal to the industrial

Mathematical modeling and simulation are moving from being powerful development and analysis tools towards having increased roles in operational monitoring, control and decision support, in which models of specific entities are continually updated in the form of a digital twin. However, current digital twins are largely the result of bespoke technical solutions that are difficult to scale. We discuss two exemplar applications that motivate challenges and opportunities for scaling digital twins, and that underscore potential barriers to wider adoption of this technology.

Application of artificial intelligence in the dental field: A literature review

PURPOSE

The purpose of this study was to comprehensively review the literature regarding the application of artificial intelligence (AI) in the dental field,focusing on the evaluation criteria and architecture types.

STUDY SELECTION

Electronic databases (PubMed, Cochrane Library, Scopus) were searched. Full-text articles describing the clinical application of AI for the detection, diagnosis, and treatment of lesions and the AI method/architecture were included.

RESULTS

The primary search presented 422 studies from 1996 to 2019, and 58 studies were finally selected. Regarding the year of publication, the oldest study, which was reported in 1996, focused on "oral and maxillofacial surgery." Machine-learning architectures were employed in the selected studies, while approximately half of them (29/58) employed neural networks. Regarding the evaluation criteria, eight studies compared the results obtained by AI with the diagnoses formulated by dentists, while several studies compared two or more architectures in terms of performance. The following parameters were employed for evaluating the AI performance: accuracy, sensitivity, specificity, mean absolute error, root mean squared error, and area under the receiver operating characteristic curve.

CONCLUSIONS

Application of AI in the dental field has progressed; however, the criteria for evaluating the efficacy of AI have not been clarified. It is necessary to obtain better quality data for machine learning to achieve the effective diagnosis of lesions and suitable treatment planning.

Integrating Quantitative Assays with Biologically Based Mathematical Modeling for Predictive Oncology

We provide an overview on the use of biological assays to calibrate and initialize mechanism-based models of cancer phenomena. Although artificial intelligence methods currently dominate the landscape in computational oncology, mathematical models that seek to explicitly incorporate biological mechanisms into their formalism are of increasing interest. These models can guide experimental design and provide insights into the underlying mechanisms of cancer progression. Historically, these models have included a myriad of parameters that have been difficult to quantify in biologically relevant systems, limiting their practical insights. Recently, however, there has been much interest calibrating biologically based models with the quantitative measurements available from (for example) RNA sequencing, time-resolved microscopy, and in vivo imaging. In this contribution, we summarize how a variety of experimental methods quantify tumor characteristics from the molecular to tissue scales and describe how such data can be directly integrated with mechanism-based models to improve predictions of tumor growth and treatment response.

Rapid, accurate, precise and reproducible ligand-protein binding free energy prediction

A central quantity of interest in molecular biology and medicine is the free energy of binding of a molecule to a target biomacromolecule. Until recently, the accurate prediction of binding affinity had been widely regarded as out of reach of theoretical methods owing to the lack of reproducibility of the available methods, not to mention their complexity, computational cost and time-consuming procedures. The lack of reproducibility stems primarily from the chaotic nature of classical molecular dynamics (MD) and the associated extreme sensitivity of trajectories to their initial conditions. Here, we review computational approaches for both relative and absolute binding free energy calculations, and illustrate their application to a diverse set of ligands bound to a range of proteins with immediate relevance in a number of medical domains. We focus on ensemble-based methods which are essential in order to compute statistically robust results, including two we have recently developed, namely thermodynamic integration with enhanced sampling and enhanced sampling of MD with an approximation of continuum solvent. Together, these form a set of rapid, accurate, precise and reproducible free energy methods. They can be used in real-world problems such as hit-to-lead and lead optimization stages in drug discovery, and in personalized medicine. These applications show that individual binding affinities equipped with uncertainty quantification may be computed in a few hours on a massive scale given access to suitable high-end computing resources and workflow automation. A high level of accuracy can be achieved using these approaches.

