A real-life overview of a hematopoietic cell transplant program throughout a four-year period, including prospective registry, exclusion causes and final donor selection

Traceability of patients who are candidates for Hematopoietic cell transplant (HCT) is crucial to ensure HCT program quality. Continuous knowledge of both a detailed registry from a HCT program and final exclusion causes can contribute to promoting a real-life vision and optimizing patient and donor selection. We analyzed epidemiological data reported in a 4 year-monocentric prospective registry, which included all patients presented as candidates for autologous (Auto) and/or allogeneic (Allo) HCT. A total of 543 patients were considered for HCT: 252 (42.4%) for Allo and 291 (57.6%) for Auto. A total of 98 (38.9%) patients were excluded from AlloHCT due to basal disease progression more commonly (18.2%). Seventy-six (30.2%) patients had an HLA identical sibling, whereas 147 (58.3%) patients had only Haplo. UD research was performed in 106 (42%) cases, significantly more often in myeloid than lymphoid malignancies (57% vs 28.7%, p < 0.001) but 61.3% were finally canceled, due to donor or disease causes in 72.4%. With respect to Auto candidates, a total of 60 (20.6%) patients were finally excluded; progression was the most common cause (12%). Currently, Haplo is the most frequent donor type. The high cancellation rate of UD research should be revised to optimize further donor algorithms.

Using machine learning techniques and genomic/proteomic information from known databases for defining relevant features for PPI classification

In modern proteomics, prediction of protein-protein interactions (PPIs) is a key research line, as these interactions take part in most essential biological processes. In this paper, a new approach is proposed to PPI data classification based on the extraction of genomic and proteomic information from well-known databases and the incorporation of semantic measures. This approach is carried out through the application of data mining techniques and provides very accurate models with high levels of sensitivity and specificity in the classification of PPIs. The well-known support vector machine paradigm is used to learn the models, which will also return a new confidence score which may help expert researchers to filter out and validate new external PPIs. One of the most-widely analyzed organisms, yeast, will be studied. We processed a very high-confidence dataset by extracting up to 26 specific features obtained from the chosen databases, half of them calculated using two new similarity measures proposed in this paper. Then, by applying a filter-wrapper algorithm for feature selection, we obtained a final set composed of the eight most relevant features for predicting PPIs, which was validated by a ROC analysis. The prediction capability of the support vector machine model using these eight features was tested through the evaluation of the predictions obtained in a set of external experimental, computational, and literature-collected datasets.

Generating balanced learning and test sets for function approximation problems

In function approximation problems, one of the most common ways to evaluate a learning algorithm consists in partitioning the original data set (input/output data) into two sets: learning, used for building models, and test, applied for genuine out-of-sample evaluation. When the partition into learning and test sets does not take into account the variability and geometry of the original data, it might lead to non-balanced and unrepresentative learning and test sets and, thus, to wrong conclusions in the accuracy of the learning algorithm. How the partitioning is made is therefore a key issue and becomes more important when the data set is small due to the need of reducing the pessimistic effects caused by the removal of instances from the original data set. Thus, in this work, we propose a deterministic data mining approach for a distribution of a data set (input/output data) into two representative and balanced sets of roughly equal size taking the variability of the data set into consideration with the purpose of allowing both a fair evaluation of learning's accuracy and to make reproducible machine learning experiments usually based on random distributions. The sets are generated using a combination of a clustering procedure, especially suited for function approximation problems, and a distribution algorithm which distributes the data set into two sets within each cluster based on a nearest-neighbor approach. In the experiments section, the performance of the proposed methodology is reported in a variety of situations through an ANOVA-based statistical study of the results.