Biomedical Event Extraction with Machine Learning

Biomedical natural language processing (BioNLP) is a subfield of natural language processing, an area of computational linguistics concerned with developing programs that work with natural language: written texts and speech. Biomedical relation extraction concerns the detection of semantic relations such as protein-protein interactions (PPI) from scientific texts. The aim is to enhance information retrieval by detecting relations between concepts, not just individual concepts as with a keyword search. In recent years, events have been proposed as a more detailed alternative for simple pairwise PPI relations. Events provide a systematic, structural representation for annotating the content of natural language texts. Events are characterized by annotated trigger words, directed and typed arguments and the ability to nest other events. For example, the sentence “Protein A causes protein B to bind protein C” can be annotated with the nested event structure CAUSE(A, BIND(B, C)). Converted to such formal representations, the information of natural language texts can be used by computational applications. Biomedical event annotations were introduced by the BioInfer and GENIA corpora, and event extraction was popularized by the BioNLP'09 Shared Task on Event Extraction. In this thesis we present a method for automated event extraction, implemented as the Turku Event Extraction System (TEES). A unified graph format is defined for representing event annotations and the problem of extracting complex event structures is decomposed into a number of independent classification tasks. These classification tasks are solved using SVM and RLS classifiers, utilizing rich feature representations built from full dependency parsing. Building on earlier work on pairwise relation extraction and using a generalized graph representation, the resulting TEES system is capable of detecting binary relations as well as complex event structures. We show that this event extraction system has good performance, reaching the first place in the BioNLP'09 Shared Task on Event Extraction. Subsequently, TEES has achieved several first ranks in the BioNLP'11 and BioNLP'13 Shared Tasks, as well as shown competitive performance in the binary relation Drug-Drug Interaction Extraction 2011 and 2013 shared tasks. The Turku Event Extraction System is published as a freely available open-source project, documenting the research in detail as well as making the method available for practical applications. In particular, in this thesis we describe the application of the event extraction method to PubMed-scale text mining, showing how the developed approach not only shows good performance, but is generalizable and applicable to large-scale real-world text mining projects. Finally, we discuss related literature, summarize the contributions of the work and present some thoughts on future directions for biomedical event extraction. This thesis includes and builds on six original research publications. The first of these introduces the analysis of dependency parses that leads to development of TEES. The entries in the three BioNLP Shared Tasks, as well as in the DDIExtraction 2011 task are covered in four publications, and the sixth one demonstrates the application of the system to PubMed-scale text mining.

