An exploration of the effect of super large n-tuples on single layer RAMnets

N-tuple recognition systems (RAMnets) are normally modeled using a small number of input lines to each RAM, because the address space grows exponentially with the number of inputs. It is impossible to implement an arbitrarily-large address space as physical memory. But given modest amounts of training data, correspondingly modest numbers of bits will be set in that memory. Hash arrays can therefore be used instead of a direct implementation of the required address space. This paper describes some exploratory experiments using the hash array technique to investigate the performance of RAMnets with very large numbers of input lines. An argument is presented which concludes that performance should peak at a relatively small n-tuple size, but the experiments carried out so far contradict this. Further experiments are needed to confirm this unexpected result.

Handling varying amounts of missing data when classifying mental-health risk levels

One of the main challenges of classifying clinical data is determining how to handle missing features. Most research favours imputing of missing values or neglecting records that include missing data, both of which can degrade accuracy when missing values exceed a certain level. In this research we propose a methodology to handle data sets with a large percentage of missing values and with high variability in which particular data are missing. Feature selection is effected by picking variables sequentially in order of maximum correlation with the dependent variable and minimum correlation with variables already selected. Classification models are generated individually for each test case based on its particular feature set and the matching data values available in the training population. The method was applied to real patients' anonymous mental-health data where the task was to predict the suicide risk judgement clinicians would give for each patient's data, with eleven possible outcome classes: zero to ten, representing no risk to maximum risk. The results compare favourably with alternative methods and have the advantage of ensuring explanations of risk are based only on the data given, not imputed data. This is important for clinical decision support systems using human expertise for modelling and explaining predictions.

Expression of high amounts of the CD117 molecule in a case of B-cell non-Hodgkin's lymphoma carrying the t(14:18) translocation.

The c-kit proto-oncogen (CD117) has been described to be present in normal and neoplastic hemopoietic cells including both myeloid and lymphoid lineages. Among the normal lymphoid cells CD117 expression would be restricted to a small subset of NK-cells, and to early T-cell precursors and it is not expressed by normal B-cells. Regarding chronic lymphoproliferative disorders the only data provided up to now suggests that CD117 expression is restricted to cases of Hodgkin's disease and anaplastic large-cell lymphoma. In the present paper we describe a case of a B-cell chronic lymphoproliferative disorder carrying the t(14:18) translocation as demonstrated by molecular studies, in which the flow cytometric immunophenotypic analysis of both peripheral blood and bone marrow samples revealed the expression of high amounts of the CD117 antigen in the surface of the clonal B-cell population. Further studies are necessary to explore both the functional role of c-kit expression in the neoplastic B-cells from this patient and its potential utility for the diagnosis and follow-up of patients with B-cell non-Hodgkin's lymphoma.

Development of a novel platform for high-throughput gene design and artificial gene synthesis to produce large libraries of recombinant venom peptides for drug discovery

Tese de Doutoramento em Ciências Veterinárias na Especialidade de Ciências Biológicas e Biomédicas