RESUMO
BACKGROUND: Various methods for differential expression analysis have been widely used to identify features which best distinguish between different categories of samples. Multiple hypothesis testing may leave out explanatory features, each of which may be composed of individually insignificant variables. Multivariate hypothesis testing holds a non-mainstream position, considering the large computation overhead of large-scale matrix operation. Random forest provides a classification strategy for calculation of variable importance. However, it may be unsuitable for different distributions of samples. RESULTS: Based on the thought of using an ensemble classifier, we develop a feature selection tool for differential expression analysis on expression profiles (i.e., ECFS-DEA for short). Considering the differences in sample distribution, a graphical user interface is designed to allow the selection of different base classifiers. Inspired by random forest, a common measure which is applicable to any base classifier is proposed for calculation of variable importance. After an interactive selection of a feature on sorted individual variables, a projection heatmap is presented using k-means clustering. ROC curve is also provided, both of which can intuitively demonstrate the effectiveness of the selected feature. CONCLUSIONS: Feature selection through ensemble classifiers helps to select important variables and thus is applicable for different sample distributions. Experiments on simulation and realistic data demonstrate the effectiveness of ECFS-DEA for differential expression analysis on expression profiles. The software is available at http://bio-nefu.com/resource/ecfs-dea.
Assuntos
Perfilação da Expressão Gênica/métodos , Software , Curva ROCRESUMO
Motivation: Pentatricopeptide repeat (PPR), which is a triangular pentapeptide repeat domain, plays an important role in plant growth. Features extracted from sequences are applicable to PPR protein identification using certain classification methods. However, which components of a multidimensional feature (namely variables) are more effective for protein discrimination has never been discussed. Therefore, we seek to select variables from a multidimensional feature for identifying PPR proteins. Method: A framework of variable selection for identifying PPR proteins is proposed. Samples representing PPR positive proteins and negative ones are equally split into a training and a testing set. Variable importance is regarded as scores derived from an iteration of resampling, training, and scoring step on the training set. A model selection method based on Gaussian mixture model is applied to automatic choice of variables which are effective to identify PPR proteins. Measurements are used on the testing set to show the effectiveness of the selected variables. Results: Certain variables other than the multidimensional feature they belong to do work for discrimination between PPR positive proteins and those negative ones. In addition, the content of methionine may play an important role in predicting PPR proteins.
RESUMO
OBJECTIVE: To present our clinical experience of treating varus malunion of the distal femur through a medial open-wedge osteotomy with double-plate fixation. METHODS: A prospective cohort study was performed. From January 2005 to February 2015, 15 consecutive patients with varus malunion following distal femur fractures were surgically treated at a single level I trauma center. The coronal and sagittal deformity were corrected by a medial open-wedge osteotomy of the distal femur. A medial buttress plate was used to maintain the realignment. A lateral locking plate was additionally used as a protection plate. The mean age of patients at the time of the surgery was 35.5 years (range, 22-58 years). The radiographical evaluation included the mechanical femorotibial angle, the mechanical lateral distal femoral angle, the anatomic posterior distal femoral angle, and the leg length discrepancy. Clinical outcome evaluation consisted of the range of motion (ROM) and Hospital for Special Surgery (HSS) score. RESULTS: Mean follow-up was 7.4 years (range, 4-11.5 years). Varus and flexion malalignment and limb discrepancy were adequately corrected in all patients. The mechanical femorotibial angle, the mechanical lateral distal femoral angle, and the anatomic posterior distal femoral angle were restored from 17.5° (range, 13°-25°) to 2.3° (range, - 2°-7°), 102.3° (range, 95°-112°) to 85.2° (range, 81°-92°), and 77.1° (range, 65°-87°) to 82.7° (range, 76°-88°), respectively. The leg length discrepancy was diminished from 3.4 cm (range, 2.4-4.5 cm) to 0.8 cm (range, 0-1.7 cm). The average bone healing time was 4.1 months (range, 2.5-6 months). The average ROM of the affected knees at 24-month follow-up was 3.4°-112.55°. The score of HSS at 4-years follow-up was 76.1 (range, 64-88). No internal fixation failure or secondary operation was noted until the last follow-up. CONCLUSION: Medial open-wedge osteotomy can adequately correct the posttraumatic varus malunion of the distal femur. With fixation of the double plate, non-displaced bone healing and good functional outcome are expected.