Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Predictive”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 433 records · Page 24Linked to original sources
PubMed2003

Comparison of intravenous myocardial contrast echocardiography and low-dose dobutamine echocardiography for predicting left ventricular functional recovery following acute myocardial infarction.

Akinesia after acute myocardial infarction (AMI) may be reversible or irreversible. Distinguishing these 2 entities early after AMI is difficult, but clinically important. Previous studies have shown that myocardial contrast echocardiography (MCE) and low-dose dobutamine echocardiography (DE) may both be useful in this setting. However, there are few data regarding the relative and combined value of these techniques. The aim of this study was to compare the utility of real-time intravenous MCE and low-dose DE in the early prediction of functional recovery of akinetic myocardium after AMI. Thirty-seven patients were studied 3 +/- 2 days after an AMI. Each subject underwent real-time MCE using an intravenous infusion of perflutren microbubbles. Immediately after this, low-dose DE was performed. Contrast opacification and wall motion were determined by experienced observers blinded to clinical data. Repeat echocardiograms were obtained 51 +/- 19 days later and wall motion at rest was scored by an observer blinded to clinical data. Normal contrast opacification predicted functional recovery with a positive predictive value of 63%, a negative predictive value of 73%, and an accuracy of 66%. Residual contractility during low-dose DE had a positive predictive value of 82%, a negative predictive value of 72%, and a predictive accuracy of 76%. When the 2 tests were concordant (64%), they had a positive predictive value of 81%, a negative predictive value of 85%, and a predictive accuracy of 83%. Low-dose DE was superior to intravenous MCE in the prediction of functional recovery of akinetic myocardium after AMI, but the combination of both maximizes predictive accuracy.

Aged↗
PubMed1999

Performance and potential impact of a chest pain prediction rule in a large public hospital.

PURPOSE: To evaluate the performance of a previously validated prediction rule for patients presenting to the emergency department with chest pain and the potential impact of the rule on triage decisions. SUBJECTS AND METHODS: In a prospective cohort study, physician investigators interviewed consecutive patients admitted for suspected acute ischemic heart disease (n = 207) by emergency department attending physicians who had not used the prediction rule. We measured the accuracy of the rule in predicting cardiac complications in these patients, and compared actual triage decisions with those that might have been recommended by use of the prediction rule. We also measured comorbid illnesses among patients stratified as very low risk by the prediction rule, as well as the effect of standardizing the definition of unstable angina and interpretation of electrocardiograms (ECG) on the rule's sensitivity and specificity. RESULTS: Overall, the rate of major cardiac complications (4.3%) was similar to that reported in the original study (3.6%). The prediction rule performed well in predicting these complications in our patients (area under receiver operating characteristic curve 0.84 versus 0.80 in the original study; difference 0.04, 95% confidence interval [CI] -0.07, 0.14). Standardized definitions of unstable angina and interpretation of ECGs improved the specificity of the prediction rule in predicting complications (55% versus 47%; difference 8%, 95% CI 1.5%, 13.7%). The prediction rule recommended admission to telemetry units in 65 fewer patients than actually occurred (31% of the entire cohort). None of these patients had major complications. A substantial minority of "very low risk" patients (27%) had comorbid illnesses requiring inpatient treatment. CONCLUSIONS: This independent validation of the prediction rule suggests that it can improve triage decisions for patients admitted with suspected acute ischemic heart disease. Additional studies are needed to test prospectively the performance of the prediction rule in actual decision making, its acceptance by clinicians, and its cost effectiveness.

Adult↗
PubMed2004

Prediction of protein-protein interaction sites using support vector machines.

