Improving the early diagnostic of prostate cancer by multiple biomarker detection with new biosensing devices

Prostate cancer (PCa) is the most common form of cancer in men, in Europe (World Health Organization data). The most recent statistics, in Portuguese territory, confirm this scenario, which states that about 50% of Portuguese men may suffer from prostate cancer and 15% of these will die from this condition. Its early detection is therefore fundamental. This is currently being done by Prostate Specific Antigen (PSA) screening in urine but false positive and negative results are quite often obtained and many patients are sent to unnecessary biopsy procedures. This early detection protocol may be improved, by the development of point-of-care cancer detection devices, not only to PSA but also to other biomarkers recently identified. Thus, the present work aims to screen several biomarkers in cultured human prostate cell lines, serum and urine samples, developing low cost sensors based on new synthetic biomaterials. Biomarkers considered in this study are the following: prostate specific antigen (PSA), annexin A3 (ANXA3), microseminoprotein-beta (MSMB) and sarcosine (SAR). The biomarker recognition may occurs by means of molecularly imprinted polymers (MIP), which are a kind of plastic antibodies, and enzymatic approaches. The growth of a rigid polymer, chemically stable, using the biomarker as a template allows the synthesis of the plastic antibody. MIPs show high sensitivity/selectivity and present much longer stability and much lower price than natural antibodies. This nanostructured material was prepared on a carbon solid. The interaction between the biomarker and the sensing-material produces electrical signals generating quantitative or semi-quantitative data. These devices allow inexpensive and portable detection in point-of-care testing.

Learning domain-specific sentiment lexicons with applications to recommender systems

Search is now going beyond looking for factual information, and people wish to search for the opinions of others to help them in their own decision-making. Sentiment expressions or opinion expressions are used by users to express their opinion and embody important pieces of information, particularly in online commerce. The main problem that the present dissertation addresses is how to model text to find meaningful words that express a sentiment. In this context, I investigate the viability of automatically generating a sentiment lexicon for opinion retrieval and sentiment classification applications. For this research objective we propose to capture sentiment words that are derived from online users’ reviews. In this approach, we tackle a major challenge in sentiment analysis which is the detection of words that express subjective preference and domain-specific sentiment words such as jargon. To this aim we present a fully generative method that automatically learns a domain-specific lexicon and is fully independent of external sources. Sentiment lexicons can be applied in a broad set of applications, however popular recommendation algorithms have somehow been disconnected from sentiment analysis. Therefore, we present a study that explores the viability of applying sentiment analysis techniques to infer ratings in a recommendation algorithm. Furthermore, entities’ reputation is intrinsically associated with sentiment words that have a positive or negative relation with those entities. Hence, is provided a study that observes the viability of using a domain-specific lexicon to compute entities reputation. Finally, a recommendation system algorithm is improved with the use of sentiment-based ratings and entities reputation.