AI-driven discovery of blood xenobiotic biomarkers in neovascular age-related macular degeneration using iterative random forests.

PURPOSE: To investigate the xenobiotic profiles of patients with neovascular age-related macular degeneration (nAMD) undergoing anti-vascular endothelial growth factor (anti-VEGF) intravitreal therapy (IVT) to identify biomarkers indicative of clinical phenotypes through advanced AI methodologies. METHODS: In this cross-sectional observational study, we analyzed 156 peripheral blood xenobiotic features in a cohort of 46 nAMD patients stratified by choroidal neovascularization (CNV) control under anti-VEGF IVT. We employed Liquid Chromatography-Tandem Mass Spectrometry (LC-MS/MS) for measurement and leveraged an AI-driven iterative Random Forests (iRF) approach for robust pattern recognition and feature selection, aligning molecular profiles with clinical phenotypes. RESULTS: AI-augmented iRF models effectively refined the metabolite spectrum by discarding non-predictive elements. Perfluorooctanesulfonate (PFOS) and Ethyl ß-glucopyranoside were identified as significant biomarkers through this process, associated with various clinically relevant phenotypes. Unlike single metabolite classes, drug metabolites were distinctly correlated with subretinal fluid presence. CONCLUSIONS: This study underscores the enhanced capability of AI, particularly iRF, in dissecting complex metabolomic data to elucidate the xenobiotic landscape of nAMD and environmental impact on the disease. The preliminary biomarkers discovered offer promising directions for personalized treatment strategies, although further validation in broader cohorts is essential for clinical application.

Exploring the Impact of Saccharin on Neovascular Age-Related Macular Degeneration: A Comprehensive Study in Patients and Mice.

Purpose: We aimed to determine the impact of artificial sweeteners (AS), especially saccharin, on the progression and treatment efficacy of patients with neovascular age-related macular degeneration (nAMD) under anti-vascular endothelial growth factor (anti-VEGF-A) treatment. Methods: In a cross-sectional study involving 46 patients with nAMD undergoing intravitreal anti-VEGF therapy, 6 AS metabolites were detected in peripheral blood using liquid chromatography - tandem mass spectrometry (LC-MS/MS). Disease features were statistically tested against these metabolite levels. Additionally, a murine choroidal neovascularization (CNV) model, induced by laser, was used to evaluate the effects of orally administered saccharin, assessing both imaging outcomes and gene expression patterns. Polymerase chain reaction (PCR) methods were used to evaluate functional expression of sweet taste receptors in a retinal pigment epithelium (RPE) cell line. Results: Saccharin levels in blood were significantly higher in patients with well-controlled CNV activity (P = 0.004) and those without subretinal hyper-reflective material (P = 0.015). In the murine model, saccharin-treated mice exhibited fewer leaking laser scars, lesser occurrence of bleeding, smaller fibrotic areas (P < 0.05), and a 40% decrease in mononuclear phagocyte accumulation (P = 0.06). Gene analysis indicated downregulation of inflammatory and VEGFR-1 response genes in the treated animals. Human RPE cells expressed taste receptor type 1 member 3 (TAS1R3) mRNA and reacted to saccharin stimulation with changes in mRNA expression. Conclusions: Saccharin appears to play a protective role in patients with nAMD undergoing intravitreal anti-VEGF treatment, aiding in better pathological lesion control and scar reduction. The murine study supports this observation, proposing saccharin's potential in mitigating pathological VEGFR-1-induced immune responses potentially via the RPE sensing saccharin in the blood stream.

Systemic Blood Proteome Patterns Reflect Disease Phenotypes in Neovascular Age-Related Macular Degeneration.