The identification of protein-protein interaction sites is essential for the mutant design and prediction of protein-protein networks. The interaction sites of residue units were predicted using support vector machines (SVM) and the profiles of sequentially/spatially neighboring residues, plus additional information. When only sequence information was used, prediction performance was highest using the feature vectors, sequentially neighboring profiles and predicted interaction site ratios, which were calculated by SVM regression using amino acid compositions. When structural information was also used, prediction performance was highest using the feature vectors, spatially neighboring residue profiles, accessible surface areas, and the with/without protein interaction sites ratios predicted by SVM regression and amino acid compositions. In the latter case, the precision at recall = 50% was 54-56% for a homo-hetero mixed test set and >20% higher than for random prediction. Approximately 30% of the residues wrongly predicted as interaction sites were the closest sequentially/spatially neighboring on the interaction site residues. The predicted residues covered 86-87% of the actual interfaces (96-97% of interfaces with over 20 residues). This prediction performance appeared to be slightly higher than a previously reported study. Comparing the prediction accuracy of each molecule, it seems to be easier to predict interaction sites for stable complexes.

Algorithms↗
PubMed2002

Is there a long-term predictive value of intraoperative low-dose dobutamine echocardiography in patients who have coronary artery bypass graft surgery with cardiopulmonary bypass?

UNLABELLED: In patients with coronary artery disease, chronic regional left ventricular systolic dysfunction at rest may be caused by hibernating or by infarcted myocardium. Intraoperative low-dose dobutamine (LDD) echocardiography reliably predicts the immediate recovery of regional myocardial function after coronary artery bypass graft (CABG) surgery. We sought to determine whether intraoperative LDD echocardiography would also predict recovery of regional function after 1 yr. Twenty-five patients with coronary artery disease who underwent CABG surgery with intraoperative LDD echocardiography were evaluated 1 yr later with a follow-up transthoracic echocardiogram. The covariates of left ventricular ejection fraction, old myocardial infarction, and diabetes mellitus were considered in an analysis of regional wall motion (RWM). A 16-segment model and a 1-5-point scoring system were used to evaluate 350 myocardial segments. Multiple logistic regression analysis was performed to determine whether response to intraoperative LDD echocardiography (5 microg. kg(-1). min(-1)) predicted changes in regional function at 1 yr. A segment was defined as stunned if the RWM score obtained during LDD infusion deteriorated after cardiopulmonary bypass but recovered in the 1-yr follow-up echocardiogram. A response to intraoperative LDD predicted changes in regional function at 1 yr. The overall odds of improvement in regional function were 2.22 times greater (95% confidence interval = 1.29, 3.82; P = 0.0039) with a positive response to intraoperative LDD. The positive predictive value of intraoperative LDD echocardiography for improvement in myocardial function was 0.81 and the negative predictive value was 0.34. The predictive values did not vary with the examined covariates. Of segments with unexpected deterioration of RWM immediately after cardiopulmonary bypass, 87% recovered at the time of the 1-yr follow-up echocardiogram. Contractile reserve demonstrated by intraoperative LDD echocardiography predicts regional function at 1 yr; however, the test cannot predict which segment will not recover. Most of unexpected regional ventricular systolic dysfunction immediately after CABG surgery can be attributed to myocardial stunning. IMPLICATIONS: In patients undergoing coronary artery bypass graft surgery, intraoperative low-dose dobutamine echocardiography has only limited value for the prediction of regional myocardial function at 1 yr. Small-dose dobutamine echocardiography predicts regional myocardial function at 1 yr when baseline regional wall motion abnormalities improve with dobutamine; however, the test cannot be used to predict which segment will not recover at 1 yr.

Adrenergic beta-Agonists↗
PubMed1998

The end of the Injury Severity Score (ISS) and the Trauma and Injury Severity Score (TRISS): ICISS, an International Classification of Diseases, ninth revision-based prediction tool, outperforms both ISS and TRISS as predictors of trauma patient survival, hospital charges, and hospital length of stay.