Chemical derivatization of galactoglucomannan for functional materials

In the framework of the biorefinery concept researchers aspire to optimize the utilization of plant materials, such as agricultural wastes and wood. For most of the known processes, the first steps in the valorisation of biomass are the extraction and purification of the individual components. The obtained raw products by means of a controlled separation can consecutively be modified to result in biofuels or biogas for energy production, but also in value-added products such as additives and important building blocks for the chemical and material industries. Considerable efforts are undertaken in order to substitute the use of oil-based starting materials or at least minimize their processing for the production of everyday goods. Wood is one of the raw materials, which have gained large attention in the last decades and its composition has been studied in detail. Nowadays, the extraction of water-soluble hemicelluloses from wood is well known and so for example xylan can be obtained from hardwoods and O-acetyl galactoglucomannans (GGMs) from softwoods. The aim of this work was to develop water-soluble amphiphilic materials of GGM and to assess their potential use as additives. Furthermore, GGM was also applied as a crosslinker in the synthesis of functional hydrogels for the removal of toxic metals and metalloid ions from aqueous solutions. The distinguished products were obtained by several chemical approaches and analysed by nuclear magnetic resonance spectroscopy (NMR), Fourier transform infrared spectroscopy (FTIR), size exclusion chromatography (SEC), thermal gravimetric analysis (TGA), scanning electron microscope SEM, among others. Bio-based surfactants were produced by applying GGM and different fatty acids as starting materials. On one hand, GGM-grafted-fatty acids were prepared by esterification and on the other hand, well-defined GGM-block-fatty acid derivatives were obtained by linking amino-functional fatty acids to the reducing end of GGM. The reaction conditions for the syntheses were optimized and the resultant amphiphilic GGM derivatives were evaluated concerning their ability to reduce the surface tension of water as surfactants. Furthermore, the block-structured derivatives were tested in respect to their applicability as additives for the surface modification of cellulosic materials. Besides the GGM surfactants with a bio-based hydrophilic and a bio-based hydrophobic part, also GGM block-structured derivatives with a synthetic hydrophobic tail, consisting of a polydimethylsiloxane chain, were prepared and assessed for the hydrophobization of surface of nanofibrillated cellulose films. In order to generate GGM block-structured derivatives containing a synthetic tail with distinguished physical and chemical properties, as well as a tailored chain length, a controlled polymerization method was used. Therefore, firstly an initiator group was introduced at the reducing end of the GGM and consecutively single electron transfer-living radical polymerization (SET-LRP) was performed by applying three different monomers in individual reactions. For the accomplishment of the synthesis and the analysis of the products, challenges related to the solubility of the reactants had to be overcome. Overall, a synthesis route for the production of GGM block-copolymers bearing different synthetic polymer chains was developed and several derivatives were obtained. Moreover, GGM with different molar masses were, after modification, used as a crosslinker in the synthesis of functional hydrogels. Hereby, a cationic monomer was used during the free radical polymerization and the resultant hydrogels were successfully tested for the removal of chromium and arsenic ions from aqueous solutions. The hydrogel synthesis was tailored and materials with distinguished physical properties, such as the swelling rate, were obtained after purification. The results generated in this work underline the potential of bio-based products and the urge to continue carrying out research in order to be able to use more green chemicals for the manufacturing of biorenewable and biodegradable daily products.

Pressurized hot water flow-through extraction of birch wood

Effective processes to fractionate the main compounds in biomass, such as wood, are a prerequisite for an effective biorefinery. Water is environmentally friendly and widely used in industry, which makes it a potential solvent also for forest biomass. At elevated temperatures over 100 °C, water can readily hydrolyse and dissolve hemicelluloses from biomass. In this work, birch sawdust was extracted using pressurized hot water (PHWE) flow-through systems. The hypothesis of the work was that it is possible to obtain polymeric, water-soluble hemicelluloses from birch sawdust using flow-through PHW extractions at both laboratory and large scale. Different extraction temperatures in the range 140–200 °C were evaluated to see the effect of temperature to the xylan yield. The yields and extracted hemicelluloses were analysed to obtain sugar ratios, the amount of acetyl groups, furfurals and the xylan yields. Higher extraction temperatures increased the xylan yield, but decreased the molar mass of the dissolved xylan. As the extraction temperature increased, more acetic acid was released from the hemicelluloses, thus further decreasing the pH of the extract. There were only trace amounts of furfurals present after the extractions, indicating that the treatment was mild enough not to degrade the sugars further. The sawdust extraction density was increased by packing more sawdust in the laboratory scale extraction vessel. The aim was to obtain extracts with higher concentration than in typical extraction densities. The extraction times and water flow rates were kept constant during these extractions. The higher sawdust packing degree decreased the water use in the extractions and the extracts had higher hemicellulose concentrations than extractions with lower sawdust degrees of packing. The molar masses of the hemicelluloses were similar in higher packing degrees and in the degrees of packing that were used in typical PHWE flow-through extractions. The structure of extracted sawdust was investigated using small angle-(SAXS) and wide angle (WAXS) x-ray scattering. The cell wall topography of birch sawdust and extracted sawdust was compared using x-ray tomography. The results showed that the structure of the cell walls of extracted birch sawdust was preserved but the cell walls were thinner after the extractions. Larger pores were opened inside the fibres and cellulose microfibrils were more tightly packed after the extraction. Acetate buffers were used to control the pH of the extracts during the extractions. The pH control prevented excessive xylan hydrolysis and increased the molar masses of the extracted xylans. The yields of buffered extractions were lower than for plain water extractions at 160–170 °C, but at 180 °C yields were similar to those from plain water and pH buffers. The pH can thus be controlled during extraction with acetate buffer to obtain xylan with higher molar mass than those obtainable using plain water. Birch sawdust was extracted both in the laboratory and pilot scale. The performance of the PHWE flow-through system was evaluated in the laboratory and the pilot scale using vessels with the same shape but different volumes, with the same relative water flow through the sawdust bed, and in the same extraction temperature. Pre-steaming improved the extraction efficiency and the water flow through the sawdust bed. The extracted birch sawdust and the extracted xylan were similar in both laboratory and pilot scale. The PHWE system was successfully scaled up by a factor of 6000 from the laboratory to pilot scale and extractions performed equally well in both scales. The results show that a flow-through system can be further scaled up and used to extract water-soluble xylans from birch sawdust. Extracted xylans can be concentrated, purified, and then used in e.g. films and barriers, or as building blocks for novel material applications.