There is early evidence of extraocular systemic signals effecting function and morphology in neovascular age-related macular degeneration (nAMD). The prospective, cross-sectional BIOMAC study is an explorative investigation of peripheral blood proteome profiles and matched clinical features to uncover systemic determinacy in nAMD under anti-vascular endothelial growth factor intravitreal therapy (anti-VEGF IVT). It includes 46 nAMD patients stratified by the level of disease control under ongoing anti-VEGF treatment. Proteomic profiles in peripheral blood samples of every patient were detected with LC-MS/MS mass spectrometry. The patients underwent extensive clinical examination with a focus on macular function and morphology. In silico analysis includes unbiased dimensionality reduction and clustering, a subsequent annotation of clinical features, and non-linear models for recognition of underlying patterns. The model assessment was performed using leave-one-out cross validation. The findings provide an exploratory demonstration of the link between systemic proteomic signals and macular disease pattern using and validating non-linear classification models. Three main results were obtained: (1) Proteome-based clustering identifies two distinct patient subclusters with the smaller one (n = 10) exhibiting a strong signature for oxidative stress response. Matching the relevant meta-features on the individual patient's level identifies pulmonary dysfunction as an underlying health condition in these patients. (2) We identify biomarkers for nAMD disease features with Aldolase C as a putative factor associated with superior disease control under ongoing anti-VEGF treatment. (3) Apart from this, isolated protein markers are only weakly correlated with nAMD disease expression. In contrast, applying a non-linear classification model identifies complex molecular patterns hidden in a high number of proteomic dimensions determining macular disease expression. In conclusion, so far unconsidered systemic signals in the peripheral blood proteome contribute to the clinically observed phenotype of nAMD, which should be examined in future translational research on AMD.

Experimental validation of computerised models of clustering of platelet glycoprotein receptors that signal via tandem SH2 domain proteins.

The clustering of platelet glycoprotein receptors with cytosolic YxxL and YxxM motifs, including GPVI, CLEC-2 and PEAR1, triggers activation via phosphorylation of the conserved tyrosine residues and recruitment of the tandem SH2 (Src homology 2) domain effector proteins, Syk and PI 3-kinase. We have modelled the clustering of these receptors with monovalent, divalent and tetravalent soluble ligands and with transmembrane ligands based on the law of mass action using ordinary differential equations and agent-based modelling. The models were experimentally evaluated in platelets and transfected cell lines using monovalent and multivalent ligands, including novel nanobody-based divalent and tetravalent ligands, by fluorescence correlation spectroscopy. Ligand valency, receptor number, receptor dimerisation, receptor phosphorylation and a cytosolic tandem SH2 domain protein act in synergy to drive receptor clustering. Threshold concentrations of a CLEC-2-blocking antibody and Syk inhibitor act in synergy to block platelet aggregation. This offers a strategy for countering the effect of avidity of multivalent ligands and in limiting off-target effects.

Proposal of a population wide genome-based testing for Covid-19.

Our lives (and deaths) have by now been dominated for two years by COVID-19, a pandemic that has caused hundreds of millions of disease cases, millions of deaths, trillions in economic costs, and major restrictions on our freedom. Here we suggest a novel tool for controlling the COVID-19 pandemic. The key element is a method for a population-scale PCR-based testing, applied on a systematic and repeated basis. For this we have developed a low cost, highly sensitive virus-genome-based test. Using Germany as an example, we demonstrate by using a mathematical model, how useful this strategy could have been in controlling the pandemic. We show using real-world examples how this might be implemented on a mass scale and discuss the feasibility of this approach.

Mini-batch optimization enables training of ODE models on large-scale datasets.

Quantitative dynamic models are widely used to study cellular signal processing. A critical step in modelling is the estimation of unknown model parameters from experimental data. As model sizes and datasets are steadily growing, established parameter optimization approaches for mechanistic models become computationally extremely challenging. Mini-batch optimization methods, as employed in deep learning, have better scaling properties. In this work, we adapt, apply, and benchmark mini-batch optimization for ordinary differential equation (ODE) models, thereby establishing a direct link between dynamic modelling and machine learning. On our main application example, a large-scale model of cancer signaling, we benchmark mini-batch optimization against established methods, achieving better optimization results and reducing computation by more than an order of magnitude. We expect that our work will serve as a first step towards mini-batch optimization tailored to ODE models and enable modelling of even larger and more complex systems than what is currently possible.

A framework for validating AI in precision medicine: considerations from the European ITFoC consortium.

