Classification query

Definition 3-8 Interactive learning involves experiment generation and classification queries to an oracle. Passive learning is non-interactive learning. 

The bug location diagnoses in case of incompleteness and incorrectness are performed by experiment generation and classification queries to an oracle. Shapiro has experimented with three different search strategies to find a clause that covers a given atom (in case of incompleteness) ... 

Answers such as / don t know should also be taken into account. Classification queries are a particular case of universal queries and of existential queries, namely when there are no variables in A. Universal queries are a particular case of conditional queries, namely when C reduces to true. Similarly to our assumption about the consistency of specifications with intended relations, we assume that the specifier s answers to queries are noise-free. Note that we talk about questions to a (human) specifier here, and not about the more general problem of asking questions to some oracle. At this level of the discourse, we are not interested in knowing whether a mechanized oracle is queried during synthesis or not. 

The protein sequence database is also a text-numeric database with bibliographic links. It is the largest public domain protein sequence database. The current PIR-PSD release 75.04 (March, 2003) contains more than 280 000 entries of partial or complete protein sequences with information on functionalities of the protein, taxonomy (description of the biological source of the protein), sequence properties, experimental analyses, and bibliographic references. Queries can be started as a text-based search or a sequence similarity search. PIR-PSD contains annotated protein sequences with a superfamily/family classification. 

XLOGP, version 2.0, is written in C-h-. The program reads the query compound (represented in SYBYL/MOL2 format), performs atom classification, detects correction factors, and then calculates the log P value. Due to its simple methodology the program is quite fast. It can process about 100 medium-sized compounds per second on an SGI 02/R10000 workstahon. 

The 3D-PSSM (Kelley et ah, 2000) server at http //www.bmm.icnet.uk/ 3dpssm/ offers online protein fold recognition. On the submission form, enter your e-mail address and a one-line description of the query protein, then paste the query sequence into the sequence box and click the Submit button. The query sequence is used to search the Fold library for homologues. You will be informed of the URL where the result is located for 4 days. The output includes a summary table (hits with statistics models that can be viewed with RasMol classifications and links) and fold recognition by 3D-PSSM with a printout as exemplified in Figure 12.13. The alignment displays consensus sequence, secondary structures (C for coil, E for extended, and H for helix), and core score (0 for exterior to 9 for interior core). 

This phase classifies chemicals passing from the previous phase into active and inactive categories. Three structural alerts (Section IV.B), seven pharmacophore queries (Section IV.C), and the Decision Tree classification model (Section IV.D) were used in parallel to discriminate active from inactive chemicals. To ensure the lowest false negative rate in this phase, a chemical predicted to be active by any of these 11 models is subsequently evaluated in Phase III, whereas only those predicted to inactive by all these models are eliminated for further evaluation. Since structural alert, pharamacophore and Decision Tree methods incorporate and weight differently the various structural features that endow a chemical with the ability to bind the ER the combined outputs derived... 

The Physical Level contains all the nuts and bolts of the formulation domain in a number of information sources, including a database. The Physical Level is accessed from the Task Level via a query interface. The physical net contains the domain knowledge in a number of objects. An object consists of a set of attributes, each of which may have zero or more values. The objects are arranged in a classification hierarchy. Subobjects, which descend from another object, inherit their attributes and values. 

Templates can be selected using the target sequence as a query for searching protein structure databases [e.g. Brookhaven Protein Data Bank (PDB) http / /www.rcsb.org/pdb/index.html Structural Classification of Proteins (SCOP) scop.mrc-lmb.cam.ac.uk/scop/ DALI www2.ebi.ac.uk/dali/ Class, Architecture, Topology and Homologous superfamily classification at CATH www.biochem.ucl.a-c.uk/bsm/cath/). 

However, as will be shown later, the physical processes involved in the solvation of the inert gases, apolar and non-polar molecules are totally distinct from those involved in the solvation of ions. It could be queried as to whether it is valid to use the entropies of solvation of these substances as the basis of a classification of ions in solution. 

Define security and control requirements Query the manufacturing administrator for user classifications by task responsibilities and authorizations. Define the user privileges, activity logging requirements, and security controls. 

The EPA maintains many databases of environmental regulatory data. Among these is the Permit Compliance System (PCS) database http //www.epa.gov/enviro/html/ pcs/pcs query java.html. This database provides many of the details governing a facility s wastewater dischaiges. Specific limitations typically depend on the classification and flow of the stream to which a facility is discharging. SiuTace waters are classified as to their intended use (recreation, water supply, fishing, etc.), and then the relevant conditions to support those uses must be maintained. Wschatge limitations are then set so that pollution will not exce these criteria. 

An additional data source that Mobius allows users to create is the calculated field. A calculated field is simply a computed expression of arbitrary complexity involving one or more existing database fields for example, the ratio of two IC50 values for two different assays. The user can optionally apply a classification method to the output value of a calculated field to categorize the result. For example, the base calculated field could simply consist of a chemical structure column and the classification could assign a chemical template name to the structure based on a set of user-defined substructure query classification rules. As with annotation tables, calculated fields can be associated with project data and assigned security attributes. Both annotation tables and calculated fields are full members of the overall integrated database and can be searched, sorted, and combined with any other data in the database. 

Sometimes, the learner asks or queries an oracle (informant) for classification of examples it invents itself. The oracle is usually the teacher, but it is sometimes automated via reliance on other information, such as background knowledge. 

Restrictions on admissible presentations may have to be imposed, such as computability (below some complexity threshold), or ordering according to some total order. A positive presentation lists all and only the positive examples, whereas a complete presentation lists all the positive and negative examples. A presentation by informant queries an oracle for classification of examples as positive or negative examples. A mixed presentation combines complete presentation and presentation by informant. Repetition is usually allowed in admissible presentations. 

---