Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Erythropoietin is a sialoglycoprotein which promotes the increase of erythropoiesis. Clinically is used for the treatment of anaemia associated to chronic renal failure. Identification and separation of isoforms of recombinant human erythropoietin (rhEPO) in biopharmaceuticals of different origins, was carried out by isoelectric focusing (IEF) western blotting and, also by lectin binding with Triticum vulgaris, showing 4-7 isoforms distributed in the isoeletric range of 4.4 to 5.2. N-acetylneuraminic acid content was quantified by reversed-phase liquid chromatography method with fluorescence detection giving values higher than 108.74 ηg/μg. Biological activity was evaluated by the normocythaemic mice bioassay, and investigating the TF-1 cell line in vitro. The correlation of the results of both of the methods were significant, as calculated by the Pearson s coefficient (r = 0.9967). In addition, the content/potency of the biopharmaceutical products was assessed by validated reversed phase and size exclusion liquid chromatography methods, showing mean values 2.11% and 1.21% lower, respectively, related to the in vivo bioassay. Sample was degraded under UV light to generate deamidate/sulphoxide forms and treatment at 65ºC for 12 hours to produce dimeric and aggregated forms. The potencies were evaluated by the normocythaemic mice assay and the TF-1 cell culture assay giving mean reduction of 14.05% and 32.87%, respectively, related to the intact molecule. The alternative in vitro assay investigated in the context of the reduction or replacement of the animals, and the evaluation of the correlations between physicochemical and biological methods, represent improvements which can be applied to the production steps and for the quality control of rhEPO, contributing to ensure the batch-to-batch consistency of bulk and finished biological products. / A eritropoietina é uma sialoglicoproteína que promove o aumento da eritropoiese. Clinicamente é usada para o tratamento de anemias associadas à falência renal crônica. No presente realizou-se identificação e separação das isoformas de eritropoietina humana recombinante (rhEPO) em produtos biofarmacêuticos de diferentes origens, por focalização isoelétrica (IEF), seguida de imunodetecção, e também por ligação à lectina Triticum vulgaris, demonstrando a presença de 4 a 7 isoformas, distribuídas na faixa de ponto isoelétrico de 4,4 a 5,2. Quantificou-se o conteúdo de ácido N-acetilneuramínico por cromatografia líquida por fase-reversa e detecção por fluorescência obtendo teores acima de 108,74 ηg/μg. Avaliou-se a atividade biológica pelo bioensaio em camundongos normocitêmicos e pesquisou-se o ensaio alternativo baseado na cultura da linhagem celular TF-1 in vitro. Os resultados dos bioensaios apresentaram correlação significativa, conforme calculado pelo coeficiente de correlação de Pearson (r = 0,9967). Paralelamente, determinou-se o teor/potência dos produtos pelas metodologias validadas por cromatografia líquida por fase reversa e por exclusão molecular, que forneceram média de resultados 2,11% e 1,21% menores, respectivamente, em relação ao bioensaio in vivo. Submeteu-se amostra à degradação por luz UV para obter as formas desamidadas/oxidadas e tratamento a 65°C por 12 horas para as diméricas e agregadas. Efetuou-se a avaliação pelo bioensaio in vivo e in vitro, que apresentaram redução média de 14,05% e 32,87% respectivamente, em relação à molécula intacta. Desse modo, o ensaio biológico alternativo in vitro, pesquisado no contexto da redução ou substituição do uso de animais, e as avaliações de correlação entre métodos físico-químicos e biológicos, representam aprimoramentos aplicáveis para as etapas do processo de produção e para o controle de qualidade de rhEPO, contribuindo para garantir a consistência lote-a-lote da solução concentrada e dos produto biológicos acabados.