INTRODUCTION: Since their inception, the Injury Severity Score (ISS) and the Trauma and Injury Severity Score (TRISS) have been suggested as measures of the quality of trauma care. In concept, they are designed to accurately assess injury severity and predict expected outcomes. ICISS, an injury severity methodology based on International Classification of Diseases, Ninth Revision, codes, has been demonstrated to be superior to ISS and TRISS. The purpose of the present study was to compare the ability of TRISS to ICISS as predictors of survival and other outcomes of injury (hospital length of stay and hospital charges). It was our hypothesis that ICISS would outperform ISS and TRISS in each of these outcome predictions. METHODS: "Training" data for creation of ICISS predictions were obtained from a state hospital discharge data base. "Test" data were obtained from a state trauma registry. ISS, TRISS, and ICISS were compared as predictors of patient survival. They were also compared as indicators of resource utilization by assessing their ability to predict patient hospital length of stay and hospital charges. Finally, a neural network was trained on the ICISS values and applied to the test data set in an effort to further improve predictive power. The techniques were compared by comparing each patient's outcome as predicted by the model to the actual outcome. RESULTS: Seven thousand seven hundred five patients had complete data available for analysis. The ICISS was far more likely than ISS or TRISS to accurately predict every measure of outcome of injured patients tested, and the neural network further improved predictive power. CONCLUSION: In addition to predicting mortality, quality tools that can accurately predict resource utilization are necessary for effective trauma center quality-improvement programs. ICISS-derived predictions of survival, hospital charges, and hospital length of stay consistently outperformed those of ISS and TRISS. The neural network-augmented ICISS was even better. This and previous studies demonstrate that TRISS is a limited technique in predicting survival resource utilization. Because of the limitations of TRISS, it should be superseded by ICISS.

Adult↗
PubMed2000

Prediction of peak oxygen uptake in men using pulmonary and hemodynamic variables during exercise.

PURPOSE: Many attempts have been made to predict peak VO2 from data obtained at rest or submaximal exercise. Predictive submaximal tests using the heart rate (HR) response have limited accuracy. Some tests incorporate submaximal gas exchange data, but a predictive test without gas exchange measurements would be of benefit. Addition of stroke volume and pulmonary function (PF) measurements might increase the predictability of a submaximal exercise test. METHODS: In this study, an incremental exercise test (10 W x min(-1)) was performed in 30 healthy men of various habitual activity levels. Step-wise multiple regression analysis was used to isolate the most important predictor variables of peak VO2 from a set of measurements of PF: lung volumes, diffusion capacity, airway resistance, and maximum inspiratory and expiratory pressures; gas exchange; minute ventilation (V(E)), tidal volume (V(T)), respiratory exchange ratio (RER = carbon dioxide output divided by VO2); and hemodynamics (HR, stroke index (SI) = stroke volume/body surface area, and mean arterial pressure). These measurements were made at rest and during submaximal exercise. RESULTS: Using the set of PF variables (expressed as percentages of predicted), FEV1 explained 30% of the variance of peak VO2. No other PF variables were predictive. After addition of resting hemodynamic data, SI was included in the prediction equation, raising the predictability to 40%. At the 60-W exercise level, 48% of the variance in peak VO2 could be explained by SI and FEV1. At 150 W, the prediction increased to 81%. At this level VCO2/O2 (RER) also entered the prediction equation of peak VO2: 6.44 x FEV1(%) + 13.0 x SI - 1921 x RER + 2380 (SE = 142 mL x min(-1) x m(-2), P < 0.0001). Leaving out the gas exchange variable RER, maximally 64% of the variance in peak VO2 could be explained. CONCLUSION: In conclusion, inclusion of pulmonary function and hemodynamic measurements could improve the prediction accuracy of a submaximal exercise test. The submaximal exercise test should be performed until a level of 150 W is reached. Noninvasive stroke volume measurements by means of EIC have additional value to measurement of HR alone. Finally, measurement of gas exchange significantly improves the predictability of peak VO2.

Adult↗
PubMed1998

Cyclosporine monitoring in patients with renal transplants: two- or three-point methods that estimate area under the curve are superior to trough levels in predicting drug exposure.

