RESUMO
Drug repurposing aims to find new therapeutic applications for existing drugs in the pharmaceutical market, leading to significant savings in time and cost. The use of artificial intelligence and knowledge graphs to propose repurposing candidates facilitates the process, as large amounts of data can be processed. However, it is important to pay attention to the explainability needed to validate the predictions. We propose a general architecture to understand several explainable methods for graph completion based on knowledge graphs and design our own architecture for drug repurposing. We present XG4Repo (eXplainable Graphs for Repurposing), a framework that takes advantage of the connectivity of any biomedical knowledge graph to link compounds to the diseases they can treat. Our method allows methapaths of different types and lengths, which are automatically generated and optimised based on data. XG4Repo focuses on providing meaningful explanations to the predictions, which are based on paths from compounds to diseases. These paths include nodes such as genes, pathways, side effects, or anatomies, so they provide information about the targets and other characteristics of the biomedical mechanism that link compounds and diseases. Paths make predictions interpretable for experts who can validate them and use them in further research on drug repurposing. We also describe three use cases where we analyse new uses for Epirubicin, Paclitaxel, and Predinisone and present the paths that support the predictions.
Assuntos
Reposicionamento de Medicamentos , Reposicionamento de Medicamentos/métodos , Humanos , Inteligência Artificial , AlgoritmosRESUMO
PURPOSE: Rare cancers constitute over 20% of human neoplasms, often affecting patients with unmet medical needs. The development of effective classification and prognostication systems is crucial to improve the decision-making process and drive innovative treatment strategies. We have created and implemented MOSAIC, an artificial intelligence (AI)-based framework designed for multimodal analysis, classification, and personalized prognostic assessment in rare cancers. Clinical validation was performed on myelodysplastic syndrome (MDS), a rare hematologic cancer with clinical and genomic heterogeneities. METHODS: We analyzed 4,427 patients with MDS divided into training and validation cohorts. Deep learning methods were applied to integrate and impute clinical/genomic features. Clustering was performed by combining Uniform Manifold Approximation and Projection for Dimension Reduction + Hierarchical Density-Based Spatial Clustering of Applications with Noise (UMAP + HDBSCAN) methods, compared with the conventional Hierarchical Dirichlet Process (HDP). Linear and AI-based nonlinear approaches were compared for survival prediction. Explainable AI (Shapley Additive Explanations approach [SHAP]) and federated learning were used to improve the interpretation and the performance of the clinical models, integrating them into distributed infrastructure. RESULTS: UMAP + HDBSCAN clustering obtained a more granular patient stratification, achieving a higher average silhouette coefficient (0.16) with respect to HDP (0.01) and higher balanced accuracy in cluster classification by Random Forest (92.7% ± 1.3% and 85.8% ± 0.8%). AI methods for survival prediction outperform conventional statistical techniques and the reference prognostic tool for MDS. Nonlinear Gradient Boosting Survival stands in the internal (Concordance-Index [C-Index], 0.77; SD, 0.01) and external validation (C-Index, 0.74; SD, 0.02). SHAP analysis revealed that similar features drove patients' subgroups and outcomes in both training and validation cohorts. Federated implementation improved the accuracy of developed models. CONCLUSION: MOSAIC provides an explainable and robust framework to optimize classification and prognostic assessment of rare cancers. AI-based approaches demonstrated superior accuracy in capturing genomic similarities and providing individual prognostic information compared with conventional statistical methods. Its federated implementation ensures broad clinical application, guaranteeing high performance and data protection.