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Erythropoietin is a hematopoietic hormone and the main physiological function is the induction of erythropoiesis. Recombinant DNA technology enabled cloning and expression of rhEPO gene to produce recombinant human erythropoietin (rhEPO). It is a sialoglycoprotein composed of 165 amino acids chain and about 40% of the molecule consists of carbohydrates, important for biological activity due to the presence of sialic acid residues at the termini of chains affecting its half-life. In the present study an alternative in vitro cell culture-based assay using TF-1 cell line was validated, to be used in conjunction with a reversed-phase liquid chromatography method with fluorescence detection (F-RP-LC) validated to determine the content of sialic acids. The values obtained for the sialic acids were higher than 126.83 ng/μg, and the biotechnology-derived products were subjected to the cell culture bioassay giving potencies 2.91% ± 0.85 lower related to the bioassay in normocythaemic mice, with significant correlation calculated by the Pearson coefficient (r = 0.9947). In parallel, it was determined the content/potency of the products by the validated reversed-phase and size-exclusion liquid chromatography methods that showed mean results 3.14% higher and 2.87% lower, respectively, compared to the in vitro bioassay. It was demonstrated that in vitro cell culture bioassay represent a valid alternative to the in vivo bioassay for the potency assessment of rhEPO, in the context of the reduction and/or replacement of animals. Likewise, correlation of the results obtained with the physicochemical methods, represents advances for the characterization of the biomolecule, which can be applied to the production steps and for the quality control, contributing to assure the batch-to-batch consistency of the bulk and the finished biological products of rhEPO. / A eritropoietina é um hormônio hematopoiético cuja principal função fisiológica é a indução da eritropoiese. Através da tecnologia do DNA recombinante foi possível a clonagem e expressão do gene para produzir a eritropoietina humana recombinante (rhEPO). É uma sialoglicoproteína composta por cadeia de 165 aminoácidos e, aproximadamente, 40% da molécula é constituída de carboidratos, importantes para a atividade biológica devido à presença de resíduos de ácidos siálicos nas extremidades das cadeias, que influenciam na meia-vida da biomolécula. No presente estudo foi validado ensaio alternativo baseado na cultura da linhagem de células TF-1 in vitro, e método por cromatografia líquida por fase reversa com detecção por fluorescência para determinação de ácidos siálicos, para avaliação em conjunto da potência de rhEPO. Determinaram-se teores de ácidos siálicos acima de 126,83 ng/μg e os produtos biotecnológicos foram submetidos ao bioensaio por cultura de células fornecendo potências 2,91% ± 0,85 menores em relação ao ensaio biológico em camundongos normocitêmicos, com correlação significativa calculada pelo coeficiente de correlação de Pearson (r = 0,9947). Paralelamente, determinou-se o teor/potência dos produtos pelas metodologias validadas por cromatografia líquida por fase reversa e por exclusão molecular, que forneceram média de resultados 3,14% maior e 2,87% menor, respectivamente, em relação ao bioensaio in vitro. Demonstrou-se que o bioensaio por cultura de células in vitro, constitui-se em alternativa ao ensaio biológico in vivo para a avaliação de potência de rhEPO, no contexto da redução e/ou substituição do uso de animais. Do mesmo modo, a correlação com os resultados fornecidos pelos métodos físico-químicos, representa avanços para caracterização da biomolécula, que podem ser aplicados nas etapas do processo de produção e para o controle de qualidade, contribuindo para garantir a consistência lote-a-lote da solução concentrada e dos produtos biológicos acabados de rhEPO.

Understanding the functional impact of physical interactions between proteins and DNA on gene expression is important for developing approaches to correct disease-associated gene dysregulation. I conducted a systematic, functional genetic analysis of protein-DNA interactions in the promoter region of the yeast ribonucleotide reductase subunit gene RNR3. I measured the transcriptional impact of systematically perturbing the major transcriptional regulator, Crt1, and three X-box sites on the DNA known to physically bind Crt1. This analysis revealed interactions between two of the three X-boxes in the presence of Crt1, and unexpectedly, a significant functional role of the X-boxes in the absence of Crt1. Further analysis revealed Crt1- independent regulators of RNR3 that were impacted by X-box perturbation. Taken together, these results support the notion that higher-order X-box-mediated interactions are important for RNR3 transcription, and that the X-boxes have unexpected roles in the regulation of RNR3 transcription that extend beyond their interaction with Crt1.