Intensification of hemicellulose hot-water extraction from spruce wood by parameter tuning

The growing population on earth along with diminishing fossil deposits and the climate change debate calls out for a better utilization of renewable, bio-based materials. In a biorefinery perspective, the renewable biomass is converted into many different products such as fuels, chemicals, and materials, quite similar to the petroleum refinery industry. Since forests cover about one third of the land surface on earth, ligno-cellulosic biomass is the most abundant renewable resource available. The natural first step in a biorefinery is separation and isolation of the different compounds the biomass is comprised of. The major components in wood are cellulose, hemicellulose, and lignin, all of which can be made into various end-products. Today, focus normally lies on utilizing only one component, e.g., the cellulose in the Kraft pulping process. It would be highly desirable to utilize all the different compounds, both from an economical and environmental point of view. The separation process should therefore be optimized. Hemicelluloses can partly be extracted with hot-water prior to pulping. Depending in the severity of the extraction, the hemicelluloses are degraded to various degrees. In order to be able to choose from a variety of different end-products, the hemicelluloses should be as intact as possible after the extraction. The main focus of this work has been on preserving the hemicellulose molar mass throughout the extraction at a high yield by actively controlling the extraction pH at the high temperatures used. Since it has not been possible to measure pH during an extraction due to the high temperatures, the extraction pH has remained a “black box”. Therefore, a high-temperature in-line pH measuring system was developed, validated, and tested for hot-water wood extractions. One crucial step in the measurements is calibration, therefore extensive efforts was put on developing a reliable calibration procedure. Initial extractions with wood showed that the actual extraction pH was ~0.35 pH units higher than previously believed. The measuring system was also equipped with a controller connected to a pump. With this addition it was possible to control the extraction to any desired pH set point. When the pH dropped below the set point, the controller started pumping in alkali and by that the desired set point was maintained very accurately. Analyses of the extracted hemicelluloses showed that less hemicelluloses were extracted at higher pH but with a higher molar-mass. Monomer formation could, at a certain pH level, be completely inhibited. Increasing the temperature, but maintaining a specific pH set point, would speed up the extraction without degrading the molar-mass of the hemicelluloses and thereby intensifying the extraction. The diffusion of the dissolved hemicelluloses from the wood particle is a major part of the extraction process. Therefore, a particle size study ranging from 0.5 mm wood particles to industrial size wood chips was conducted to investigate the internal mass transfer of the hemicelluloses. Unsurprisingly, it showed that hemicelluloses were extracted faster from smaller wood particles than larger although it did not seem to have a substantial effect on the average molar mass of the extracted hemicelluloses. However, smaller particle sizes require more energy to manufacture and thus increases the economic cost. Since bark comprises 10 – 15 % of a tree, it is important to also consider it in a biorefinery concept. Spruce inner and outer bark was hot-water extracted separately to investigate the possibility to isolate the bark hemicelluloses. It was showed that the bark hemicelluloses comprised mostly of pectic material and differed considerably from the wood hemicelluloses. The bark hemicelluloses, or pectins, could be extracted at lower temperatures than the wood hemicelluloses. A chemical characterization, done separately on inner and outer bark, showed that inner bark contained over 10 % stilbene glucosides that could be extracted already at 100 °C with aqueous acetone.

