High-Content Analysis of Breast Cancer Using Single-Cell Deep Transfer Learning

High-content analysis has revolutionized cancer drug discovery by identifying substances that alter the phenotype of a cell, which prevents tumor growth and metastasis. The high-resolution biofluorescence images from assays allow precise quantitative measures enabling the distinction of small molecules of a host cell from a tumor. In this work, we are particularly interested in the application of deep neural networks (DNNs), a cutting-edge machine learning method, to the classification of compounds in chemical mechanisms of action (MOAs). Compound classification has been performed using image-based profiling methods sometimes combined with feature reduction methods such as principal component analysis or factor analysis. In this article, we map the input features of each cell to a particular MOA class without using any treatment-level profiles or feature reduction methods. To the best of our knowledge, this is the first application of DNN in this domain, leveraging single-cell information. Furthermore, we use deep transfer learning (DTL) to alleviate the intensive and computational demanding effort of searching the huge parameter's space of a DNN. Results show that using this approach, we obtain a 30% speedup and a 2% accuracy improvement.

Framework development for providing accessibility to qualitative spatial calculi

Dissertation submitted in partial fulfillment of the requirements for the Degree of Master of Science in Geospatial Technologies.

Spatial point pattern analysis of gorilla nest sites in the Kagwene Sanctuary, Cameroon: Towards understanding the nesting behavior of a critically endangered subspecies

Dissertation submitted in partial fulfillment of the requirements for the Degree of Master of Science in Geospatial Technologies.

HIV-2 Integrase Polymorphisms and Longitudinal Genotypic Analysis of HIV-2 Infected Patients Failing a Raltegravir-Containing Regimen

To characterize the HIV-2 integrase gene polymorphisms and the pathways to resistance of HIV-2 patients failing a raltegravir-containing regimen, we studied 63 integrase strand transfer inhibitors (INSTI)-naïve patients, and 10 heavily pretreated patients exhibiting virological failure while receiving a salvage raltegravir-containing regimen. All patients were infected by HIV-2 group A. 61.4% of the integrase residues were conserved, including the catalytic motif residues. No INSTI-major resistance mutations were detected in the virus population from naïve patients, but two amino acids that are secondary resistance mutations to INSTIs in HIV-1 were observed. The 10 raltegravir-experienced patients exhibited resistance mutations via three main genetic pathways: N155H, Q148R, and eventually E92Q - T97A. The 155 pathway was preferentially used (7/10 patients). Other mutations associated to raltegravir resistance in HIV-1 were also observed in our HIV-2 population (V151I and D232N), along with several novel mutations previously unreported. Data retrieved from this study should help build a more robust HIV-2-specific algorithm for the genotypic interpretation of raltegravir resistance, and contribute to improve the clinical monitoring of HIV-2-infected patients.

Integrated study by NMR and X-ray Crystallography on the analysis of the molecular interactions in heme-binding proteins

Dissertação para obtenção do Grau de Doutor em Bioquímica, Especialidade Bioquímica Estrutural

Analysis of the intranuclear life of nonsense transcripts

Dissertação para obtenção do Grau de Doutor em Biologia, Especialidade de Biologia Molecular

Quantitative Analysis of Immunoglobulin E Reactivity Profiles in Patients Allergic or Sensitized to Natural Rubber Latex (Hevea Brasiliensis)

Characterized native and recombinant Hevea brasiliensis (rHev b) natural rubber latex (NRL) allergens are available to assess patient allergen sensitization profiles. OBJECTIVE: Quantification of individual IgE responses to the spectrum of documented NRL allergens and evaluation of cross-reactive carbohydrate determinants (CCDs) for more definitive diagnosis. METHODS: Sera of 104 healthcare workers (HCW; 51 German, 21 Portuguese, 32 American), 31 spina bifida patients (SB; 11 German, 20 Portuguese) and 10 Portuguese with multiple surgeries (MS) were analysed for allergen-specific IgE antibody (sIgE) to NRL, single Hev b allergens and CCDs with ImmunoCAP technology. RESULTS: In all patient groups rHev b 5-sIgE concentrations were the most pronounced. Hev b 2, 5, 6.01 and 13 were identified as the major allergens in HCW and combined with Hev b 1 and Hev b 3 in SB. In MS Hev b 1 displayed an intermediate relevance. Different sIgE antibody levels to native Hevea brasiliensis (nHev b) 2 and rHev b 6.01 allowed discrimination of SB with clinical relevant latex allergy vs. those with latex sensitization. Sensitization profiles of German, Portuguese and American patients were equivalent. rHev b 5, 6.01 and nHev b 13 combined detected 100% of the latex-allergic HCW and 80.1% of the SB. Only 8.3% of the sera showed sIgE response to CCDs. CONCLUSIONS: Hev b 1, 2, 5, 6.01 and 13 were identified as the major Hev b allergens and they should be present in standardized latex extracts and in vitro allergosorbents. CCDs are only of minor relevance in patients with clinical relevant latex allergy. Component-resolved diagnostic analyses for latex allergy set the stage for an allergen-directed immunotherapy strategy

The two-component system of a novel copper resistant operon of Marinobacter hydrocarbonoclasticus

Dissertation for the Master’s Degree in Structural and Functional Biochemistry

Factor analysis in the stock market: An application to statistical arbitrage

A Work Project, presented as part of the requirements for the Award of a Masters Degree in Finance from the NOVA – School of Business and Economics

Benchmarking in primary health care: An application of the stochasticd frontier analysis and the grades of membership approach to Portuguese family health units

A Work Project, presented as part of the requirements for the Award of a Masters Degree in Economics from the NOVA – School of Business and Economics

Time series morphological analysis applied to biomedical signals events detection

Dissertation submitted in the fufillment of the requirements for the Degree of Master in Biomedical Engineering

Environmental remediation project of Cunha Baixa mining area cost benefit analysis

A Work Project, presented as part of the requirements for the Award of a Masters Degree in Economics from the NOVA – School of Business and Economics

Analysis of PAX2 gene alterations in renal cell tumors

Dissertation for applying to a Master’s Degree in Molecular Genetics and Biomedicine submitted to the Sciences and Technology Faculty of New University of Lisbon

Biochemical behavior of Trypanosoma cruzi strains isolated from mice submitted to specific chemotherapy

To investigate the influence of chemotherapy on the biochemical beha vior of Trypanosoma cruzi strains, three groups of mice were infected with one of three strains of T. cruzi of different biological and isoenzymic patterns (Peruvian, 21 SF and Colombian strains). Each group was subdivided into subgroups: 1 - treated with nifurtimox; 2 - treated with benznidazole and 3 - untreated infected controls. At the end of treatment, that lasted for 90 days, xenodiagnosis, sub inoculation of blood into new born mice and haemoculture were performed as tests of cure. From the positive tests, 22 samples of T. cruzi were isolated from all subgroups. Electrophoretic analysis of the isoenzymes PGM, GP1, ALAT and AS AT failed to show any difference between parasite strains isolated from treated and untreated mice, which indicates that no detectable clonal selection or parasite genetic markers alterations concerning the isoenzymes analysed have been determined by treatment with drugs of recognized antiparasitic effect, suggesting stability of the phenotypic characteristics of the three biological types of T. cruzi strains.

Sentiment analysis on twitter for the portuguese language

Dissertação para obtenção do Grau de Mestre em Engenharia Informática