This work is concerned by the issue of calibrating a robotic workplace, including the localization of a calibration object for the purpose of calibrating a 2D or 3D camera, a robotic arm and a scene of robotic workplace. At first, the problems related to the calibration of the aforementioned elements were studied. Further, an analysis of suitable methods for performing these calibrations was performed. The result of this work is application of ROS robotic system providing methods for three different types of calibration programs, whose functionality is experimentally verified at the end of this work.

The master's thesis deals with automatic classifi cation of text document. It explains basic terms and problems of text mining. The thesis explains term clustering and shows some basic clustering algoritms. The thesis also shows some methods of classi fication and deals with matrix regression closely. Application using matrix regression for classifi cation was designed and developed. Experiments were focused on normalization and thresholding.

The thesis deals with machine processing of textual data. In the theoretical part, issues related to natural language processing are described and different ways of pre-processing and representation of text are also introduced. The thesis also focuses on the usage of N-grams as features for document representation and describes some algorithms used for their extraction. The next part includes an outline of classification methods used. In the practical part, an application for pre-processing and creation of different textual data representations is suggested and implemented. Within the experiments made, the influence of these representations on accuracy of classification algorithms is analysed.

This thesis focuses on finding an end-to-end unsupervised solution to solve a two-step problem of extracting semantically meaningful topics and trend analysis of these topics from a large temporal text corpus. To achieve this, the focus is on using the latest develop- ments in Natural Language Processing (NLP) related to pre-trained language models like Google’s Bidirectional Encoder Representations for Transformers (BERT) and other BERT based models. These transformer-based pre-trained language models provide word and sentence embeddings based on the context of the words. The results are then compared with traditional machine learning techniques for topic modeling. This is done to evalu- ate if the quality of topic models has improved and how dependent the techniques are on manually defined model hyperparameters and data preprocessing. These topic models provide a good mechanism for summarizing and organizing a large text corpus and give an overview of how the topics evolve with time. In the context of research publications or scientific journals, such analysis of the corpus can give an overview of research/scientific interest areas and how these interests have evolved over the years. The dataset used for this thesis is research articles and papers from a journal, namely ’Journal of Cleaner Productions’. This journal has more than 24000 research articles at the time of working on this project. We started with implementing Latent Dirichlet Allocation (LDA) topic modeling. In the next step, we implemented LDA along with document clus- tering to get topics within these clusters. This gave us an idea of the dataset and also gave us a benchmark. After having some base results, we explored transformer-based contextual word and sentence embeddings to evaluate if this leads to more meaningful, contextual, and semantic topics. For document clustering, we have used K-means clustering. In this thesis, we also discuss methods to optimally visualize the topics and the trend changes of these topics over the years. Finally, we conclude with a method for leveraging contextual embeddings using BERT and Sentence-BERT to solve this problem and achieve semantically meaningful topics. We also discuss the results from traditional machine learning techniques and their limitations.