Towards integration of 64Cu-DOTA-trastuzumab PET-CT and MRI with mathematical modeling to predict response to neoadjuvant therapy in HER2 + breast cancer

While targeted therapies exist for human epidermal growth factor receptor 2 positive (HER2 +) breast cancer, HER2 + patients do not always respond to therapy. We present the results of utilizing a biophysical mathematical model to predict tumor response for two HER2 + breast cancer patients treated with the same therapeutic regimen but who achieved different treatment outcomes. Quantitative data from magnetic resonance imaging (MRI) and 64Cu-DOTA-trastuzumab positron emission tomography (PET) are used to estimate tumor density, perfusion, and distribution of HER2-targeted antibodies for each individual patient. MRI and PET data are collected prior to therapy, and follow-up MRI scans are acquired at a midpoint in therapy. Given these data types, we align the data sets to a common image space to enable model calibration. Once the model is parameterized with these data, we forecast treatment response with and without HER2-targeted therapy. By incorporating targeted therapy into the model, the resulting predictions are able to distinguish between the two different patient responses, increasing the difference in tumor volume change between the two patients by > 40%. This work provides a proof-of-concept strategy for processing and integrating PET and MRI modalities into a predictive, clinical-mathematical framework to provide patient-specific predictions of HER2 + treatment response.

From digital hype to analogue reality: Universal simulation beyond the quantum and exascale eras

Many believe that the future of innovation lies in simulation. However, as computers are becoming ever more powerful, so does the hyperbole used to discuss their potential in modelling across a vast range of domains, from subatomic physics to chemistry, climate science, epidemiology, economics and cosmology. As we are about to enter the era of quantum and exascale computing, machine learning and artificial intelligence have entered the field in a significant way. In this article we give a brief history of simulation, discuss how machine learning can be more powerful if underpinned by deeper mechanistic understanding, outline the potential of exascale and quantum computing, highlight the limits of digital computing - classical and quantum - and distinguish rhetoric from reality in assessing the future of modelling and simulation, when we believe analogue computing will play an increasingly important role.

Application of Systems Engineering Principles and Techniques in Biological Big Data Analytics: A Review

In the past few decades, we have witnessed tremendous advancements in biology, life sciences and healthcare. These advancements are due in no small part to the big data made available by various high-throughput technologies, the ever-advancing computing power, and the algorithmic advancements in machine learning. Specifically, big data analytics such as statistical and machine learning has become an essential tool in these rapidly developing fields. As a result, the subject has drawn increased attention and many review papers have been published in just the past few years on the subject. Different from all existing reviews, this work focuses on the application of systems, engineering principles and techniques in addressing some of the common challenges in big data analytics for biological, biomedical and healthcare applications. Specifically, this review focuses on the following three key areas in biological big data analytics where systems engineering principles and techniques have been playing important roles: the principle of parsimony in addressing overfitting, the dynamic analysis of biological data, and the role of domain knowledge in biological data analytics.

Formidable females redux: male social integration into female networks and the value of dynamic multilayer networks

The development of multilayer network techniques is a boon for researchers who wish to understand how different interaction layers might influence each other, and how these in turn might influence group dynamics. Here, we investigate how integration between male and female grooming and aggression interaction networks influences male power trajectories in vervet monkeys Chlorocebus pygerythrus. Our previous analyses of this phenomenon used a monolayer approach, and our aim here is to extend these analyses using a dynamic multilayer approach. To do so, we constructed a temporal series of male and female interaction layers. We then used a multivariate multilevel autoregression model to compare cross-lagged associations between a male’s centrality in the female grooming layer and changes in male Elo ratings. Our results confirmed our original findings: changes in male centrality within the female grooming network were weakly but positively tied to changes in their Elo ratings. However, the multilayer network approach offered additional insights into this social process, identifying how changes in a male’s centrality cascade through the other network layers. This dynamic view indicates that the changes in Elo ratings are likely to be short-lived, but that male centrality within the female network had a much stronger impact throughout the multilayer network as a whole, especially on reducing intermale aggression (i.e., aggression directed by males toward other males). We suggest that multilayer social network approaches can take advantage of increased amounts of social data that are more commonly collected these days, using a variety of methods. Such data are inherently multilevel and multilayered, and thus offer the ability to quantify more precisely the dynamics of animal social behaviors.

Incorporating Physical Knowledge Into Machine Learning for Planetary Space Physics