The recent introduction of a cyclosporine microemulsion demonstrating less pharmacokinetic variability than the conventional formulation offers the potential for accurately and precisely predicting area under the curve (AUC) with a limited-sampling monitoring strategy. This was studied based on the pharmacokinetic profiles from 55 stable patients with renal transplants who were observed on two occasions at steady state on both formulations. Multiple linear regression analyses were performed on a training dataset from 27 patients, in which combinations of cyclosporine concentrations drawn from 0 to 4 hours postdose were regressed against the full AUC over the dosing interval. Predictor regression equations used concentration combinations ranging from one-point (concentrations at 0, 1, 2, 3, or 4 hours) through five-points (all five concentrations 0 to 4 hours). The predictive performance of these equations was then assessed in the training group with data from a subsequent profiling occasion and in the remaining 28 patients who constituted an independent test group. Prediction bias (mean prediction error) and prediction precision (absolute prediction error) were quantified and compared between formulations. Correlations between predicted and actual AUC were consistently stronger for the microemulsion, suggesting the possibility of more accurate and precise predictions of exposure than from the conventional formulation. For both formulations, the one-point predictors rendered the lowest prediction precision, and predictive performance improved considerably when multiple-point predictors were used. Significantly higher precision and lower variability were observed with the microemulsion for most predictors in the both training and test groups. For the microemulsion, two-point (C0 + C1 or C0 + C2) and three-point (C0 + C1 + C2) predictors yielded relatively unbiased and precise exposure predictions, inasmuch as mean absolute prediction error was less than 10% and 5%, respectively. Hence, a two- or three-point method may provide a clinically important improvement over the use of trough levels in monitoring cyclosporine therapy in patients with renal transplants.

Area Under Curve↗
PubMedDate not supplied

Searching for clinical prediction rules in MEDLINE.

OBJECTIVES: Clinical prediction rules have been advocated as a possible mechanism to enhance clinical judgment in diagnostic, therapeutic, and prognostic assessment. Despite renewed interest in the their use, inconsistent terminology makes them difficult to index and retrieve by computerized search systems. No validated approaches to locating clinical prediction rules appear in the literature. The objective of this study was to derive and validate an optimal search filter for retrieving clinical prediction rules, using the National Library of Medicine's MEDLINE database. DESIGN: A comparative, retrospective analysis was conducted. The "gold standard" was established by a manual search of all articles from select print journals for the years 1991 through 1998, which identified articles covering various aspects of clinical prediction rules such as derivation, validation, and evaluation. Search filters were derived, from the articles in the July through December issues of the journals (derivation set), by analyzing the textwords (words in the title and abstract) and the medical subject heading (from the MeSH Thesaurus) used to index each article. The accuracy of these filters in retrieving clinical prediction rules was then assessed using articles in the January through June issues (validation set). MEASUREMENTS: The sensitivity, specificity, positive predictive value, and positive likelihood ratio of several different search filters were measured. RESULTS: The filter "predict$ OR clinical$ OR outcome$ OR risk$" retrieved 98 percent of clinical prediction rules. Four filters, such as "predict$ OR validat$ OR rule$ OR predictive value of tests," had both sensitivity and specificity above 90 percent. The top-performing filter for positive predictive value and positive likelihood ratio in the validation set was "predict$.ti. AND rule$." CONCLUSIONS: Several filters with high retrieval value were found. Depending on the goals and time constraints of the searcher, one of these filters could be used.

Decision Support Techniques↗
PubMed2006

Prediction of cis/trans isomerization in proteins using PSI-BLAST profiles and secondary structure information.

