Explore the vast range of titles available.

Deep learning methods applied to drug discovery have been used to generate novel structures. In this study, we propose a new deep learning architecture, LatentGAN, which combines an autoencoder and a generative adversarial neural network for de novo molecular design. We applied the method in two scenarios: one to generate random drug-like compounds and another to generate target-biased compounds. Our results show that the method works well in both cases. Sampled compounds from the trained model can largely occupy the same chemical space as the training set and also generate a substantial fraction of novel compounds. Moreover, the drug-likeness score of compounds sampled from LatentGAN is also similar to that of the training set. Lastly, generated compounds differ from those obtained with a Recurrent Neural Network-based generative model approach, indicating that both methods can be used complementarily.

Generative models are becoming a tool of choice for exploring the molecular space. These models learn on a large training dataset and produce novel molecular structures with similar properties. Generated structures can be utilized for virtual screening or training semi-supervized predictive models in the downstream tasks. While there are plenty of generative models, it is unclear how to compare and rank them. In this work, we introduce a benchmarking platform called Molecular Sets (MOSES) to standardize training and comparison of molecular generative models. MOSES provides training and testing datasets, and a set of metrics to evaluate the quality and diversity of generated structures. We have implemented and compared several molecular generation models and suggest to use our results as reference points for further advancements in generative chemistry research. The platform and source code are available at https://github.com/molecularsets/moses .

Recurrent Neural Networks (RNNs) trained with a set of molecules represented as unique (canonical) SMILES strings, have shown the capacity to create large chemical spaces of valid and meaningful structures. Herein we perform an extensive benchmark on models trained with subsets of GDB-13 of different sizes (1 million, 10,000 and 1000), with different SMILES variants (canonical, randomized and DeepSMILES), with two different recurrent cell types (LSTM and GRU) and with different hyperparameter combinations. To guide the benchmarks new metrics were developed that define how well a model has generalized the training set. The generated chemical space is evaluated with respect to its uniformity, closedness and completeness. Results show that models that use LSTM cells trained with 1 million randomized SMILES, a non-unique molecular string representation, are able to generalize to larger chemical spaces than the other approaches and they represent more accurately the target chemical space. Specifically, a model was trained with randomized SMILES that was able to generate almost all molecules from GDB-13 with a quasi-uniform probability. Models trained with smaller samples show an even bigger improvement when trained with randomized SMILES models. Additionally, models were trained on molecules obtained from ChEMBL and illustrate again that training with randomized SMILES lead to models having a better representation of the drug-like chemical space. Namely, the model trained with randomized SMILES was able to generate at least double the amount of unique molecules with the same distribution of properties comparing to one trained with canonical SMILES.

This research aims to develop an automatic unmanned aerial vehicle (UAV)-based indoor environmental monitoring system for the acquisition of data at a very fine scale to detect rapid changes in environmental features of plants growing in greenhouses. Due to the complexity of the proposed research, in this paper we proposed an off-board distributed control system based on visual input for a micro aerial vehicle (MAV) able to hover, navigate, and fly to a desired target location without considerably affecting the effective flight time. Based on the experimental results, the MAV was able to land on the desired location within a radius of about 10 cm from the center point of the landing pad, with a reduction in the effective flight time of about 28%.

In the steel industry, waste hydrochloric acid is produced through the process to pickle steel slabs for removal of corrosion. Regenerated hydrochloric acid is obtained by separating the chloride gas from the waste product through spray roasting. This process also produces a by-product in the form of iron oxide which is sold to different industries. The present study is a continuation of a study arising from the need to better understand the dynamics inside the regeneration reactor, which in tum will improve possibilities to optimize the regeneration process, which to date has been manually adjusted by trial and error. In this study the velocity and temperature distribution inside the reactor is numerically modelled together with the droplet motion through the reactor. The main objective is to investigate the influence of a changed spray nozzle position on the flow characteristics of the continuous and dispersed phase, and the relation between temperature and energy efficiency and the regeneration process. Numerical models of the type of flow present in the regeneration reactor are not represented to any major extent in the literature, making the present study relevant to the engineers and researchers active in the steel industry and the application in question.