The goal of this project is to investigate any correlation between marketing emails and their receivers using machine learning and only a limited amount of initial data. The data consists of roughly 1200 emails and 98.000 receivers of these. Initially, the emails are grouped together based on their content using text clustering. They contain no information regarding prior labeling or categorization which creates a need for an unsupervised learning approach using solely the raw text based content as data. The project investigates state-of-the-art concepts like bag-of-words for calculating term importance and the gap statistic for determining an optimal number of clusters. The data is vectorized using term frequency - inverse document frequency to determine the importance of terms relative to the document and to all documents combined. An inherit problem of this approach is high dimensionality which is reduced using latent semantic analysis in conjunction with singular value decomposition. Once the resulting clusters have been obtained, the most frequently occurring terms for each cluster are analyzed and compared. Due to the absence of initial labeling an alternative approach is required to evaluate the clusters validity. To do this, the receivers of all emails in each cluster who actively opened an email is collected and investigated. Each receiver have different attributes regarding their purpose of using the service and some personal information. Once gathered and analyzed, conclusions could be drawn that it is possible to find distinguishable connections between the resulting email clusters and their receivers but to a limited extent. The receivers from the same cluster did show similar attributes as each other which were distinguishable from the receivers of other clusters. Hence, the resulting email clusters and their receivers are specific enough to distinguish themselves from each other but too general to handle more detailed information. With more data, this could become a useful tool for determining which users of a service should receive a particular email to increase the conversion rate and thereby reach out to more relevant people based on previous trends. / Målet med detta projekt att undersöka eventuella samband mellan marknadsföringsemail och dess mottagare med hjälp av oövervakad maskininlärning på en brgränsad mängd data. Datan består av ca 1200 email meddelanden med 98.000 mottagare. Initialt så gruperas alla meddelanden baserat på innehåll via text klustering. Meddelandena innehåller ingen information angående tidigare gruppering eller kategorisering vilket skapar ett behov för ett oövervakat tillvägagångssätt för inlärning där enbart det råa textbaserade meddelandet används som indata. Projektet undersöker moderna tekniker så som bag-of-words för att avgöra termers relevans och the gap statistic för att finna ett optimalt antal kluster. Datan vektoriseras med hjälp av term frequency - inverse document frequency för att avgöra relevansen av termer relativt dokumentet samt alla dokument kombinerat. Ett fundamentalt problem som uppstår via detta tillvägagångssätt är hög dimensionalitet, vilket reduceras med latent semantic analysis tillsammans med singular value decomposition. Då alla kluster har erhållits så analyseras de mest förekommande termerna i vardera kluster och jämförs. Eftersom en initial kategorisering av meddelandena saknas så krävs ett alternativt tillvägagångssätt för evaluering av klustrens validitet. För att göra detta så hämtas och analyseras alla mottagare för vardera kluster som öppnat något av dess meddelanden. Mottagarna har olika attribut angående deras syfte med att använda produkten samt personlig information. När de har hämtats och undersökts kan slutsatser dras kring hurvida samband kan hittas. Det finns ett klart samband mellan vardera kluster och dess mottagare, men till viss utsträckning. Mottagarna från samma kluster visade likartade attribut som var urskiljbara gentemot mottagare från andra kluster. Därav kan det sägas att de resulterande klustren samt dess mottagare är specifika nog att urskilja sig från varandra men för generella för att kunna handera mer detaljerad information. Med mer data kan detta bli ett användbart verktyg för att bestämma mottagare av specifika emailutskick för att på sikt kunna öka öppningsfrekvensen och därmed nå ut till mer relevanta mottagare baserat på tidigare resultat.

Eftersom samhället blir allt mer datadrivet revolutionerar användningen av AI och maskininlärning sättet företag fungerar och utvecklas på. Denna studie utforskar användningen av AI, Big Data och Natural Language Processing (NLP) för att förbättra affärsverksamhet och intelligens i företag. Huvudsyftet med denna avhandling är att undersöka om den nuvarande klassificeringsprocessen hos värdorganisationen kan upprätthållas med minskade driftskostnader, särskilt lägre moln-GPU-kostnader. Detta har potential att förbättra klassificeringsmetoden, förbättra produkten som företaget erbjuder sina kunder på grund av ökad klassificeringsnoggrannhet och stärka deras värdeerbjudande. Vidare utvärderas tre tillvägagångssätt mot varandra och implementationerna visar utvecklingen inom området. Modellerna som jämförs i denna studie inkluderar traditionella maskininlärningsmetoder som Support Vector Machine (SVM) och Logistisk Regression, tillsammans med state-of-the-art transformermodeller som BERT, både Pre-Trained och Fine-Tuned. Artikeln visar att det finns en avvägning mellan prestanda och kostnad vilket illustrerar problemet som många företag, som Valu8, står inför när de utvärderar vilket tillvägagångssätt de ska implementera. Denna avvägning diskuteras och analyseras sedan mer detaljerat för att utforska möjliga kompromisser från varje perspektiv i ett försök att hitta en balanserad lösning som kombinerar prestandaeffektivitet och kostnadseffektivitet. / As society is becoming more data-driven, Artificial Intelligence (AI) and Machine Learning are revolutionizing how companies operate and evolve. This study explores the use of AI, Big Data, and Natural Language Processing (NLP) in improving business operations and intelligence in enterprises. The primary objective of this thesis is to examine if the current classification process at the host company can be maintained with reduced operating costs, specifically lower cloud GPU costs. This can improve the classification method, enhance the product the company offers its customers due to increased classification accuracy, and strengthen its value proposition. Furthermore, three approaches are evaluated against each other, and the implementations showcase the evolution within the field. The models compared in this study include traditional machine learning methods such as Support Vector Machine (SVM) and Logistic Regression, alongside state-of-the-art transformer models like BERT, both Pre-Trained and Fine-Tuned. The paper shows a trade-off between performance and cost, showcasing the problem many companies like Valu8 stand before when evaluating which approach to implement. This trade-off is discussed and analyzed in further detail to explore possible compromises from each perspective to strike a balanced solution that combines performance efficiency and cost-effectiveness.