BACKGROUND: Artificial intelligence (AI) has the potential to transform our healthcare systems significantly. New AI technologies based on machine learning approaches should play a key role in clinical decision-making in the future. However, their implementation in health care settings remains limited, mostly due to a lack of robust validation procedures. There is a need to develop reliable assessment frameworks for the clinical validation of AI. We present here an approach for assessing AI for predicting treatment response in triple-negative breast cancer (TNBC), using real-world data and molecular -omics data from clinical data warehouses and biobanks. METHODS: The European "ITFoC (Information Technology for the Future Of Cancer)" consortium designed a framework for the clinical validation of AI technologies for predicting treatment response in oncology. RESULTS: This framework is based on seven key steps specifying: (1) the intended use of AI, (2) the target population, (3) the timing of AI evaluation, (4) the datasets used for evaluation, (5) the procedures used for ensuring data safety (including data quality, privacy and security), (6) the metrics used for measuring performance, and (7) the procedures used to ensure that the AI is explainable. This framework forms the basis of a validation platform that we are building for the "ITFoC Challenge". This community-wide competition will make it possible to assess and compare AI algorithms for predicting the response to TNBC treatments with external real-world datasets. CONCLUSIONS: The predictive performance and safety of AI technologies must be assessed in a robust, unbiased and transparent manner before their implementation in healthcare settings. We believe that the consideration of the ITFoC consortium will contribute to the safe transfer and implementation of AI in clinical settings, in the context of precision oncology and personalized care.

Data and knowledge management in translational research: implementation of the eTRIKS platform for the IMI OncoTrack consortium.

BACKGROUND: For large international research consortia, such as those funded by the European Union's Horizon 2020 programme or the Innovative Medicines Initiative, good data coordination practices and tools are essential for the successful collection, organization and analysis of the resulting data. Research consortia are attempting ever more ambitious science to better understand disease, by leveraging technologies such as whole genome sequencing, proteomics, patient-derived biological models and computer-based systems biology simulations. RESULTS: The IMI eTRIKS consortium is charged with the task of developing an integrated knowledge management platform capable of supporting the complexity of the data generated by such research programmes. In this paper, using the example of the OncoTrack consortium, we describe a typical use case in translational medicine. The tranSMART knowledge management platform was implemented to support data from observational clinical cohorts, drug response data from cell culture models and drug response data from mouse xenograft tumour models. The high dimensional (omics) data from the molecular analyses of the corresponding biological materials were linked to these collections, so that users could browse and analyse these to derive candidate biomarkers. CONCLUSIONS: In all these steps, data mapping, linking and preparation are handled automatically by the tranSMART integration platform. Therefore, researchers without specialist data handling skills can focus directly on the scientific questions, without spending undue effort on processing the data and data integration, which are otherwise a burden and the most time-consuming part of translational research data analysis.

Efficient Parameter Estimation Enables the Prediction of Drug Response Using a Mechanistic Pan-Cancer Pathway Model.

Mechanistic models are essential to deepen the understanding of complex diseases at the molecular level. Nowadays, high-throughput molecular and phenotypic characterizations are possible, but the integration of such data with prior knowledge on signaling pathways is limited by the availability of scalable computational methods. Here, we present a computational framework for the parameterization of large-scale mechanistic models and its application to the prediction of drug response of cancer cell lines from exome and transcriptome sequencing data. This framework is over 104 times faster than state-of-the-art methods, which enables modeling at previously infeasible scales. By applying the framework to a model describing major cancer-associated pathways (>1,200 species and >2,600 reactions), we could predict the effect of drug combinations from single drug data. This is the first integration of high-throughput datasets using large-scale mechanistic models. We anticipate this to be the starting point for development of more comprehensive models allowing a deeper mechanistic insight.

The micromechanical behavior of implant-abutment connections under a dynamic load protocol.

BACKGROUND: The implant-abutment connection (IAC) is known to be a key factor for the long-term stability of peri-implant tissue. PURPOSE: The aim of the present in vitro study was to detect and measure the mechanical behavior of different IACs by X-ray imaging. MATERIALS AND METHODS: A total of 20 different implant systems with various implant dimensions and IACs (13 conical-, 6 flat-, and 1 gable-like IAC) have been tested using a chewing device simulating dynamic and static loading up to 200 N. Micromovements have been recorded with a high-resolution, high-speed X-ray camera, and gap length and gap width between implant and abutment have been calculated. Furthermore, X-ray video sequences have been recorded to investigate the sealing capacity of different IACs. RESULTS: Out of the 20 implant systems, eight implant systems with a conical IAC showed no measurable gaps under static and dynamic loading (200 N). By contrast, all investigated implant systems with a flat IAC showed measurable gaps under dynamic and static loading. X-ray video sequences revealed that a representative conical IAC had sufficient sealing capacity. CONCLUSION: Within the limits of the present in vitro study, X-ray imaging showed reduced formation of microgaps and consecutive micromovements in implants with conical IAC compared to flat IACs.