Recent improvements in data collection volume from planetary and space physics missions have allowed the application of novel data science techniques. The Cassini mission for example collected over 600 gigabytes of scientific data from 2004 to 2017. This represents a surge of data on the Saturn system. In comparison, the previous mission to Saturn, Voyager over 20 years earlier, had onboard a ~70 kB 8-track storage ability. Machine learning can help scientists work with data on this larger scale. Unlike many applications of machine learning, a primary use in planetary space physics applications is to infer behavior about the system itself. This raises three concerns: first, the performance of the machine learning model, second, the need for interpretable applications to answer scientific questions, and third, how characteristics of spacecraft data change these applications. In comparison to these concerns, uses of "black box" or un-interpretable machine learning methods tend toward evaluations of performance only either ignoring the underlying physical process or, less often, providing misleading explanations for it. The present work uses Cassini data as a case study as these data are similar to space physics and planetary missions at Earth and other solar system objects. We build off a previous effort applying a semi-supervised physics-based classification of plasma instabilities in Saturn's magnetic environment, or magnetosphere. We then use this previous effort in comparison to other machine learning classifiers with varying data size access, and physical information access. We show that incorporating knowledge of these orbiting spacecraft data characteristics improves the performance and interpretability of machine leaning methods, which is essential for deriving scientific meaning. Building on these findings, we present a framework on incorporating physics knowledge into machine learning problems targeting semi-supervised classification for space physics data in planetary environments. These findings present a path forward for incorporating physical knowledge into space physics and planetary mission data analyses for scientific discovery.

Pre-Drilling Production Forecasting of Parent and Child Wells Using a 2-Segment Decline Curve Analysis (DCA) Method Based on an Analytical Flow-Cell Model Scaled by a Single Type Well

This paper advances a practical tool for production forecasting, using a 2-segment Decline Curve Analysis (DCA) method, based on an analytical flow-cell model for multi-stage fractured shale wells. The flow-cell model uses a type well and can forecast the production rate and estimated ultimate recovery (EUR) of newly planned wells, accounting for changes in completion design (fracture spacing, height, half-length), total well length, and well spacing. The basic equations for the flow-cell model have been derived in two earlier papers, the first one dedicated to well forecasts with fracture down-spacing, the second one to well performance forecasts when inter-well spacing changes (and for wells drilled at different times, to account for parent-child well interaction). The present paper provides a practical workflow, introduces correction parameters to account for acreage quality and fracture treatment quality. Further adjustments to the flow-cell model based 2-segment DCA method are made after history matching field data and numerical reservoir simulations, which indicate that terminal decline is not exponential (b = 0) but hyperbolic (with 0 < b< 1). The timing for the onset of boundary dominated flow was also better constrained, using inputs from a reservoir simulator. The new 2-segment DCA method is applied to real field data from the Eagle Ford Formation. Among the major insights of our analyses are: (1) fracture down-spacing does not increase the long-term EUR, and (2) fracture down-spacing of real wells does not result in the rate increases predicted by either the flow-cell model based 2-segment DCA (or its matching reservoir simulations) with the assumed perfect fractures in the down-spaced well models. Our conclusion is that real wells with down-spaced fracture clusters, involving up to 5000 perforations, are unlikely to develop successful hydraulic fractures from each cluster. The fracture treatment quality factor (TQF) or failure rate (1-TQF) can be estimated by comparing the actual well performance with the well forecast based on the ideal well model (albeit flow-cell model or reservoir model, both history-matched on the type curve).

Development of Supervised Learning Predictive Models for Highly Non-linear Biological, Biomedical, and General Datasets

In highly non-linear datasets, attributes or features do not allow readily finding visual patterns for identifying common underlying behaviors. Therefore, it is not possible to achieve classification or regression using linear or mildly non-linear hyperspace partition functions. Hence, supervised learning models based on the application of most existing algorithms are limited, and their performance metrics are low. Linear transformations of variables, such as principal components analysis, cannot avoid the problem, and even models based on artificial neural networks and deep learning are unable to improve the metrics. Sometimes, even when features allow classification or regression in reported cases, performance metrics of supervised learning algorithms remain unsatisfyingly low. This problem is recurrent in many areas of study as, per example, the clinical, biotechnological, and protein engineering areas, where many of the attributes are correlated in an unknown and very non-linear fashion or are categorical and difficult to relate to a target response variable. In such areas, being able to create predictive models would dramatically impact the quality of their outcomes, generating an immediate added value for both the scientific and general public. In this manuscript, we present RV-Clustering, a library of unsupervised learning algorithms, and a new methodology designed to find optimum partitions within highly non-linear datasets that allow deconvoluting variables and notoriously improving performance metrics in supervised learning classification or regression models. The partitions obtained are statistically cross-validated, ensuring correct representativity and no over-fitting. We have successfully tested RV-Clustering in several highly non-linear datasets with different origins. The approach herein proposed has generated classification and regression models with high-performance metrics, which further supports its ability to generate predictive models for highly non-linear datasets. Advantageously, the method does not require significant human input, which guarantees a higher usability in the biological, biomedical, and protein engineering community with no specific knowledge in the machine learning area.