Le regroupement est une tâche non supervisée consistant à rassembler les éléments semblables sous un même groupe et les éléments différents dans des groupes distincts. Le regroupement de textes est effectué en représentant les textes dans un espace vectoriel et en étudiant leur similarité dans cet espace. Les meilleurs résultats sont obtenus à l’aide de modèles neuronaux qui affinent une représentation vectorielle contextuelle de manière non supervisée. Or, cette technique peuvent nécessiter un temps d’entraînement important et sa performance n’est pas comparée à des techniques plus simples ne nécessitant pas l’entraînement de modèles neuronaux. Nous proposons, dans ce mémoire, une étude de l’état actuel du domaine. Tout d’abord, nous étudions les meilleures métriques d’évaluation pour le regroupement de textes. Puis, nous évaluons l’état de l’art et portons un regard critique sur leur protocole d’entraînement. Nous proposons également une analyse de certains choix d’implémentation en regroupement de textes, tels que le choix de l’algorithme de regroupement, de la mesure de similarité, de la représentation vectorielle ou de l’affinage non supervisé de la représentation vectorielle. Finalement, nous testons la combinaison de certaines techniques ne nécessitant pas d’entraînement avec la représentation vectorielle contextuelle telles que le prétraitement des données, la réduction de dimensionnalité ou l’inclusion de Tf-idf. Nos expériences démontrent certaines lacunes dans l’état de l’art quant aux choix des métriques d’évaluation et au protocole d’entraînement. De plus, nous démontrons que l’utilisation de techniques simples permet d’obtenir des résultats meilleurs ou semblables à des méthodes sophistiquées nécessitant l’entraînement de modèles neuronaux. Nos expériences sont évaluées sur huit corpus issus de différents domaines. / Clustering is an unsupervised task of bringing similar elements in the same cluster and different elements in distinct groups. Text clustering is performed by representing texts in a vector space and studying their similarity in this space. The best results are obtained using neural models that fine-tune contextual embeddings in an unsupervised manner. However, these techniques require a significant amount of training time and their performance is not compared to simpler techniques that do not require training of neural models. In this master’s thesis, we propose a study of the current state of the art. First, we study the best evaluation metrics for text clustering. Then, we evaluate the state of the art and take a critical look at their training protocol. We also propose an analysis of some implementation choices in text clustering, such as the choice of clustering algorithm, similarity measure, contextual embeddings or unsupervised fine-tuning of the contextual embeddings. Finally, we test the combination of contextual embeddings with some techniques that don’t require training such as data preprocessing, dimensionality reduction or Tf-idf inclusion. Our experiments demonstrate some shortcomings in the state of the art regarding the choice of evaluation metrics and the training protocol. Furthermore, we demonstrate that the use of simple techniques yields better or similar results to sophisticated methods requiring the training of neural models. Our experiments are evaluated on eight benchmark datasets from different domains.