BACKGROUND: The majority of peptide bonds in proteins are found to occur in the trans conformation. However, for proline residues, a considerable fraction of Prolyl peptide bonds adopt the cis form. Proline cis/trans isomerization is known to play a critical role in protein folding, splicing, cell signaling and transmembrane active transport. Accurate prediction of proline cis/trans isomerization in proteins would have many important applications towards the understanding of protein structure and function. RESULTS: In this paper, we propose a new approach to predict the proline cis/trans isomerization in proteins using support vector machine (SVM). The preliminary results indicated that using Radial Basis Function (RBF) kernels could lead to better prediction performance than that of polynomial and linear kernel functions. We used single sequence information of different local window sizes, amino acid compositions of different local sequences, multiple sequence alignment obtained from PSI-BLAST and the secondary structure information predicted by PSIPRED. We explored these different sequence encoding schemes in order to investigate their effects on the prediction performance. The training and testing of this approach was performed on a newly enlarged dataset of 2424 non-homologous proteins determined by X-Ray diffraction method using 5-fold cross-validation. Selecting the window size 11 provided the best performance for determining the proline cis/trans isomerization based on the single amino acid sequence. It was found that using multiple sequence alignments in the form of PSI-BLAST profiles could significantly improve the prediction performance, the prediction accuracy increased from 62.8% with single sequence to 69.8% and Matthews Correlation Coefficient (MCC) improved from 0.26 with single local sequence to 0.40. Furthermore, if coupled with the predicted secondary structure information by PSIPRED, our method yielded a prediction accuracy of 71.5% and MCC of 0.43, 9% and 0.17 higher than the accuracy achieved based on the singe sequence information, respectively. CONCLUSION: A new method has been developed to predict the proline cis/trans isomerization in proteins based on support vector machine, which used the single amino acid sequence with different local window sizes, the amino acid compositions of local sequence flanking centered proline residues, the position-specific scoring matrices (PSSMs) extracted by PSI-BLAST and the predicted secondary structures generated by PSIPRED. The successful application of SVM approach in this study reinforced that SVM is a powerful tool in predicting proline cis/trans isomerization in proteins and biological sequence analysis.

Databases, Protein↗
PubMed2025

Impact of personalised risk predictions on breast cancer risk perceptions: insights from the BREATHE study.

OBJECTIVE: Biennial mammography screening is well-established for women aged 50 and above, but guidelines for younger women are less clear. Risk-based screening may provide women with key information to make informed decisions about their breast cancer risk and screening. This study examines how predicted breast cancer (BC) risk shapes women's perception and confidence in risk prediction. METHODS: Women aged 35 to 59&#xa0;years were recruited for a prospective multi-centre cohort and stratified into above-average, average, or below-average BC risk categories based on genetic and non-genetic risk factors. Perceived risk was assessed at enrolment and after participants were informed of their predicted risk. We used ordinal models to identify predictors of perceived risk and logistic regression to examine the relationship between changes in perceived risk and confidence in the risk prediction. RESULTS: At enrolment, 43% and 47% of 4112 participants perceived their BC risk pre-result as low or average, respectively. Thirty-five percent adjusted their perceived risk to align more closely with their predicted risk. Predictors of perceived risk post-result: perceived risk pre-result, predicted risk, ethnicity and having regular menstruation. Participants who underestimated their BC risk were nearly eight times more likely to have low confidence in the accuracy of their predicted risk (OR for underestimation vs. accurate perception: 7.94 [95% CI 5.60-11.28]). Predictors of perceived risk post-result: perceived risk pre-result, predicted risk, ethnicity and having regular menstruation. Confidence in risk prediction was lowest when women's perceived risk pre-result was lower than their predicted risk (OR-2 vs 0 [95%CI] 5.06 [3.67 to 6.97]). CONCLUSION: Many women underestimated their BC risk, and their initial perceptions were influenced by the knowledge of their predicted risk. Women who underestimated their risk had less confidence in their predicted risk scores.

Humans↗
PubMedDate not supplied

Open-access appointment scheduling in family practice: comparison of a demand prediction grid with actual appointments.

