Predicción de la estructura secundaria de proteínas usando Máquinas de soporte Vectorial / Protein secondary structure prediction using support vector machines

Entre los métodos computacionales utilizados para la predicción de la estructura secundaria de proteí­nas, se destaca el uso de máquinas de soporte vectorial. Este trabajo de investigación presenta la predicción de la estructura secundaria de proteínas desde su secuencia primaria de aminoácidos usando Máquinas de Soporte Vectorial. Como entradas, en la metodologí­a propuesta, se utilizan características de los diferentes motivos estructurales o cadenas de texto asociadas a la estructura primaria que representa la estructura secundaria, tales como el R-grupo y la probabilidad de que el aminoácido en la posición central adopte una determinada estructura secundaria. Para la extracción de características se utiliza un método de codificación de secuencias en el que cada símbolo en la estructura primaria se relaciona con cada sí­mbolo en la estructura secundaria. El uso de este método de codificación permite reducir la dimensionalidad de los datos de miles de características a sólo 220 de estas. Los resultados obtenidos son comparables a los registrados en la literatura, teniendo cerca de un 70% de precisión. Además, se logra reducir los costos computacionales en la construcción de los clasificadores debido a que este trabajo modela el problema de multi-clasificación como un grupo de clasificadores binarios.

Among the computational methods used for predicting secondary structure proteins highlights the use of support vector machines. This research shows the predicted secondary structure of protein from its primary amino acid sequence using Support Vector Machines. As inputs, in the proposed methodology, features are used from different structural motifs or text strings associated with the primary structure which represents the secondary structure, such as R-group and the probability that the amino acid at position adopts a central particular secondary structure. For feature extraction method is used coding of sequences in which each symbol in the primary structure is associated with each symbol in the secondary structure. The use of this encoding method reduces the dimensionality of the data of thousands of characteristics only 220 of these. The results obtained are comparable to those reported in the literature, taking about 70% accuracy. Furthermore, it is possible to reduce computational cost in the construction of classifiers because this work models the problem of multi classification as a group of binary classifiers.

Defecto escrotal en una gammagrafía ósea / Scrotal defect on bone scintigraphy

No disponible

Patterns of chemotherapy administration in patients with intermediate-grade non-Hodgkin's lymphoma.

Records from 653 patients treated between 1991 and 1998 in the Oncology Practice Patterns Study (OPPS) were analyzed to determine contemporary chemotherapy delivery patterns in patients with intermediate-grade non-Hodgkin's lymphoma (NHL). Of the 653 patient records reviewed, 90 (14%) omitted an anthracycline or mitoxantrone (Novantrone) from primary therapy. Among patients receiving CHOP (cyclophosphamide [Cytoxan, Neosar], doxorubicin HCl, vincristine [Oncovin], prednisone) or CNOP (cyclophosphamide, mitoxantrone, vincristine, prednisone), 134 (27%) of 492 received an average relative dose intensity of less than 80% of the literature-referenced dose, due either to an inadequate planned or delivered dose. Of 181 advanced-stage patients with responsive disease, 28 (15%) failed to receive at least six treatment cycles. Overall, 283 (43%) of 653 patients potentially received suboptimal chemotherapy due either to choice of regimen or chemotherapy delivered. Patient age > or = 65 years and cardiac comorbidity appeared to have the greatest influence on a physician's decision regarding chemotherapy administration. Among the 492 patients who received CHOP or CNOP, 235 (48%) experienced a delay or reduction in chemotherapy dose (usually neutropenia-related), 100 (20%) developed mucositis, and 116 (24%) were hospitalized for febrile neutropenia. Growth factor was administered to 261 patients (53%), and its primary prophylactic use was associated with a significant reduction in the incidence of hospitalizations for febrile neutropenia in all patient subgroups receiving appropriate chemotherapeutic dose intensity (P = .02). This assessment of chemotherapy delivery to patients with intermediate-grade NHL showed significant variation from current standards. Further analysis of factors influencing chemotherapy delivery might improve therapeutic outcomes.

The role of Hispanic race/ethnicity and poverty in breast cancer survival.

The association of Hispanic race/ethnicity and poverty with general survival time and breast cancer survival time was examined for a total of 14,896 breast cancer patients (14,035 White and 861 Hispanic) included in the National Cancer Institute Surveillance Epidemiology and End Results (NCI SEER) program in New Mexico and San Francisco between 1975 and 1984. Variables examined included: age, marital status, stage at diagnosis, tumor histology, delay, treatment, period of diagnosis (1975-79 vs. 1980-84), and poverty. Univariate analysis of 14,896 patients indicated that a greater proportion of Hispanics (vs. Whites) with breast cancer were: younger than age 50, married, diagnosed at a later stage, diagnosed in New Mexico, lived in greater poverty, were diagnosed between 1980-84, and died from breast cancer. Univariate Cox Proportion Hazards analysis indicated that poverty was a significant predictor for reduced general survival time. Being diagnosed in the 1980-84 period was a predictor for improved general survival time. Poverty and Hispanic race/ethnicity were significant predictors of reduced breast cancer survival time. Multivariate Cox Proportional Hazards models indicated that Hispanic race/ethnicity was a significant risk factor for breast cancer survival time for women aged 50 and older. For White women: state, marital status, poverty, surgery, radiation/hormonal treatments, and histology were significant risk factors for breast cancer survival time. For Hispanic women: stage, surgery, hormonal treatment and period of diagnosis were significant risk factors for breast cancer survival time. For White breast cancer patients, period of diagnosis was not a significant risk factor for reduced breast cancer survival time; but for Hispanics, it was a significant risk factor. In the age and race/ethnicity-stratified models of breast cancer survival time, similar risk factors emerged for both Whites and Hispanics. For both younger and older Hispanics, being diagnosed in the early 1980's (vs. the late 1970's) was associated with reduced breast cancer survival time--vs. Whites, who experienced no significant change in breast cancer survival time in the same time period. Poverty was not a predictor for Hispanic survival time in any of the models; however, it was a predictor for younger Whites for breast cancer survival time. These results fueled discussion in three areas targeting breast cancer in underserved women: the development of racial/ethnic-specific cancer control guidelines, the development of a breast cancer integrated delivery system, and population management.