A problem that occurs in machine learning methods for drug discovery is a need for standardized data. Methods and interest exist for producing new data but due to material and budget constraints it is desirable that each iteration of producing data is as efficient as possible. In this thesis, we present two papers methods detailing different problems for selecting data to produce. We investigate Active Learning for models that use the margin in model decisiveness to measure the model uncertainty to guide data acquisition. We demonstrate that the models perform better with Active Learning than with random acquisition of data independent of machine learning model and starting knowledge. We also study the multi-objective optimization problem of combinatorial library design. Here we present a framework that could process the output of generative models for molecular design and give an optimized library design. The results show that the framework successfully optimizes a library based on molecule availability, for which the framework also attempts to identify using retrosynthesis prediction. We conclude that the next step in intelligent data acquisition is to combine the two methods and create a library design model that use the information of previous libraries to guide subsequent designs.

This study is primarily an account of my examination work in archival science which took place in the archive of Margareta Böttiger, the state epidemiologist at the Swedish Institute for Communicable Disease Control Stockholm. The records are from Böttigers period of work, mainly divided into three parts, polio, HIVS/AIDS and vaccination. Of these I have focused on polio with was the area she got renowned for. Moreover, owing to the uniqueness of the material this study has focused on the properties of the archive as a working-life archive which I propose as a special type of personal archive with unique attributes. To summarize, a working-life archive has in comparison with other personal archives a more fluid process of archiving where the profession is important, not the personal production of records. This leads to greater difficulties in determine importance and even a simpler process than other personal archives in the scheduling process.

Several approaches have been developed for improving the ship energy efficiency, thereby reducing operating costs and ensuring compliance with climate change mitigation regulations. Many of these approaches will heavily depend on measured data from onboard IoT devices, including operational and environmental information, as well as external data sources for additional navigational data. In this paper, we develop a framework that implements time-series analysis techniques to optimize the vessel's speed profile for improving the vessel's energy efficiency. We present a case study involving a real-world data from a passenger vessel that was collected over a span of 15 months in the south of Sweden. The results indicate that the implemented models exhibit a range of outcomes and adaptability across different scenarios. The findings highlight the effectiveness of time-series analysis approach for optimizing vessel voyages within the context of constrained landscapes, as often seen in short-sea shipping.

Artificial intelligence (AI) contributes new methods for designing compounds in drug discovery, ranging from de novo design models suggesting new molecular structures or optimizing existing leads to predictive models evaluating their toxicological properties. However, a limiting factor for the effectiveness of AI methods in drug discovery is the lack of access to high-quality data sets leading to a focus on approaches optimizing data generation. Combinatorial library design is a popular approach for bioactivity testing as a large number of molecules can be synthesized from a limited number of building blocks. We propose a framework for designing combinatorial libraries from de novo generated building blocks using k-Determinantal Point Processes and Gibbs sampling. We explore optimization of biological activity, Quantitative Estimate of Drug-likeness (QED) and diversity and the trade-offs between them, both in single-objective and in multi-objective library design settings. Using retrosynthesis models to estimate building block availability, the proposed framework is able to explore the prospective benefit from expanding a stock of available building blocks by synthesis or purchase the preferred building blocks before designing a library. In simulation experiments with building block collections from all available commercial vendors near-optimal libraries could be found without synthesis of additional building blocks; in other simulation experiments we showed that even one synthesis step to increase the number of available building blocks could improve library designs when starting with an in-house building block collection of reasonable size.

To meet the urgent requirements for the climate change mitigation, several proactive measures of energy efficiency have been implemented in maritime industry. Many of these practices depend highly on the onboard data of vessel's operation and environmental conditions. In this paper, a high resolution onboard data from passenger vessels in short-sea shipping (SSS) have been collected and preprocessed. We first investigated the available data to deploy it effectively to model the physics of the vessel, and hence the vessel performance. Since in SSS, the weather measurements and forecasts might have not been in temporal and spatial resolutions that accurately representing the actual environmental conditions. Then, We proposed a data-driven modeling approach for vessel energy efficiency. This approach addresses the challenges of data representation and energy modeling by combining and aggregating data from multiple sources and seamlessly integrates explainable artificial intelligence (XAI) to attain clear insights about the energy efficiency for a vessel in SSS. After that, the developed model of energy efficiency has been utilized in developing a framework for optimizing the vessel voyage to minimize the fuel consumption and meeting the constraint of arrival time. Moreover, we developed a spatial clustering approach for labeling the vessel paths to detect the paths for vessels with operating routes of repeatable and semi-repeatable paths.