Continuous Counter-current Solvent Extraction of Magnesium and Calcium from Lithium-rich Brine

Solvent extraction of calcium and magnesium impurities from a lithium-rich brine (Ca ~ 2,000 ppm, Mg ~ 50 ppm, Li ~ 30,000 ppm) was investigated using a continuous counter-current solvent extraction mixer-settler set-up. The literature review includes a general review about resources, demands and production methods of Li followed by basics of solvent extraction. Experimental section includes batch experiments for investigation of pH isotherms of three extractants; D2EHPA, Versatic 10 and LIX 984 with concentrations of 0.52, 0.53 and 0.50 M in kerosene respectively. Based on pH isotherms LIX 984 showed no affinity for solvent extraction of Mg and Ca at pH ≤ 8 while D2EHPA and Versatic 10 were effective in extraction of Ca and Mg. Based on constructed pH isotherms, loading isotherms of D2EHPA (at pH 3.5 and 3.9) and Versatic 10 (at pH 7 and 8) were further investigated. Furthermore based on McCabe-Thiele method, two extraction stages and one stripping stage (using HCl acid with concentration of 2 M for Versatic 10 and 3 M for D2EHPA) was practiced in continuous runs. Merits of Versatic 10 in comparison to D2EHPA are higher selectivity for Ca and Mg, faster phase disengagement, no detrimental change in viscosity due to shear amount of metal extraction and lower acidity in stripping. On the other hand D2EHPA has less aqueous solubility and is capable of removing Mg and Ca simultaneously even at higher Ca loading (A/O in continuous runs > 1). In general, shorter residence time (~ 2 min), lower temperature (~23 °C), lower pH values (6.5-7.0 for Versatic 10 and 3.5-3.7 for D2EHPA) and a moderately low A/O value (< 1:1) would cause removal of 100% of Ca and nearly 100% of Mg while keeping Li loss less than 4%, much lower than the conventional precipitation in which 20% of Li is lost.

Excavation-drier method of energy-peat extraction reduces long-term climatic impact

Climatic impacts of energy-peat extraction are of increasing concern due to EU emissions trading requirements. A new excavation-drier peat extraction method has been developed to reduce the climatic impact and increase the efficiency of peat extraction. To quantify and compare the soil GHG fluxes of the excavation drier and the traditional milling methods, as well as the areas from which the energy peat is planned to be extracted in the future (extraction reserve area types), soil CO2, CH4 and N2O fluxes were measured during 2006–2007 at three sites in Finland. Within each site, fluxes were measured from drained extraction reserve areas, extraction fields and stockpiles of both methods and additionally from the biomass driers of the excavation-drier method. The Life Cycle Assessment (LCA), described at a principal level in ISO Standards 14040:2006 and 14044:2006, was used to assess the long-term (100 years) climatic impact from peatland utilisation with respect to land use and energy production chains where utilisation of coal was replaced with peat. Coal was used as a reference since in many cases peat and coal can replace each other in same power plants. According to this study, the peat extraction method used was of lesser significance than the extraction reserve area type in regards to the climatic impact. However, the excavation-drier method seems to cause a slightly reduced climatic impact as compared with the prevailing milling method.

