Mining biomedical information from scientific literature

The rapid evolution and proliferation of a world-wide computerized network, the Internet, resulted in an overwhelming and constantly growing amount of publicly available data and information, a fact that was also verified in biomedicine. However, the lack of structure of textual data inhibits its direct processing by computational solutions. Information extraction is the task of text mining that intends to automatically collect information from unstructured text data sources. The goal of the work described in this thesis was to build innovative solutions for biomedical information extraction from scientific literature, through the development of simple software artifacts for developers and biocurators, delivering more accurate, usable and faster results. We started by tackling named entity recognition - a crucial initial task - with the development of Gimli, a machine-learning-based solution that follows an incremental approach to optimize extracted linguistic characteristics for each concept type. Afterwards, Totum was built to harmonize concept names provided by heterogeneous systems, delivering a robust solution with improved performance results. Such approach takes advantage of heterogenous corpora to deliver cross-corpus harmonization that is not constrained to specific characteristics. Since previous solutions do not provide links to knowledge bases, Neji was built to streamline the development of complex and custom solutions for biomedical concept name recognition and normalization. This was achieved through a modular and flexible framework focused on speed and performance, integrating a large amount of processing modules optimized for the biomedical domain. To offer on-demand heterogenous biomedical concept identification, we developed BeCAS, a web application, service and widget. We also tackled relation mining by developing TrigNER, a machine-learning-based solution for biomedical event trigger recognition, which applies an automatic algorithm to obtain the best linguistic features and model parameters for each event type. Finally, in order to assist biocurators, Egas was developed to support rapid, interactive and real-time collaborative curation of biomedical documents, through manual and automatic in-line annotation of concepts and relations. Overall, the research work presented in this thesis contributed to a more accurate update of current biomedical knowledge bases, towards improved hypothesis generation and knowledge discovery.

An extreme planetary system around HD 219828: one long-period super Jupiter to a hot-Neptune host star

Context. With about 2000 extrasolar planets confirmed, the results show that planetary systems have a whole range of unexpected properties. This wide diversity provides fundamental clues to the processes of planet formation and evolution. Aims: We present a full investigation of the HD 219828 system, a bright metal-rich star for which a hot Neptune has previously been detected. Methods: We used a set of HARPS, SOPHIE, and ELODIE radial velocities to search for the existence of orbiting companions to HD 219828. The spectra were used to characterise the star and its chemical abundances, as well as to check for spurious, activity induced signals. A dynamical analysis is also performed to study the stability of the system and to constrain the orbital parameters and planet masses. Results: We announce the discovery of a long period (P = 13.1 yr) massive (m sini = 15.1 MJup) companion (HD 219828 c) in a very eccentric orbit (e = 0.81). The same data confirms the existence of a hot Neptune, HD 219828 b, with a minimum mass of 21 M⊕ and a period of 3.83 days. The dynamical analysis shows that the system is stable, and that the equilibrium eccentricity of planet b is close to zero. Conclusions: The HD 219828 system is extreme and unique in several aspects. First, ammong all known exoplanet systems it presents an unusually high mass ratio. We also show that systems like HD 219828, with a hot Neptune and a long-period massive companion are more frequent than similar systems with a hot Jupiter instead. This suggests that the formation of hot Neptunes follows a different path than the formation of their hot jovian counterparts. The high mass, long period, and eccentricity of HD 219828 c also make it a good target for Gaia astrometry as well as a potential target for atmospheric characterisation, using direct imaging or high-resolution spectroscopy. Astrometric observations will allow us to derive its real mass and orbital configuration. If a transit of HD 219828 b is detected, we will be able to fully characterise the system, including the relative orbital inclinations. With a clearly known mass, HD 219828 c may become a benchmark object for the range in between giant planets and brown dwarfs.