Models of Models: A Translational Route for Cancer Treatment and Drug Development.

Every patient and every disease is different. Each patient therefore requires a personalized treatment approach. For technical reasons, a personalized approach is feasible for treatment strategies such as surgery, but not for drug-based therapy or drug development. The development of individual mechanistic models of the disease process in every patient offers the possibility of attaining truly personalized drug-based therapy and prevention. The concept of virtual clinical trials and the integrated use of in silico, in vitro, and in vivo models in preclinical development could lead to significant gains in efficiency and order of magnitude increases in the cost effectiveness of drug development and approval. We have developed mechanistic computational models of large-scale cellular signal transduction networks for prediction of drug effects and functional responses, based on patient-specific multi-level omics profiles. However, a major barrier to the use of such models in a clinical and developmental context is the reliability of predictions. Here we detail how the approach of using "models of models" has the potential to impact cancer treatment and drug development. We describe the iterative refinement process that leverages the flexibility of experimental systems to generate highly dimensional data, which can be used to train and validate computational model parameters and improve model predictions. In this way, highly optimized computational models with robust predictive capacity can be generated. Such models open up a number of opportunities for cancer drug treatment and development, from enhancing the design of experimental studies, reducing costs, and improving animal welfare, to increasing the translational value of results generated.

Cancer Precision Medicine: Why More Is More and DNA Is Not Enough.

Every tumour is different. They arise in patients with different genomes, from cells with different epigenetic modifications, and by random processes affecting the genome and/or epigenome of a somatic cell, allowing it to escape the usual controls on its growth. Tumours and patients therefore often respond very differently to the drugs they receive. Cancer precision medicine aims to characterise the tumour (and often also the patient) to be able to predict, with high accuracy, its response to different treatments, with options ranging from the selective characterisation of a few genomic variants considered particularly important to predict the response of the tumour to specific drugs, to deep genome analysis of both tumour and patient, combined with deep transcriptome analysis of the tumour. Here, we compare the expected results of carrying out such analyses at different levels, from different size panels to a comprehensive analysis incorporating both patient and tumour at the DNA and RNA levels. In doing so, we illustrate the additional power gained by this unusually deep analysis strategy, a potential basis for a future precision medicine first strategy in cancer drug therapy. However, this is only a step along the way of increasingly detailed molecular characterisation, which in our view will, in the future, introduce additional molecular characterisation techniques, including systematic analysis of proteins and protein modification states and different types of metabolites in the tumour, systematic analysis of circulating tumour cells and nucleic acids, the use of spatially resolved analysis techniques to address the problem of tumour heterogeneity as well as the deep analyses of the immune system of the patient to, e.g., predict the response of the patient to different types of immunotherapy. Such analyses will generate data sets of even greater complexity, requiring mechanistic modelling approaches to capture enough of the complex situation in the real patient to be able to accurately predict his/her responses to all available therapies.

Molecular dissection of colorectal cancer in pre-clinical models identifies biomarkers predicting sensitivity to EGFR inhibitors.

Colorectal carcinoma represents a heterogeneous entity, with only a fraction of the tumours responding to available therapies, requiring a better molecular understanding of the disease in precision oncology. To address this challenge, the OncoTrack consortium recruited 106 CRC patients (stages I-IV) and developed a pre-clinical platform generating a compendium of drug sensitivity data totalling >4,000 assays testing 16 clinical drugs on patient-derived in vivo and in vitro models. This large biobank of 106 tumours, 35 organoids and 59 xenografts, with extensive omics data comparing donor tumours and derived models provides a resource for advancing our understanding of CRC. Models recapitulate many of the genetic and transcriptomic features of the donors, but defined less complex molecular sub-groups because of the loss of human stroma. Linking molecular profiles with drug sensitivity patterns identifies novel biomarkers, including a signature outperforming RAS/RAF mutations in predicting sensitivity to the EGFR inhibitor cetuximab.