Assuntos
Inteligência Artificial , Medicina de Precisão , Humanos , Prognóstico , Medicina de Precisão/métodos , Feminino , Doenças Raras/classificação , Doenças Raras/genética , Doenças Raras/diagnóstico , Masculino , Aprendizado Profundo , Neoplasias/classificação , Neoplasias/genética , Neoplasias/diagnóstico , Síndromes Mielodisplásicas/diagnóstico , Síndromes Mielodisplásicas/classificação , Síndromes Mielodisplásicas/genética , Síndromes Mielodisplásicas/terapia , Algoritmos , Pessoa de Meia-Idade , Idoso , Análise por ConglomeradosRESUMO
Estimating treatment effects from observational data in medicine using causal inference is a very relevant task due to the abundance of observational data and the ethical and cost implications of conducting randomized experiments or experimental interventions. However, how could we estimate the effect of a treatment in a hospital that has very restricted access to treatment? In this paper, we want to address the problem of distributed causal inference, where hospitals not only have different distributions of patients, but also different treatment assignment criteria. Furthermore, it is necessary to take into account that due to privacy restrictions, personal patient data cannot be shared between hospitals. To address this problem, we propose an adaptation of the federated learning algorithm FederatedAveraging to one of the most advanced models for the prediction of treatment effects based on neural networks, TEDVAE. Our algorithm adaptation takes into account the shift in the treatment distribution between hospitals and is therefore called Propensity WeightedFederatedAveraging (PW FedAvg). As the distributions of the assignment of treatments become more unbalanced between the nodes, the estimation of causal effects becomes more challenging. The experiments show that PW FedAvg manages to reduce errors in the estimation of individual causal effects when imbalances are large, compared to VanillaFedAvg and other federated learning-based causal inference algorithms based on the application of federated learning to linear parametric models, Gaussian Processes and Random Fourier Features.
Assuntos
Algoritmos , Humanos , Aprendizado de Máquina , Redes Neurais de ComputaçãoRESUMO
Acute lymphoblastic leukemia (ALL) is the most common pediatric cancer, with survival rates exceeding 85%. However, 15% of patients will relapse; consequently, their survival rates decrease to below 50%. Therefore, several research and innovation studies are focusing on pediatric relapsed or refractory ALL (R/R ALL). Driven by this context and following the European strategic plan to implement precision medicine equitably, the Relapsed ALL Network (ReALLNet) was launched under the umbrella of SEHOP in 2021, aiming to connect bedside patient care with expert groups in R/R ALL in an interdisciplinary and multicentric network. To achieve this objective, a board consisting of experts in diagnosis, management, preclinical research, and clinical trials has been established. The requirements of treatment centers have been evaluated, and the available oncogenomic and functional study resources have been assessed and organized. A shipping platform has been developed to process samples requiring study derivation, and an integrated diagnostic committee has been established to report results. These biological data, as well as patient outcomes, are collected in a national registry. Additionally, samples from all patients are stored in a biobank. This comprehensive repository of data and samples is expected to foster an environment where preclinical researchers and data scientists can seek to meet the complex needs of this challenging population. This proof of concept aims to demonstrate that a network-based organization, such as that embodied by ReALLNet, provides the ideal niche for the equitable and efficient implementation of "what's next" in the management of children with R/R ALL.
RESUMO
We cover the Warburg effect with a three-component evolutionary model, where each component represents a different metabolic strategy. In this context, a scenario involving cells expressing three different phenotypes is presented. One tumour phenotype exhibits glycolytic metabolism through glucose uptake and lactate secretion. Lactate is used by a second malignant phenotype to proliferate. The third phenotype represents healthy cells, which performs oxidative phosphorylation. The purpose of this model is to gain a better understanding of the metabolic alterations associated with the Warburg effect. It is suitable to reproduce some of the clinical trials obtained in colorectal cancer and other even more aggressive tumours. It shows that lactate is an indicator of poor prognosis, since it favours the setting of polymorphic tumour equilibria that complicates its treatment. This model is also used to train a reinforcement learning algorithm, known as Double Deep Q-networks, in order to provide the first optimal targeted therapy based on experimental tumour growth inhibitors as genistein and AR-C155858. Our in silico solution includes the optimal therapy for all the tumour state space and also ensures the best possible quality of life for the patients, by considering the duration of treatment, the use of low-dose medications and the existence of possible contraindications. Optimal therapies obtained with Double Deep Q-networks are validated with the solutions of the Hamilton-Jacobi-Bellman equation.