BACKGROUND: Inadequate access to their primary care physician remains a major reason for patient dissatisfaction in ambulatory care. The concept of open-access appointment scheduling has been found to accommodate patients' urgent health care needs while providing continuous, routine care. We describe the development of a demand prediction grid for future appointments, compare it with one developed by Kaiser Permanente, and compare the predictions with actual appointments made and held in our clinic. METHODS: Using adjusted 1999 appointments based on historical data for the Scott & White Killeen Clinic (> 75,000 annual appointments; 13 family physicians), we computed appointment predictions for calendar year 2000 by day of the week and by month of the year. We then compared our predictions with those of Kaiser and actual appointments for the first half of 2000. RESULTS: Our data and the Kaiser data agreed on the day of week, but they were different for the summer and winter months. Overall, actual appointments made and held at our clinic for January through June 2000 were within 6% of the predictions. Appointments for January and February were 18% and 4% more than the predictions, respectively, while appointments for March were 3% less than the predictions. Appointments for April through June were 3% to 7% more than the predictions. Few daily variations were observed between actual appointments and predictions. CONCLUSIONS: We conclude that the Kaiser data might be tempered by a different climate, underscoring the need for each practice to develop its own demand prediction grid. That our actual appointments were 6% more than predicted overall but fluctuated month by month reemphasizes the need for continuous monitoring of the adjustment factor for prediction.

Appointments and Schedules↗
PubMed2002

Can we predict prognosis using mortality probability model IIo?

OBJECTIVE: To evaluate Mortality Probability Model (MPM) IIo as a tool to predict very poor prognosis after intensive care unit admission. METHODS: The study was conducted as a prospective observational study in a medical-surgical intensive care unit in a tertiary care teaching hospital, Riyadh, Kingdom of Saudi Arabia. Data necessary to calculate MPM IIo predicted mortality was collected from March 1999 through to February 2000 on all intensive care unit admissions. The hospital outcome was documented. We calculated the sensitivity, specificity, positive predictive value and negative predictive value of MPM IIo using cutoff points of 90% and 95%. RESULTS: Data was complete on 557/569 patients (98%). Thirty-one patients had predicted mortality of >95% and all died yielding a specificity of 100% and positive predictive value of 100%. However, sensitivity was only 18% and negative predictive value 73%. Forty-four patients had predicted mortality of >90% of whom only one survived yielding a specificity of 99.7% and a positive predictive value of 97.7%. Sensitivity was only 25% and negative predictive value of 75%. CONCLUSIONS: Using a decision-cutoff of 95% predicted mortality using MPMI IIo had a very high specificity in predicting death after intensive care unit admission, although with a low sensitivity. This information can be used to support clinical judgment regarding the very ill patients who are unlikely to benefit from intensive care unit admission.

Adult↗
PubMed1996

Topology prediction for helical transmembrane proteins at 86% accuracy.

Previously, we introduced a neural network system predicting locations of transmembrane helices (HTMs) based on evolutionary profiles (PHDhtm, Rost B, Casadio R, Fariselli P, Sander C, 1995, Protein Sci 4:521-533). Here, we describe an improvement and an extension of that system. The improvement is achieved by a dynamic programming-like algorithm that optimizes helices compatible with the neural network output. The extension is the prediction of topology (orientation of first loop region with respect to membrane) by applying to the refined prediction the observation that positively charged residues are more abundant in extra-cytoplasmic regions. Furthermore, we introduce a method to reduce the number of false positives, i.e., proteins falsely predicted with membrane helices. The evaluation of prediction accuracy is based on a cross-validation and a double-blind test set (in total 131 proteins). The final method appears to be more accurate than other methods published: (1) For almost 89% (+/-3%) of the test proteins, all HTMs are predicted correctly. (2) For more than 86% (+/-3%) of the proteins, topology is predicted correctly. (3) We define reliability indices that correlate with prediction accuracy: for one half of the proteins, segment accuracy raises to 98%; and for two-thirds, accuracy of topology prediction is 95%. (4) The rate of proteins for which HTMs are predicted falsely is below 2% (+/-1%). Finally, the method is applied to 1,616 sequences of Haemophilus influenzae. We predict 19% of the genome sequences to contain one or more HTMs. This appears to be lower than what we predicted previously for the yeast VIII chromosome (about 25%).