Impaired Planar Germ Cell Division in the Testis, Caused by Dissociation of RHAMM from the Spindle, Results in Hypofertility and Seminoma.

Hypofertility is a risk factor for the development of testicular germ cell tumors (TGCT), but the initiating event linking these pathologies is unknown. We hypothesized that excessive planar division of undifferentiated germ cells promotes their self-renewal and TGCT development. However, our results obtained from mouse models and seminoma patients demonstrated the opposite. Defective planar divisions of undifferentiated germ cells caused their premature exit from the seminiferous tubule niche, resulting in germ cell depletion, hypofertility, intratubular germ cell neoplasias, and seminoma development. Oriented divisions of germ cells, which determine their fate, were regulated by spindle-associated RHAMM-a function we found to be abolished in 96% of human seminomas. Mechanistically, RHAMM expression is regulated by the testis-specific polyadenylation protein CFIm25, which is downregulated in the human seminomas. These results suggested that spindle misorientation is oncogenic, not by promoting self-renewing germ cell divisions within the niche, but by prematurely displacing proliferating cells from their normal epithelial milieu. Furthermore, they suggested RHAMM loss-of-function and spindle misorientation as an initiating event underlying both hypofertility and TGCT initiation. These findings identify spindle-associated RHAMM as an intrinsic regulator of male germ cell fate and as a gatekeeper preventing initiation of TGCTs. Cancer Res; 76(21); 6382-95. ©2016 AACR.

Predictive Modeling of Drug Treatment in the Area of Personalized Medicine.

Despite a growing body of knowledge on the mechanisms underlying the onset and progression of cancer, treatment success rates in oncology are at best modest. Current approaches use statistical methods that fail to embrace the inherent and expansive complexity of the tumor/patient/drug interaction. Computational modeling, in particular mechanistic modeling, has the power to resolve this complexity. Using fundamental knowledge on the interactions occurring between the components of a complex biological system, large-scale in silico models with predictive capabilities can be generated. Here, we describe how mechanistic virtual patient models, based on systematic molecular characterization of patients and their diseases, have the potential to shift the theranostic paradigm for oncology, both in the fields of personalized medicine and targeted drug development. In particular, we highlight the mechanistic modeling platform ModCell™ for individualized prediction of patient responses to treatment, emphasizing modeling techniques and avenues of application.

Network and systems biology: essential steps in virtualising drug discovery and development.

The biological processes that keep us healthy or cause disease, as well as the mechanisms of action of possible drugs are inherently complex. In the face of this complexity, attempts at discovering new drugs to treat diseases have alternated between trial-and-error (typically on experimental systems) and grand simplification, usually based on much too little information. We now have the chance to combine these strategies through establishment of 'virtual patient' models, centred on a detailed molecular characterisation of thousands or even, in the future, millions of patients. In doing so, we lay the foundations for truly personalised therapy, as well as a far-reaching virtualisation of drug discovery and development in oncology and other areas of medicine.

Personalized medicine approaches for colon cancer driven by genomics and systems biology: OncoTrack.

The post-genomic era promises to pave the way to a personalized understanding of disease processes, with technological and analytical advances helping to solve some of the world's health challenges. Despite extraordinary progress in our understanding of cancer pathogenesis, the disease remains one of the world's major medical problems. New therapies and diagnostic procedures to guide their clinical application are urgently required. OncoTrack, a consortium between industry and academia, supported by the Innovative Medicines Initiative, signifies a new era in personalized medicine, which synthesizes current technological advances in omics techniques, systems biology approaches, and mathematical modeling. A truly personalized molecular imprint of the tumor micro-environment and subsequent diagnostic and therapeutic insight is gained, with the ultimate goal of matching the "right" patient to the "right" drug and identifying predictive biomarkers for clinical application. This comprehensive mapping of the colon cancer molecular landscape in tandem with crucial, clinical functional annotation for systems biology analysis provides unprecedented insight and predictive power for colon cancer management. Overall, we show that major biotechnological developments in tandem with changes in clinical thinking have laid the foundations for the OncoTrack approach and the future clinical application of a truly personalized approach to colon cancer theranostics.