Deep Learning for Deep Chemistry: Optimizing the Prediction of Chemical Patterns

Computational Chemistry is currently a synergistic assembly between ab initio calculations, simulation, machine learning (ML) and optimization strategies for describing, solving and predicting chemical data and related phenomena. These include accelerated literature searches, analysis and prediction of physical and quantum chemical properties, transition states, chemical structures, chemical reactions, and also new catalysts and drug candidates. The generalization of scalability to larger chemical problems, rather than specialization, is now the main principle for transforming chemical tasks in multiple fronts, for which systematic and cost-effective solutions have benefited from ML approaches, including those based on deep learning (e.g. quantum chemistry, molecular screening, synthetic route design, catalysis, drug discovery). The latter class of ML algorithms is capable of combining raw input into layers of intermediate features, enabling bench-to-bytes designs with the potential to transform several chemical domains. In this review, the most exciting developments concerning the use of ML in a range of different chemical scenarios are described. A range of different chemical problems and respective rationalization, that have hitherto been inaccessible due to the lack of suitable analysis tools, is thus detailed, evidencing the breadth of potential applications of these emerging multidimensional approaches. Focus is given to the models, algorithms and methods proposed to facilitate research on compound design and synthesis, materials design, prediction of binding, molecular activity, and soft matter behavior. The information produced by pairing Chemistry and ML, through data-driven analyses, neural network predictions and monitoring of chemical systems, allows (i) prompting the ability to understand the complexity of chemical data, (ii) streamlining and designing experiments, (ii) discovering new molecular targets and materials, and also (iv) planning or rethinking forthcoming chemical challenges. In fact, optimization engulfs all these tasks directly.

An integrative methodology based on protein-protein interaction networks for identification and functional annotation of disease-relevant genes applied to channelopathies

Background

Biologically data-driven networks have become powerful analytical tools that handle massive, heterogeneous datasets generated from biomedical fields. Protein-protein interaction networks can identify the most relevant structures directly tied to biological functions. Functional enrichments can then be performed based on these structural aspects of gene relationships for the study of channelopathies. Channelopathies refer to a complex group of disorders resulting from dysfunctional ion channels with distinct polygenic manifestations. This study presents a semi-automatic workflow using protein-protein interaction networks that can identify the most relevant genes and their biological processes and pathways in channelopathies to better understand their etiopathogenesis. In addition, the clinical manifestations that are strongly associated with these genes are also identified as the most characteristic in this complex group of diseases.

Results

In particular, a set of nine representative disease-related genes was detected, these being the most significant genes in relation to their roles in channelopathies. In this way we attested the implication of some voltage-gated sodium (SCN1A, SCN2A, SCN4A, SCN4B, SCN5A, SCN9A) and potassium (KCNQ2, KCNH2) channels in cardiovascular diseases, epilepsies, febrile seizures, headache disorders, neuromuscular, neurodegenerative diseases or neurobehavioral manifestations. We also revealed the role of Ankyrin-G (ANK3) in the neurodegenerative and neurobehavioral disorders as well as the implication of these genes in other systems, such as the immunological or endocrine systems.

Conclusions

This research provides a systems biology approach to extract information from interaction networks of gene expression. We show how large-scale computational integration of heterogeneous datasets, PPI network analyses, functional databases and published literature may support the detection and assessment of possible potential therapeutic targets in the disease. Applying our workflow makes it feasible to spot the most relevant genes and unknown relationships in channelopathies and shows its potential as a first-step approach to identify both genes and functional interactions in clinical-knowledge scenarios of target diseases.

Methods

An initial gene pool is previously defined by searching general databases under a specific semantic framework. From the resulting interaction network, a subset of genes are identified as the most relevant through the workflow that includes centrality measures and other filtering and enrichment databases.

The Human Ecological Perspective and Biopsychosocial Medicine

With regard to philosophical anthropology, a human ecological framework for the human-environment relationship as an "ecology of the person" is outlined, which focuses on the term "relationship" and aims to be scientifically sound. It also provides theoretical orientations for multiprofessional clinical work. For this purpose, a multi-dimensional basic grid for the characterization of the individual human being is proposed. The necessity and meaningfulness of a differentiation and systematization of the terms "environment", and above all "relationship", are demonstrated, and practical examples and links to similar framework models are given.