Utilizing hemicelluloses – the first step : controlled extraction with hot water

Människor utnyttjar ofta kemi mångsidigt i sitt vardagliga liv utan att närmare tänka på detaljerna. Nuförtiden kan man framställa en ökande mängd av produkter ur förnybara råmaterial och en av de mest mångsidiga nybara råmaterialet i Norden är barrträd. Den lyriska lägerelden eller spiselden och möbler av ved samt papper är en väsentlig del av vardagen. Också livsmedel och läkemedel kan innehålla föreningar ur ved. Ved som råmaterial består av tre huvudkomponenten: cellulosa, som är uppbyggd av druvsockermolekyler är en långkedjad, oförgrenad polymer; lignin, som sammanhåller fibrerna i vedmaterialet som lim samt hemicellulosor, som ofta är uppbyggda av olika sockerarter och är en förgrenad polymer. Följaktligen består vedmaterialet av 70 % socker. I detta arbete har vi koncentrerat på i hemicellulosa och dess extraktion ur gran, samt bestämning av hemicellulosans egenskaper. Den slutliga målsättningen i forskningen var att skapa nya produkter ur gran. Forskning i extraktionens hemligheter eller hur hemicellulosa kan effektivt extraheras i den önskade formen kräver nya typers experimentellasanläggningar och experiment samt matematisk modellering. Den långkedjade hemicellulosan är lämplig för att användas t.ex. i skyddshinnor eller i livsmedel. Medel- och småmolekylär hemicellulosa kan användas som utgångsämne för framställning av bränslen, smörjmedel, sockersyror och alkoholer, av vilka xylitol är mest känd för alla pga hälsobefrämjande effekter. Det är utomordentligt viktigt ur miljöns och energiekonomins synvinkel att sträva efter effektivering av utnyttjandet av den värdefullaste och största naturtillgången, skogen i vårt land, med alla möjliga sätt. Resultaten av denna forskning utnyttjar avsevärt den växande, nya, på skogen baserande biobaseradeindustrin, som framställer nya spetsprodukter samt skapar nya arbetsplatser. ----------------------------------------------------- Ihmiset hyödyntävät usein huomaamattaan kemiaa monipuolisesti jokapäiväisessä elämässä. Nykyään kasvava määrä tuotteista kyetään valmistamaan uusiutuvista raaka-aineista ja yksi monipuolisimmista uusiutuvista luonnonvaroistamme pohjolassa ovat havupuut. Tunnelmallinen nuotio tai takkatuli ja puiset huonekalut sekä paperi ovat olennainen osa arkea. Myös elintarvikkeet ja lääkkeet voivat sisältää puusta peräisin olevia yhdisteitä. Puu materiaalina koostuu rakenteeltaan pääosin kolmesta osasta; selluloosasta, joka on rypälesokerista koostuva pitkäketjuinen haaroittumaton polymeeri, ligniinistä, joka toimii puun koossa pitävänä liima-aineena ja hemiselluloosasta, joka on useista eri sokereista rakentunut haaroittunut polymeeri. Näin ollen puusta 70 % on sokeria. Tässä työssä olemme keskittyneet hemiselluloosaan ja sen uuttamiseen kuusesta, sekä ominaisuuksien kartoittamiseen. Tutkimusaiheen lopullinen tavoite on luoda uusia tuotteita kuusesta. Uuton salojen tutkiminen eli miten hemiselluloosa saadaan tehokkaasti uutettua halutunlaisena vaatii uudenlaisia koelaitteistoja ja kokeita, sekä matemaattista mallintamista. Suurikokoinen hemiselluloosa on sopivaa käytettäväksi esimerkiksi suojakalvoissa tai elintarvikkeissa. Keskikokoista ja pienimolekyylistä hemiselluloosaa voidaan käyttää lähtöaineena valmistettaessa polttoaineita, voiteluaineita, sokerihappoja ja sokerialkoholeja, joista xylitoli on terveysvaikutustensa vuoksi kaikille tuttu. Niin ympäristömme kuin myös energiataloutemme kannalta on ensiarvoisen tärkeää pyrkiä kaikin keinoin tehostamaan maallemme arvokkaan, sekä luonnonvaroistamme yhden suurimman, metsän, vastuullista hyödyntämistä. Tämän tutkimuksen tulokset hyödyntävät merkittävästi maahamme nousevaa uutta metsään pohjautuvaa biojalostusteollisuutta, joka valmistaa uusia huipputuotteita sekä luo työpaikkoja.

