SPRINT: side-chain prediction inference toolbox for multistate protein design.

UNLABELLED: SPRINT is a software package that performs computational multistate protein design using state-of-the-art inference on probabilistic graphical models. The input to SPRINT is a list of protein structures, the rotamers modeled for each structure and the pre-calculated rotamer energies. Probabilistic inference is performed using the belief propagation or A* algorithms, and dead-end elimination can be applied as pre-processing. The output can either be a list of amino acid sequences simultaneously compatible with these structures, or probabilistic amino acid profiles compatible with the structures. In addition, higher order (e.g. pairwise) amino acid probabilities can also be predicted. Finally, SPRINT also has a module for protein side-chain prediction and single-state design. AVAILABILITY: The full C++ source code for SPRINT can be freely downloaded from http://www.protonet.cs.huji.ac.il/sprint.

A novel algorithm to improve pathologic stage prediction of clinically organ-confined muscle-invasive bladder cancer.

BACKGROUND: An algorithm was created to predict pathologic stage in patients with clinically organ-confined muscle-invasive bladder cancer. METHODS: The sample consisted of 133 consecutive patients scheduled to undergo cystectomy. To develop a tool to predict nonorgan-confined disease before surgery, principal component analysis (PCA) was applied. Patients were stratified into a training set (n = 89) and a validation set (n = 44), and 7 parameters were evaluated: levels of carcinoembryonic antigen, cancer antigen (CA) 125, and carbohydrate antigen (CA) 19-9; clinical stage; presence of hydronephrosis; presence of carcinoma in situ; and initial tumor size >3 cm. PCA was applied to the training set to determine the weight of each parameter. A PCA score was generated for each patient in the set, and a cutoff defining nonorgan-confined disease was established. The accuracy of the cutoff was quantified by the area under the receiver operator characteristics curve (AUC). The model was then applied to the validation set without recalculation; the AUC and the positive and negative predictive values of the validation set were calculated. RESULTS: On pathologic evaluation, 71 patients (53%) were found to have organ-confined tumors and 62 patients (47%) had extravesical disease. The AUC was 0.85 in the training group (95% confidence interval [95% CI], 0.71-0.97) and 0.84 in the validation group (95% CI, 0.75-0.93). The positive and negative predictive values in the validation group were 88% (95% CI, 71%-96%) and 94% (95% CI, 71%-99%), respectively. CONCLUSIONS: The newly devised, internally validated, algorithm was 85% accurate in predicting nonorgan-confined bladder disease before cystectomy. Further external validation in a large cohort was recommended as still necessary.

Magnetization transfer based contrast for imaging denatured collagen.

PURPOSE: To study of the sensitivity of various NMR and MRI methods and parameters to the degree of thermal denaturation of collagen. MATERIALS AND METHODS: Collagen type I powder was washed with methanol:chloroform to remove traces of lipids and then suspended in saline. Denaturation was carried out by heating the suspension for 5-120 minutes at a temperature range of 50-100 degrees C. The NMR methods tested were two T(2) filter methods: Goldman-Shen (GS) and Edzes-Samulski (ES); magnetization transfer contrast (MTC); double quantum filtering (DQF) and high resolution spectroscopy. MRI contrasts based on these methods were compared. RESULTS: The following parameters were found to be sensitive to denaturation of collagen: 1) the amount of spins that experience high dipolar interactions as assessed by DQF; 2) MTR; 3) k(w)T(1w) (where k(w) is the magnetization transfer rate from water to collagen, and T(1w) is the water protons longitudinal relaxation time); and 4) aliphatic residues content. The contrast between native and denatured collagen was improved by all the tested methods, with ES and DQF producing the highest contrast. CONCLUSION: Methods depending on T(2) filtering and DQF were found to be sensitive to the degree of thermal denaturation of collagen and improve the contrast between native and denatured collagen.

EVEREST: automatic identification and classification of protein domains in all protein sequences.

BACKGROUND: Proteins are comprised of one or several building blocks, known as domains. Such domains can be classified into families according to their evolutionary origin. Whereas sequencing technologies have advanced immensely in recent years, there are no matching computational methodologies for large-scale determination of protein domains and their boundaries. We provide and rigorously evaluate a novel set of domain families that is automatically generated from sequence data. Our domain family identification process, called EVEREST (EVolutionary Ensembles of REcurrent SegmenTs), begins by constructing a library of protein segments that emerge in an all vs. all pairwise sequence comparison. It then proceeds to cluster these segments into putative domain families. The selection of the best putative families is done using machine learning techniques. A statistical model is then created for each of the chosen families. This procedure is then iterated: the aforementioned statistical models are used to scan all protein sequences, to recreate a library of segments and to cluster them again. RESULTS: Processing the Swiss-Prot section of the UniProt Knoledgebase, release 7.2, EVEREST defines 20,230 domains, covering 85% of the amino acids of the Swiss-Prot database. EVEREST annotates 11,852 proteins (6% of the database) that are not annotated by Pfam A. In addition, in 43,086 proteins (20% of the database), EVEREST annotates a part of the protein that is not annotated by Pfam A. Performance tests show that EVEREST recovers 56% of Pfam A families and 63% of SCOP families with high accuracy, and suggests previously unknown domain families with at least 51% fidelity. EVEREST domains are often a combination of domains as defined by Pfam or SCOP and are frequently sub-domains of such domains. CONCLUSION: The EVEREST process and its output domain families provide an exhaustive and validated view of the protein domain world that is automatically generated from sequence data. The EVEREST library of domain families, accessible for browsing and download at 1, provides a complementary view to that provided by other existing libraries. Furthermore, since it is automatic, the EVEREST process is scalable and we will run it in the future on larger databases as well. The EVEREST source files are available for download from the EVEREST web site.