RESUMEN
PURPOSE: The cure rate in Hodgkin lymphoma is high, but the response along with treatment is still unpredictable and highly variable among patients. Detecting those patients who do not respond to treatment at early stages could bring improvements in their treatment. This research tries to identify the main biological prognostic variables currently gathered at diagnosis and design a simple machine learning methodology to help physicians improve the treatment response assessment. METHODS: We carried out a retrospective analysis of the response to treatment of a cohort of 263 Caucasians who were diagnosed with Hodgkin lymphoma in Asturias (Spain). For that purpose, we used a list of 35 clinical and biological variables that are currently measured at diagnosis before any treatment begins. To establish the list of most discriminatory prognostic variables for treatment response, we designed a machine learning approach based on two different feature selection methods (Fisher's ratio and maximum percentile distance) and backwards recursive feature elimination using a nearest-neighbor classifier (k-NN). The weights of the k-NN classifier were optimized using different terms of the confusion matrix (true- and false-positive rates) to minimize risk in the decisions. RESULTS AND CONCLUSIONS: We found that the optimum strategy to predict treatment response in Hodgkin lymphoma consists in solving two different binary classification problems, discriminating first if the patient is in progressive disease; if not, then discerning among complete and partial remission. Serum ferritin turned to be the most discriminatory variable in predicting treatment response, followed by alanine aminotransferase and alkaline phosphatase. The importance of these prognostic variables suggests a close relationship between inflammation, iron overload, liver damage and the extension of the disease.
Asunto(s)
Protocolos de Quimioterapia Combinada Antineoplásica/uso terapéutico , Enfermedad de Hodgkin/tratamiento farmacológico , Inflamación/epidemiología , Sobrecarga de Hierro/epidemiología , Hepatopatías/epidemiología , Adulto , Anciano , Anciano de 80 o más Años , Bleomicina/uso terapéutico , Dacarbazina/uso terapéutico , Doxorrubicina/uso terapéutico , Femenino , Estudios de Seguimiento , Enfermedad de Hodgkin/patología , Humanos , Incidencia , Aprendizaje Automático , Masculino , Persona de Mediana Edad , Estadificación de Neoplasias , Pronóstico , Inducción de Remisión , Estudios Retrospectivos , Vinblastina/uso terapéuticoRESUMEN
Exponential growth in the number of available protein sequences is unmatched by the slower growth in the number of structures. As a result, the development of efficient and fast protein secondary structure prediction methods is essential for the broad comprehension of protein structures. Computational methods that can efficiently determine secondary structure can in turn facilitate protein tertiary structure prediction, since most methods rely initially on secondary structure predictions. Recently, we have developed a fast learning optimized prediction methodology (FLOPRED) for predicting protein secondary structure (Saraswathi et al. in JMM 18:4275, 2012). Data are generated by using knowledge-based potentials combined with structure information from the CATH database. A neural network-based extreme learning machine (ELM) and advanced particle swarm optimization (PSO) are used with this data to obtain better and faster convergence to more accurate secondary structure predicted results. A five-fold cross-validated testing accuracy of 83.8 % and a segment overlap (SOV) score of 78.3 % are obtained in this study. Secondary structure predictions and their accuracy are usually presented for three secondary structure elements: α-helix, ß-strand and coil but rarely have the results been analyzed with respect to their constituent amino acids. In this paper, we use the results obtained with FLOPRED to provide detailed behaviors for different amino acid types in the secondary structure prediction. We investigate the influence of the composition, physico-chemical properties and position specific occurrence preferences of amino acids within secondary structure elements. In addition, we identify the correlation between these properties and prediction accuracy. The present detailed results suggest several important ways that secondary structure predictions can be improved in the future that might lead to improved protein design and engineering.
Asunto(s)
Simulación por Computador , Proteínas/química , Secuencia de Aminoácidos , Enlace de Hidrógeno , Bases del Conocimiento , Modelos Moleculares , Redes Neurales de la Computación , Estructura Secundaria de ProteínaRESUMEN
Computational methods are rapidly gaining importance in the field of structural biology, mostly due to the explosive progress in genome sequencing projects and the large disparity between the number of sequences and the number of structures. There has been an exponential growth in the number of available protein sequences and a slower growth in the number of structures. There is therefore an urgent need to develop computational methods to predict structures and identify their functions from the sequence. Developing methods that will satisfy these needs both efficiently and accurately is of paramount importance for advances in many biomedical fields, including drug development and discovery of biomarkers. A novel method called fast learning optimized prediction methodology (FLOPRED) is proposed for predicting protein secondary structure, using knowledge-based potentials combined with structure information from the CATH database. A neural network-based extreme learning machine (ELM) and advanced particle swarm optimization (PSO) are used with this data that yield better and faster convergence to produce more accurate results. Protein secondary structures are predicted reliably, more efficiently and more accurately using FLOPRED. These techniques yield superior classification of secondary structure elements, with a training accuracy ranging between 83 % and 87 % over a widerange of hidden neurons and a cross-validated testing accuracy ranging between 81 % and 84 % and a segment overlap (SOV) score of 78 % that are obtained with different sets of proteins. These results are comparable to other recently published studies, but are obtained with greater efficiencies, in terms of time and cost.
Asunto(s)
Algoritmos , Biología Computacional/métodos , Estructura Secundaria de Proteína , Proteínas/química , Secuencia de Aminoácidos , Intervalos de Confianza , Bases de Datos de Proteínas , Modelos Moleculares , Datos de Secuencia MolecularRESUMEN
To evaluate dural puncture headache (DPH) after intradural anesthesia (IA) carried out by residents of anesthesiology and reanimation, and its relation with the degree of difficulty of the puncture, a sample of 81 patients with ages ranging between 48 and 88 years was evaluated. The incidence of DPH was 12.35%, and it was not statistically associated with age, sex, anesthetic approach, local anesthetic, or degree of difficulty of lumbar puncture.