Algorithms↗
PubMed1996

Identification and application of the concepts important for accurate and reliable protein secondary structure prediction.

A protein secondary structure prediction method from multiply aligned homologous sequences is presented with an overall per residue three-state accuracy of 70.1%. There are two aims: to obtain high accuracy by identification of a set of concepts important for prediction followed by use of linear statistics; and to provide insight into the folding process. The important concepts in secondary structure prediction are identified as: residue conformational propensities, sequence edge effects, moments of hydrophobicity, position of insertions and deletions in aligned homologous sequence, moments of conservation, auto-correlation, residue ratios, secondary structure feedback effects, and filtering. Explicit use of edge effects, moments of conservation, and auto-correlation are new to this paper. The relative importance of the concepts used in prediction was analyzed by stepwise addition of information and examination of weights in the discrimination function. The simple and explicit structure of the prediction allows the method to be reimplemented easily. The accuracy of a prediction is predictable a priori. This permits evaluation of the utility of the prediction: 10% of the chains predicted were identified correctly as having a mean accuracy of > 80%. Existing high-accuracy prediction methods are "black-box" predictors based on complex nonlinear statistics (e.g., neural networks in PHD: Rost & Sander, 1993a). For medium- to short-length chains (> or = 90 residues and < 170 residues), the prediction method is significantly more accurate (P < 0.01) than the PHD algorithm (probably the most commonly used algorithm). In combination with the PHD, an algorithm is formed that is significantly more accurate than either method, with an estimated overall three-state accuracy of 72.4%, the highest accuracy reported for any prediction method.

Amino Acid Sequence↗
PubMed2003

Predictions without templates: new folds, secondary structure, and contacts in CASP5.

We present the assessment of CASP5 predictions in the new fold category. For coordinate predictions, we considered five targets with new folds and eight lying on the fold recognition borderline. We performed detailed visual and numerical comparisons between predicted and experimental structures to assess prediction accuracy. The two procedures largely agreed, but the visual inspection identified instances where metrics, such as GDT_TS, ranked what we considered incorrect predictions highly. We found the quality of the best predictions to be very good: for nearly every target at least one group predicted a structure close to the correct one. However, selection of the best of five models is still problematic. The group of David Baker once again proved to be best overall, with many individual highlights. However, high quality and consistency were also seen from others, suggesting that the community is moving toward general procedures to predict accurate structures for proteins showing no resemblance to anything seen before. Predictions for secondary structure showed at best limited progress since CASP4. The number of targets is probably too small to spot differences in performance between methods, suggesting that such predictions might be better evaluated with schemes involving more proteins. For contact predictions, accuracies are still low, although there were several instances of accurate and useful contacts predicted de novo, and new approaches hint at future progress.

Algorithms↗
PubMed2006

SimFold energy function for de novo protein structure prediction: consensus with Rosetta.

Predicting protein tertiary structures by in silico folding is still very difficult for proteins that have new folds. Here, we developed a coarse-grained energy function, SimFold, for de novo structure prediction, performed a benchmark test of prediction with fragment assembly simulations for 38 test proteins, and proposed consensus prediction with Rosetta. The SimFold energy consists of many terms that take into account solvent-induced effects on the basis of physicochemical consideration. In the benchmark test, SimFold succeeded in predicting native structures within 6.5 A for 12 of 38 proteins; this success rate was the same as that by the publicly available version of Rosetta (ab initio version 1.2) run with default parameters. We investigated which energy terms in SimFold contribute to structure prediction performance, finding that the hydrophobic interaction is the most crucial for the prediction, whereas other sequence-specific terms have weak but positive roles. In the benchmark, well-predicted proteins by SimFold and by Rosetta were not the same for 5 of 12 proteins, which led us to introduce consensus prediction. With combined decoys, we succeeded in prediction for 16 proteins, four more than SimFold or Rosetta separately. For each of 38 proteins, structural ensembles generated by SimFold and by Rosetta were qualitatively compared by mapping sampled structural space onto two dimensions. For proteins of which one of the two methods succeeded and the other failed in prediction, the former had a less scattered ensemble located around the native. For proteins of which both methods succeeded in prediction, often two ensembles were mixed up.

