RAPID: fast and accurate sequence-based prediction of intrinsic disorder content on proteomic scale.

Recent research in the protein intrinsic disorder was stimulated by the availability of accurate computational predictors. However, most of these methods are relatively slow, especially considering proteome-scale applications, and were shown to produce relatively large errors when estimating disorder at the protein- (in contrast to residue-) level, which is defined by the fraction/content of disordered residues. To this end, we propose a novel support vector Regression-based Accurate Predictor of Intrinsic Disorder (RAPID). Key advantages of RAPID are speed (prediction of an average-size eukaryotic proteome takes <1h on a modern desktop computer); sophisticated design (multiple, complementary information sources that are aggregated over an input chain are combined using feature selection); and high-quality and robust predictive performance. Empirical tests on two diverse benchmark datasets reveal that RAPID's predictive performance compares favorably to a comprehensive set of state-of-the-art disorder and disorder content predictors. Drawing on high speed and good predictive quality, RAPID was used to perform large-scale characterization of disorder in 200+ fully sequenced eukaryotic proteomes. Our analysis reveals interesting relations of disorder with structural coverage and chain length, and unusual distribution of fully disordered chains. We also performed a comprehensive (using 56000+ annotated chains, which doubles the scope of previous studies) investigation of cellular functions and localizations that are enriched in the disorder in the human proteome. RAPID, which allows for batch (proteome-wide) predictions, is available as a web server at http://biomine.ece.ualberta.ca/RAPID/.

Anterior chest wall inflammation by whole-body magnetic resonance imaging in patients with spondyloarthritis: lack of association between clinical and imaging findings in a cross-sectional study.

INTRODUCTION: Inflammatory involvement of the anterior chest wall (ACW) affects the quality of life of patients with spondyloarthritis (SpA), although involvement of the ACW is often neglected on clinical and imaging evaluation. Whole-body (WB) MRI is an imaging method used to assess the ACW in addition to the sacroiliac joints and spine without inconvenience for patients. Our goals in this study were to describe the distribution of ACW inflammation by WB MRI in both early and established SpA and associations between clinical and imaging findings indicative of inflammation. METHODS: The ACWs of 122 consecutive SpA patients (95 with ankylosing spondylitis (AS) and 27 with nonradiographic SpA (nrSpA)) and 75 healthy controls were scanned by sagittal and coronal WB MRI. The MRI scans were scored independently in random order by seven readers blinded to patient identifiers. Active and structural inflammatory lesions of the ACW were recorded on a web-based data entry form. ACW pain by patient self-report, ACW tenderness on physical examination according to the Maastricht Ankylosing Spondylitis Enthesitis Score (MASES) and lesions detected by MRI were analyzed descriptively. κ statistics served to assess the agreement between clinical and imaging findings. RESULTS: ACW pain or tenderness was present in 26% of patients, with little difference between AS and nrSpA patients. Bone marrow edema (BME), erosion and fat infiltration were recorded in 44.3%, 34.4% and 27.0% of SpA patients and in 9.3%, 12.0% and 5.3% of controls, respectively. Lesions found by MRI occurred more frequently in AS patients (BME, erosion and fat infiltration in 49.5%, 36.8% and 33.7%, respectively) than in nrSpA patients (25.9%, 25.9% and 3.7%, respectively). The joint most frequently affected by lesions found on MRI scans was the manubriosternal joint. The κ values between clinical assessments and MRI inflammation ranged from -0.10 to only 0.33 for both AS and nrSpA patients. CONCLUSIONS: Among SpA patients, 26% had clinical involvement of the ACW. WB MRI signs of ACW inflammation were found in a substantial proportion of patients with AS (49.5%) and nrSpA (25.9%). There was no association between clinical assessments of ACW, including the MASES, and MRI features.