Factoring a 2 x 2 contingency table

We show that a two-component proportional representation provides the necessary framework to account for the properties of a 2 × 2 contingency table. This corresponds to the factorization of the table as a product of proportion and diagonal row or column sum matrices. The row and column sum invariant measures for proportional variation are obtained. Geometrically, these correspond to displacements of two point vectors in the standard one-simplex, which are reduced to a center-of-mass coordinate representation, [Formula: see text]. Then, effect size measures, such as the odds ratio and relative risk, correspond to different perspective functions for the mapping of (δ, μ) to [Formula: see text]. Furthermore, variations in δ and μ will be associated with different cost-benefit trade-offs for a given application. Therefore, pure mathematics alone does not provide the specification of a general form for the perspective function. This implies that the question of the merits of the odds ratio versus relative risk cannot be resolved in a general way. Expressions are obtained for the marginal sum dependence and the relations between various effect size measures, including the simple matching coefficient, odds ratio, relative risk, Yule's Q, ϕ, and Goodman and Kruskal's τc|r. We also show that Gini information gain (IGG) is equivalent to ϕ2 in the classification and regression tree (CART) algorithm. Then, IGG can yield misleading results due to the dependence on marginal sums. Monte Carlo methods facilitate the detailed specification of stochastic effects in the data acquisition process and provide a practical way to estimate the confidence interval for an effect size.

Natural and Artificial Intelligence in Neurosurgery: A Systematic Review

BACKGROUND

Machine learning (ML) is a domain of artificial intelligence that allows computer algorithms to learn from experience without being explicitly programmed.

OBJECTIVE

To summarize neurosurgical applications of ML where it has been compared to clinical expertise, here referred to as "natural intelligence."

METHODS

A systematic search was performed in the PubMed and Embase databases as of August 2016 to review all studies comparing the performance of various ML approaches with that of clinical experts in neurosurgical literature.

RESULTS

Twenty-three studies were identified that used ML algorithms for diagnosis, presurgical planning, or outcome prediction in neurosurgical patients. Compared to clinical experts, ML models demonstrated a median absolute improvement in accuracy and area under the receiver operating curve of 13% (interquartile range 4-21%) and 0.14 (interquartile range 0.07-0.21), respectively. In 29 (58%) of the 50 outcome measures for which a P-value was provided or calculated, ML models outperformed clinical experts (P < .05). In 18 of 50 (36%), no difference was seen between ML and expert performance (P > .05), while in 3 of 50 (6%) clinical experts outperformed ML models (P < .05). All 4 studies that compared clinicians assisted by ML models vs clinicians alone demonstrated a better performance in the first group.

CONCLUSION

We conclude that ML models have the potential to augment the decision-making capacity of clinicians in neurosurgical applications; however, significant hurdles remain associated with creating, validating, and deploying ML models in the clinical setting. Shifting from the preconceptions of a human-vs-machine to a human-and-machine paradigm could be essential to overcome these hurdles.

Improving palliative and end-of-life care with machine learning and routine data: a rapid review

Introduction: Improving end-of-life (EOL) care is a priority worldwide as this population experiences poor outcomes and accounts disproportionately for costs. In clinical practice, physician judgement is the core method of identifying EOL care needs but has important limitations. Machine learning (ML) is a subset of artificial intelligence advancing capacity to identify patterns and make predictions using large datasets.  ML approaches have the potential to improve clinical decision-making and policy design, but there has been no systematic assembly of current evidence. Methods: We conducted a rapid review, searching systematically seven databases from inception to December 31st, 2018: EMBASE, MEDLINE, Cochrane Library, PsycINFO, WOS, SCOPUS and ECONLIT.  We included peer-reviewed studies that used ML approaches on routine data to improve palliative and EOL care for adults.  Our specified outcomes were survival, quality of life (QoL), place of death, costs, and receipt of high-intensity treatment near end of life.  We did not search grey literature and excluded material that was not a peer-reviewed article. Results: The database search identified 426 citations. We discarded 162 duplicates and screened 264 unique title/abstracts, of which 22 were forwarded for full text review.  Three papers were included, 18 papers were excluded and one full text was sought but unobtainable.  One paper predicted six-month mortality, one paper predicted 12-month mortality and one paper cross-referenced predicted 12-month mortality with healthcare spending.  ML-informed models outperformed logistic regression in predicting mortality but poor prognosis is a weak driver of costs.  Models using only routine administrative data had limited benefit from ML methods. Conclusion: While ML can in principle help to identify those at risk of adverse outcomes and inappropriate treatment near EOL, applications to policy and practice are formative.  Future research must not only expand scope to other outcomes and longer timeframes, but also engage with individual preferences and ethical challenges.