Assuntos
Neoplasias , Qualidade de Vida , Humanos , Neoplasias/patologia , Fosforilação Oxidativa , Ácido Láctico , GlicóliseRESUMO
We use the recent advances in Deep Learning to solve an underwater motion planning problem by making use of optimal control tools-namely, we propose using the Deep Galerkin Method (DGM) to approximate the Hamilton-Jacobi-Bellman PDE that can be used to solve continuous time and state optimal control problems. In order to make our approach more realistic, we consider that there are disturbances in the underwater medium that affect the trajectory of the autonomous vehicle. After adapting DGM by making use of a surrogate approach, our results show that our method is able to efficiently solve the proposed problem, providing large improvements over a baseline control in terms of costs, especially in the case in which the disturbances effects are more significant.
Assuntos
Aprendizado Profundo , Redes Neurais de Computação , Humanos , Movimento (Física) , Dinâmica não LinearRESUMO
Recent advances in Deep Reinforcement Learning allow solving increasingly complex problems. In this work, we show how current defense mechanisms in Wireless Sensor Networks are vulnerable to attacks that use these advances. We use a Deep Reinforcement Learning attacker architecture that allows having one or more attacking agents that can learn to attack using only partial observations. Then, we subject our architecture to a test-bench consisting of two defense mechanisms against a distributed spectrum sensing attack and a backoff attack. Our simulations show that our attacker learns to exploit these systems without having a priori information about the defense mechanism used nor its concrete parameters. Since our attacker requires minimal hyper-parameter tuning, scales with the number of attackers, and learns only by interacting with the defense mechanism, it poses a significant threat to current defense procedures.
Assuntos
Segurança Computacional , ConfidencialidadeRESUMO
In this work, a real-time software-in-loop simulation technique was employed to test and analyse an underwater wireless sensor network. This simulation should facilitate the deployment of the real network and helps guarantee the network's expected behaviour. We study duplicated packets, one-way delay, and power consumption to analyse the network's leading parameters. Evaluating production-ready software in simulated conditions eases effective deployment. This method will ultimately allow us to establish these parameters, test the software before the deployment, and have an excellent understanding of the network's behaviour.
RESUMO
We study a CSMA/CA (Carrier Sense Medium Access with Collision Avoidance) wireless network where some stations deviate from the defined contention mechanism. By using Bianchi's model, we study how this deviation impacts the network throughput and show that the fairness of the network is seriously affected, as the stations that deviate achieve a larger share of the resources than the rest of stations. Previously, we modeled this situation using a static game and now, we use repeated games, which, by means of the Folk theorem, allow all players to have better outcomes. We provide analytical solutions to this game for the two player case using subgame perfect and correlated equilibria concepts. We also propose a distributed algorithm based on communicating candidate equilibrium points for learning the equilibria of this game for an arbitrary number of players. We validate approach using numerical simulations, which allows comparing the solutions we propose and discussing the advantages of using each of the methods we propose.
RESUMO
In recent years, there has been a significant effort towards developing localization systems in the underwater medium, with current methods relying on anchor nodes, explicitly modeling the underwater channel or cooperation from the target. Lately, there has also been some work on using the approximation capabilities of Deep Neural Networks in order to address this problem. In this work, we study how the localization precision of using Deep Neural Networks is affected by the variability of the channel, the noise level at the receiver, the number of neurons of the neural network and the utilization of the power or the covariance of the received acoustic signals. Our study shows that using deep neural networks is a valid approach when the channel variability is low, which opens the door to further research in such localization methods for the underwater environment.
