Abstract
Recent studies have shown that the microbiome can impact cancer development, progression, and response to therapies suggesting microbiome-based approaches for cancer characterization. As cancer-related signatures are complex and implicate many taxa, their discovery often requires Machine Learning approaches. This review discusses Machine Learning methods for cancer characterization from microbiome data. It focuses on the implications of choices undertaken during sample collection, feature selection and pre-processing. It also discusses ML model selection, guiding how to choose an ML model, and model validation. Finally, it enumerates current limitations and how these may be surpassed. Proposed methods, often based on Random Forests, show promising results, however insufficient for widespread clinical usage. Studies often report conflicting results mainly due to ML models with poor generalizability. We expect that evaluating models with expanded, hold-out datasets, removing technical artifacts, exploring representations of the microbiome other than taxonomical profiles, leveraging advances in deep learning, and developing ML models better adapted to the characteristics of microbiome data will improve the performance and generalizability of models and enable their usage in the clinic.

Abstract
The potential of ultrafast laser machining for the design of integrated optical devices in ULE (R) glass, a material known for its low coefficient of thermal expansion (CTE), is addressed. This was done through laser direct writing and characterization of optical waveguides and through the fabrication of 3D cavities inside the glass by following laser irradiation with chemical etching. Type I optical waveguides were produced and their internal loss mechanisms at 1550 nm were studied. Coupling losses lower than 0.2 dB cm-1 were obtained within a wide processing window. However, propagation loss lower than 4.2-4.3 dB cm-1 could not be realized, unlike in other glasses, due to laser-induced photodarkening. Selective-induced etching was observed over a large processing window and found to be maximum when irradiating the glass with a fs-laser beam linearly polarised orthogonally to the scanning direction, akin to what is observed in fused silica laser-machined microfluidic channels. In fact, the etching selectivity and surface roughness of laser-machined ULE (R) glass was found to be similar to that of fused silica, allowing some of the already reported microfluidic and optofluidic devices to be replicated in this low CTE glass. An example of a 3D cavity with planar-spherically convex interfaces is given. Due to the thermal properties of ULE (R) glass, these cavities can be employed as interferometers for wavelength and/or temperature referencing.

Abstract
This paper present an instance transformation procedure to modify known instances of the resource -constrained project scheduling problem to make them easier to solve by heuristic and/or exact solution algorithms. The procedure makes use of a set of transformation rules that aim at reducing the feasible search space without excluding at least one possible optimal solution. The procedure will be applied to a set of 11,183 instances and it will be shown by a set of experiments that these transformations lead to 110 improved lower bounds, 16 new and better schedules (found by three meta -heuristic procedures and a set of branch -and -bound procedures) and even 64 new optimal solutions which were never not found before.

Abstract
System operators (SO) require Converted-Interfaced Renewable Energy Systems (CI-RES) power plants investors to provide demonstrative studies related to different operational performance capabilities and advanced system services provision to the grid. Typically, these studies rely on Original Equipment Manufacturer (OEM) simulation models for the power converters and CI-RES power plants control units. Such models might be unavailable to the SO due to confidentiality reasons and might present challenges in parametrization due to their complexity. Moreover, compatibility issues between simulation packages used by the SO and those utilized by the independent entity performing the studies creates additional difficulties. Hence, SO demand to power plant investors the proving of equivalent simulation models and resorting preferably to standardized open-source models. This work presents a methodology to derive an equivalent model of a CI-RES power plant using Generic Renewable Energy Models (GREM) in which the parameters identification is performed exploiting an Evolutionary Particle Swarm Optimization (EPSO) to capture the plant's dynamic behaviour at the Point of Interconnection (POI) in face of a set of reference network disturbances. Considering as Case-Study the integration of a PV-Battery Hybrid power plat into the electrical system of Terceira Island, the results demonstrate successful derivation of GREM parameters allowing the representation of the dynamic behaviour of the power plant in face of network disturbance events. © Energynautics GmbH.

Abstract
Lung Cancer (LC) is still among the top main causes of death worldwide, and it is the leading death number among other cancers. Several AI-based methods have been developed for the early detection of LC, trying to use Computed Tomography (CT) images to identify the initial signs of the disease. The survival prediction could help the clinicians to adequate the treatment plan and all the proceedings, by the identification of the most severe cases that need more attention. In this study, several deep learning models were compared to predict the survival of LC patients using CT images. The best performing model, a CNN with 3 layers, achieved an AUC value of 0.80, a Precision value of 0.56 and a Recall of 0.64. The obtained results showed that CT images carry information that can be used to assess the survival of LC.

Abstract