Perfluorattuja yhdisteitä sisältävien jätevesien puhdistus- ja analyysimenetelmät

Perfluoratut alkyyliyhdisteet eli PFAS-yhdisteet ovat synteettisiä orgaanisia yhdisteitä, joissa on fluorattu hiiliketju. Hiilen ja fluorin väliset vahvat sidokset ovat muodostuneet ongelmaksi jätevedenpuhdistamoilla, sillä yhdisteet eivät hajoa puhdistamoilla käytössä olevilla vedenpuhdistusmenetelmillä. Yhdisteitä kertyy luontoon jätevesien mukana. Kandidaatintyössä on vertailtu yhdisteitä sisältävien vesien käsittelymenetelmiä parhaiten soveltuvan menetelmän löytämiseksi. Menetelmien kustannuksia tai soveltuvuutta vedenpuhdistamomittakaavan prosessiksi ei ole arvioitu. Lisäksi työssä on koottu yhdisteitä sisältävien jätevesien analysointiin sopivia analyysimenetelmiä. Soveltuvat puhdistus- ja analyysimenetelmät on esitelty uusien tieteellisten artikkelien pohjalta. Mahdollisia erotusmenetelmiä ovat membraanierotus ja sorptio. Membraaneista soveltuvimpia ovat nanosuodatus- ja käänteisosmoosimembraanit, joilla erottuvat jopa 0,0001 μm:n kokoiset partikkelit. PFAS-yhdisteet voidaan erottaa sorptiolla muun muassa aktiivihiileen. Yhdisteiden rakenne hajoaa nykyaikaisilla hapetusmenetelmillä ja polttamalla lietteen mukana. Hapettaminen permanganaatin avulla ei tuottanut hyvää tulosta, mutta fotokemiallisella hapetuksella ja alhaisen lämpötilan plasmatekniikalla (NTP) yhdisteiden rakenne hajosi lähes kokonaan. Fotokemiallinen hapetus onnistui erityisesti perfluorokarboksyylihapoilla, joiden rakenne hajosi jopa kolmessa tunnissa. Yleisimmin käytetty analyysimenetelmä on nestekromatografin ja massaspektrometrin yhdistelmä (LC-MS/MS) ja matriisivaikutus minimoidaan tyypillisesti kiinteäfaasiuutolla (SPE). Työssä esitellyistä käsittelymenetelmistä parhaiten soveltuva on NTP-menetelmä, koska sillä saatiin tutkimusten mukaan hajotettua yhdisteiden rakenne muita menetelmiä lyhyemmässä ajassa ja se soveltuu parhaiten kaikille PFAS-yhdisteille. NTP-menetelmässä ei tarvita katalyyttiä tai lisäkemikaaleja. Voimakkaana hapettimena toimivat epästabiilit hydroksyyliradikaalit, jotka syntyvät koronapurkauksen kautta. Koronapurkauksessa muodostuu myös otsonia ja lisäksi vapaa happi voi tehostaa hapettumista. Menetelmässä muodostuvien hajoamistuotteiden hallinta vaatii lisätutkimusta. Mahdollinen hallintakeino voisi olla esimerkiksi hapettumisessa vapautuvien fluoridi-ionien saostaminen. Muodostuvien hajoamistuotteiden toksisuutta voitaisiin tarkkailla biosensorilla.