RESUMO
We study a wireless sensor network using CSMA/CA in the MAC layer under a backoff attack: some of the sensors of the network are malicious and deviate from the defined contention mechanism. We use Bianchi's network model to study the impact of the malicious sensors on the total network throughput, showing that it causes the throughput to be unfairly distributed among sensors. We model this conflict using game theory tools, where each sensor is a player. We obtain analytical solutions and propose an algorithm, based on Regret Matching, to learn the equilibrium of the game with an arbitrary number of players. Our approach is validated via simulations, showing that our theoretical predictions adjust to reality.
RESUMO
Underwater Wireless Sensor Networks (UWSNs) using electromagnetic (EM) technology in marine shallow waters are examined, not just for environmental monitoring but for further interesting applications. Particularly, the use of EM waves is reconsidered in shallow waters due to the benefits offered in this context, where acoustic and optical technologies have serious disadvantages. Sea water scenario is a harsh environment for radiocommunications, and there is no standard model for the underwater EM channel. The high conductivity of sea water, the effect of seabed and the surface make the behaviour of the channel hard to predict. This justifies the need of link characterization as the first step to approach the development of EM underwater sensor networks. To obtain a reliable link model, measurements and simulations are required. The measuring setup for this purpose is explained and described, as well as the procedures used. Several antennas have been designed and tested in low frequency bands. Agreement between attenuation measurements and simulations at different distances was analysed and made possible the validation of simulation setups and the design of different communications layers of the system. This leads to the second step of this work, where data and routing protocols for the sensor network are examined.
RESUMO
In the first part of the paper, we modeled and characterized the underwater radio channel in shallowwaters. In the second part,we analyze the application requirements for an underwaterwireless sensor network (U-WSN) operating in the same environment and perform detailed simulations. We consider two localization applications, namely self-localization and navigation aid, and propose algorithms that work well under the specific constraints associated with U-WSN, namely low connectivity, low data rates and high packet loss probability. We propose an algorithm where the sensor nodes collaboratively estimate their unknown positions in the network using a low number of anchor nodes and distance measurements from the underwater channel. Once the network has been self-located, we consider a node estimating its position for underwater navigation communicating with neighboring nodes. We also propose a communication system and simulate the whole electromagnetic U-WSN in the Castalia simulator to evaluate the network performance, including propagation impairments (e.g., noise, interference), radio parameters (e.g., modulation scheme, bandwidth, transmit power), hardware limitations (e.g., clock drift, transmission buffer) and complete MAC and routing protocols. We also explain the changes that have to be done to Castalia in order to perform the simulations. In addition, we propose a parametric model of the communication channel that matches well with the results from the first part of this paper. Finally, we provide simulation results for some illustrative scenarios.
RESUMO
Algorithms for distributed agreement are a powerful means for formulating distributed versions of existing centralized algorithms. We present a toolkit for this task and show how it can be used systematically to design fully distributed algorithms for static linear Gaussian models, including principal component analysis, factor analysis, and probabilistic principal component analysis. These algorithms do not rely on a fusion center, require only low-volume local (1-hop neighborhood) communications, and are thus efficient, scalable, and robust. We show how they are also guaranteed to asymptotically converge to the same solution as the corresponding existing centralized algorithms. Finally, we illustrate the functioning of our algorithms on two examples, and examine the inherent cost-performance trade-off.
Assuntos
Modelos Lineares , Estimulação Luminosa/métodos , Análise de Componente Principal , Distribuição Normal , Análise de Componente Principal/métodosRESUMO
The improvement in the transmission range in wireless applications without the use of batteries remains a significant challenge in identification applications. In this paper, we describe a heterogeneous wireless identification network mostly powered by kinetic energy, which allows the localization of animals in open environments. The system relies on radio communications and a global positioning system. It is made up of primary and secondary nodes. Secondary nodes are kinetic-powered and take advantage of animal movements to activate the node and transmit a specific identifier, reducing the number of batteries of the system. Primary nodes are battery-powered and gather secondary-node transmitted information to provide it, along with position and time data, to a final base station in charge of the animal monitoring. The system allows tracking based on contextual information obtained from statistical data.