Alanine↗
PubMed1994

Conservation and prediction of solvent accessibility in protein families.

Currently, the prediction of three-dimensional (3D) protein structure from sequence alone is an exceedingly difficult task. As an intermediate step, a much simpler task has been pursued extensively: predicting 1D strings of secondary structure. Here, we present an analysis of another 1D projection from 3D structure: the relative solvent accessibility of each residue. We show that solvent accessibility is less conserved in 3D homologues than is secondary structure, and hence is predicted less accurately from automatic homology modeling; the correlation coefficient of relative solvent accessibility between 3D homologues is only 0.77, and the average accuracy of predictions based on sequence alignments is only 0.68. The latter number provides an effective upper limit on the accuracy of predicting accessibility from sequence when homology modeling is not possible. We introduce a neural network system that predicts relative solvent accessibility (projected onto ten discrete states) using evolutionary profiles of amino acid substitutions derived from multiple sequence alignments. Evaluated in a cross-validation test on 238 unique proteins, the correlation between predicted and observed relative accessibility is 0.54. Interpreted in terms of a three-state (buried, intermediate, exposed) description of relative accessibility, the fraction of correctly predicted residue states is about 58%. In absolute terms this accuracy appears poor, but given the relatively low conservation of accessibility in 3D families, the network system is not far from its likely optimal performance. The most reliably predicted fraction of the residues (50%) is predicted as accurately as by automatic homology modeling. Prediction is best for buried residues, e.g., 86% of the completely buried sites are correctly predicted as having 0% relative accessibility.

Biological Evolution↗
PubMed1992

Prediction of nuclear maturity from cumulus-coronal morphology: influence of embryologist experience.

PURPOSE: A majority of in vitro fertilization (IVF) programs continues to evaluate oocyte maturity on the basis of cumulus-coronal morphology (CCM) even though marked asynchrony has been reported between CCM and nuclear maturity. This study was designed to examine changes in embryologists' ability to correctly predict nuclear maturity from CCM as a function of increasing experience. Nuclear maturity was assessed by inverted microscopy with a modified spreading technique at follicular aspiration. A second objective was to determine the percentage of oocytes which displayed asynchrony between CCM and nuclear maturity as assessed by embryologists with extensive experience in oocyte maturity evaluation. RESULTS: The three participating embryologists had directly evaluated 1304, 75, and 0 oocytes for nuclear maturity and CCM at study initiation and correctly predicted nuclear maturity from CCM in 74, 64, and 47% of oocytes, respectively. Embryologist 1 did not significantly change in predictive ability during the 17-month study period. Embryologist 2 significantly improved in predictive ability during the first 9 months of the study (841 oocytes evaluated) and plateaued thereafter, at a similar percentage of correct predictions as embryologist 1. Embryologist 3 continued to improve in predictive ability throughout the study period, reaching 61% correct predictions at the close of the study after evaluating 223 oocytes. Once embryologists had plateaued in their predictive ability, 72% of oocytes evaluated received the correct nuclear maturity classification based on CCM. Significantly fewer oocytes (54%; 375/690) evaluated by embryologists who had not plateaued in their predictive ability received the correct nuclear maturity classification based on CCM. CONCLUSIONS: These results indicate that embryologists' ability to predict oocyte nuclear maturity correctly from CCM continues to change over several months even when pretraining video recordings are used before beginning direct evaluations. After embryologists plateaued in their predictive ability, nuclear maturity still could not be correctly predicted from CCM in 28% of oocytes due to asynchrony between nuclear and CCM maturity. Based upon this, circumstances in which the spreading technique should be used for direct assessment of nuclear maturity as opposed to assessment of CCM only are discussed.

Cell Differentiation↗