LGALS3BP regulates centriole biogenesis and centrosome hypertrophy in cancer cells.

Centrosome morphology and number are frequently deregulated in cancer cells. Here, to identify factors that are functionally relevant for centrosome abnormalities in cancer cells, we established a protein-interaction network around 23 centrosomal and cell-cycle regulatory proteins, selecting the interacting proteins that are deregulated in cancer for further studies. One of these components, LGALS3BP, is a centriole- and basal body-associated protein with a dual role, triggering centrosome hypertrophy when overexpressed and causing accumulation of centriolar substructures when downregulated. The cancer cell line SK-BR-3 that overexpresses LGALS3BP exhibits hypertrophic centrosomes, whereas in seminoma tissues with low expression of LGALS3BP, supernumerary centriole-like structures are present. Centrosome hypertrophy is reversed by depleting LGALS3BP in cells endogenously overexpressing this protein, supporting a direct role in centrosome aberration. We propose that LGALS3BP suppresses assembly of centriolar substructures, and when depleted, causes accumulation of centriolar complexes comprising CPAP, acetylated tubulin and centrin.

Functional analysis of centrosomal kinase substrates in Drosophila melanogaster reveals a new function of the nuclear envelope component otefin in cell cycle progression.

Phosphorylation is one of the key mechanisms that regulate centrosome biogenesis, spindle assembly, and cell cycle progression. However, little is known about centrosome-specific phosphorylation sites and their functional relevance. Here, we identified phosphoproteins of intact Drosophila melanogaster centrosomes and found previously unknown phosphorylation sites in known and unexpected centrosomal components. We functionally characterized phosphoproteins and integrated them into regulatory signaling networks with the 3 important mitotic kinases, cdc2, polo, and aur, as well as the kinase CkIIß. Using a combinatorial RNA interference (RNAi) strategy, we demonstrated novel functions for P granule, nuclear envelope (NE), and nuclear proteins in centrosome duplication, maturation, and separation. Peptide microarrays confirmed phosphorylation of identified residues by centrosome-associated kinases. For a subset of phosphoproteins, we identified previously unknown centrosome and/or spindle localization via expression of tagged fusion proteins in Drosophila SL2 cells. Among those was otefin (Ote), an NE protein that we found to localize to centrosomes. Furthermore, we provide evidence that it is phosphorylated in vitro at threonine 63 (T63) through Aurora-A kinase. We propose that phosphorylation of this site plays a dual role in controlling mitotic exit when phosphorylated while dephosphorylation promotes G(2)/M transition in Drosophila SL2 cells.

New insights into subcomplex assembly and modifications of centrosomal proteins.

This review provides a brief overview of the recent work on centrosome proteomics, protein complex identification and functional characterization with an emphasis on the literature of the last three years. Proteomics, genetic screens and comparative genomics studies in different model organisms have almost exhaustively identified the molecular components of the centrosome. However, much knowledge is still missing on the protein-protein interactions, protein modifications and molecular changes the centrosome undergoes throughout the cell cycle and development. The dynamic nature of this large multi-protein complex is reflected in the variety of annotated subcellular locations and biological processes of its proposed components. Some centrosomal proteins and complexes have been studied intensively in different organisms and provided detailed insight into centrosome functions. For example, the molecular, structural and functional characterization of the γ-Tubulin ring complex (γ-TuRC) and the the discovery of the Augmin/HAUS complex has advanced our understanding of microtubule (MT) capture, nucleation and organization. Surprising findings revealed new functions and localizations of proteins that were previously regarded as bona fide centriolar or centrosome components, e.g. at the kinetochore or in the nuclear pore complex regulating MT plus end capture or mRNA processing. Many centrosome components undergo posttranslational modifications such as phosphorylation, SUMOylation and ubiquitylation that are critical in modulating centrosome function and biology. A wealth of information has recently become available driven by new developments in technologies such as mass spectrometry, light and electron microscopy providing more detailed molecular and structural definition of the centrosome and particular roles of proteins throughout the cell cycle and development.