Hannu Toivonen - Böcker

8. 1. 1 Protein Subcellular Location The life sciences have entered the post-genome era where the focus of biologicalresearchhasshiftedfromgenomesequencestoproteinfunctionality. Withwhole-genomedraftsofmouseandhumaninhand,scientistsareputting more and more e?ort into obtaining information about the entire proteome in a given cell type. The properties of a protein include its amino acid sequences, its expression levels under various developmental stages and in di?erenttissues,its3Dstructureandactivesites,itsfunctionalandstructural binding partners, and its subcellular location. Protein subcellular location is important for understanding protein function inside the cell. For example, the observation that the product of a gene is localized in mitochondria will support the hypothesis that this protein or gene is involved in energy metabolism. Proteins localized in the cytoskeleton are probably involved in intracellular tra?cking and support. The context of protein functionality is well represented by protein subcellular location. Proteins have various subcellular location patterns [250]. One major category of proteins is synthesized on free ribosomes in the cytoplasm. Soluble proteins remain in the cytoplasm after their synthesis and function as small factories catalyzing cellular metabolites. Other proteins that have a target signal in their sequences are directed to their target organelle (such as mitochondria) via posttranslational transport through the organelle membrane. Nuclear proteins are transferred through pores on the nuclear envelope to the nucleus and mostly function as regulators. The second major category of proteins is synthesized on endoplasmic reticulum(ER)-associated ribosomes and passes through the reticuloendothelial system, consisting of the ERand the Golgi apparatus.

The goal of this book is to help readers understand state-of-the-art techniques in biological data mining and data management and includes topics such as: - preprocessing tasks such as data cleaning and data integration as applied to biological data - classification and clustering techniques for microarrays - comparison of RNA structures based on string properties and energetics - discovery of the sequence characteristics of different parts of the genome - mining of haplotypes to find disease markers - sequencing of events leading to the folding of a protein - inference of the subcellular location of protein activity - classification of chemical compounds based on structure - special purpose metrics and index structures for phylogenetic applications - a new query language for protein searching based on the shape of proteins - very fast indexing schemes for sequences and pathways Aimed at computer scientists, necessary biology is explained.

This book constitutes the refereed preceedings of the 13th European Conference on Machine Learning, ECML 2002, held in Helsinki, Finland in August 2002.The 41 revised full papers presented together with 4 invited contributions were carefully reviewed and selected from numerous submissions. Among the topics covered are computational discovery, search strategies, Classification, support vector machines, kernel methods, rule induction, linear learning, decision tree learning, boosting, collaborative learning, statistical learning, clustering, instance-based learning, reinforcement learning, multiagent learning, multirelational learning, Markov decision processes, active learning, etc.

We are pleased to present the proceedings of the 13th European Conference on Machine Learning (LNAI 2430) and the 6th European Conference on Principles and Practice of Knowledge Discovery in Databases (LNAI 2431). These two c- ferences were colocated in Helsinki, Finland during August 19-23, 2002. ECML and PKDD were held together for the second year in a row, following the success of the colocation in Freiburg in 2001. Machine learning and knowledge discovery are two highly related ?elds and ECML/PKDD is a unique forum to foster their collaboration. The bene?t of colocation to both the machine learning and data mining communities is most clearly displayed in the common workshop, tutorial, and invited speaker program. Altogether six workshops and six tutorials were or- nized on Monday and Tuesday. As invited speakers we had the pleasure to have Erkki Oja (Helsinki Univ. of Technology), Dan Roth (Univ. of Illinois, Urbana- Champaign), Bernhard Scholkopf (Max Planck Inst. for Biological Cybernetics, Tubingen), and Padhraic Smyth (Univ. of California, Irvine). The main events ran from Tuesday until Friday, comprising 41 ECML te- nical papers and 39 PKDD papers.In total, 218 manuscripts were submitted to these two conferences: 95 to ECML, 70 to PKDD, and 53 as joint submissions. All papers were assigned at least three reviewers from our international program committees. Out of the 80 accepted papers 31 were ?rst accepted conditi- ally; the revised manuscripts were accepted only after the conditions set by the reviewers had been met.

Was genau ist eigentlich künstliche Intelligenz – und wie verändert sie unser Leben?Dieses Buch beantwortet hundert Fragen zur Funktionsweise, zu Chancen und Risiken sowie zu den gesellschaftlichen Auswirkungen von künstlicher Intelligenz – klar, prägnant und verständlich. Die Herausforderungen sind vielfältig: KI wirft Fragen nach Fairness, Verantwortung und Transparenz auf, sie stellt uns vor ethische Dilemmata, technische Grenzen und kulturelle Unterschiede. Gleichzeitig entwickelt sich das Feld so rasant, dass viele Antworten schnell überholt wirken könnten.Müssen wir uns vor KI fürchten? Warum macht sie Fehler? Kann sie bessere Entscheidungen treffen als Menschen? Kann ein Computerprogramm intelligent, kreativ oder gar bewusst sein? Dies sind nur einige der Fragen, die dieses Buch aufgreift. Auf witzige und unterhaltsame Art liefert das Werk Denkanstöße, sorgt für Aha-Momente und bietet Orientierung in einem komplexen, oft missverstandenen Themenfeld. Statt erschöpfender Abhandlungen finden die Leserinnen und Leser hier leicht zugängliche Antworten, die sich sowohl zum schnellen Nachschlagen als auch für vertieftes Nachdenken eignen. Die Texte sind wissenschaftlich fundiert, beruhen auf jahrzehntelanger Erfahrung und eröffnen klischeefrei neue, klare Perspektiven.