POOL server: machine learning application for functional site prediction in proteins.
Ontology highlight
ABSTRACT: Summary
We present an automated web server for partial order optimum likelihood (POOL), a machine learning application that combines computed electrostatic and geometric information for high-performance prediction of catalytic residues from 3D structures. Input features consist of THEMATICS electrostatics data and pocket information from ConCavity. THEMATICS measures deviation from typical, sigmoidal titration behavior to identify functionally important residues and ConCavity identifies binding pockets by analyzing the surface geometry of protein structures. Both THEMATICS and ConCavity (structure only) do not require the query protein to have any sequence or structure similarity to other proteins. Hence, POOL is applicable to proteins with novel folds and engineered proteins. As an additional option for cases where sequence homologues are available, users can include evolutionary information from INTREPID for enhanced accuracy in site prediction.Availability
The web site is free and open to all users with no login requirements at http://www.pool.neu.edu.Contact
m.ondrechen@neu.eduSupplementary information
Supplementary data are available at Bioinformatics online.
SUBMITTER: Somarowthu S
PROVIDER: S-EPMC3400966 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Gene expression profiles were generated from 199 primary breast cancer patients. Samples 1-176 were used in another study, GEO Series GSE22820, and form the training data set in this study. Sample numbers 200-222 form a validation set. This data is used to model a machine learning classifier for Estrogen Receptor Status. RNA was isolated from 199 primary breast cancer patients. A machine learning classifier was built to predict ER status using only three gene features.
2013-01-01 | E-GEOD-29210 | biostudies-arrayexpress
Project description:Knowledge of protein function is important for biological, medical and therapeutic studies, but many proteins are still unknown in function. There is a need for more improved functional prediction methods. Our SVM-Prot web-server employed a machine learning method for predicting protein functional families from protein sequences irrespective of similarity, which complemented those similarity-based and other methods in predicting diverse classes of proteins including the distantly-related proteins and homologous proteins of different functions. Since its publication in 2003, we made major improvements to SVM-Prot with (1) expanded coverage from 54 to 192 functional families, (2) more diverse protein descriptors protein representation, (3) improved predictive performances due to the use of more enriched training datasets and more variety of protein descriptors, (4) newly integrated BLAST analysis option for assessing proteins in the SVM-Prot predicted functional families that were similar in sequence to a query protein, and (5) newly added batch submission option for supporting the classification of multiple proteins. Moreover, 2 more machine learning approaches, K nearest neighbor and probabilistic neural networks, were added for facilitating collective assessment of protein functions by multiple methods. SVM-Prot can be accessed at http://bidd2.nus.edu.sg/cgi-bin/svmprot/svmprot.cgi.
| S-EPMC4985167 | biostudies-literature
Project description:Neoantigens are derived from somatic mutations in the tumors but are absent in normal tissues. Emerging evidence suggests that neoantigens can stimulate tumor-specific T-cell-mediated antitumor immune responses, and therefore are potential immunotherapeutic targets. We developed ImmuneMirror as a stand-alone open-source pipeline and a web server incorporating a balanced random forest model for neoantigen prediction and prioritization. The prediction model was trained and tested using known immunogenic neopeptides collected from 19 published studies. The area under the curve of our trained model was 0.87 based on the testing data. We applied ImmuneMirror to the whole-exome sequencing and RNA sequencing data obtained from gastrointestinal tract cancers including 805 tumors from colorectal cancer (CRC), esophageal squamous cell carcinoma (ESCC) and hepatocellular carcinoma patients. We discovered a subgroup of microsatellite instability-high (MSI-H) CRC patients with a low neoantigen load but a high tumor mutation burden (> 10 mutations per Mbp). Although the efficacy of PD-1 blockade has been demonstrated in advanced MSI-H patients, almost half of such patients do not respond well. Our study identified a subset of MSI-H patients who may not benefit from this treatment with lower neoantigen load for major histocompatibility complex I (P < 0.0001) and II (P = 0.0008) molecules, respectively. Additionally, the neopeptide YMCNSSCMGV-TP53G245V, derived from a hotspot mutation restricted by HLA-A02, was identified as a potential actionable target in ESCC. This is so far the largest study to comprehensively evaluate neoantigen prediction models using experimentally validated neopeptides. Our results demonstrate the reliability and effectiveness of ImmuneMirror for neoantigen prediction.
| S-EPMC10859690 | biostudies-literature
Project description:Systematic dissection of the sumoylation proteome is emerging as an appealing but challenging research topic because of the significant roles sumoylation plays in cellular dynamics and plasticity. Although several proteome-scale analyzes have been performed to delineate potential sumoylatable proteins, the bona fide sumoylation sites still remain to be identified. Previously, we carried out a genome-wide analysis of the SUMO substrates in human nucleus using the putative motif psi-K-X-E and evolutionary conservation. However, a highly specific predictor for in silico prediction of sumoylation sites in any individual organism is still urgently needed to guide experimental design. In this work, we present a computational system SUMOsp--SUMOylation Sites Prediction, based on a manually curated dataset, integrating the results of two methods, GPS and MotifX, which were originally designed for phosphorylation site prediction. SUMOsp offers at least as good prediction performance as the only available method, SUMOplot, on a very large test set. We expect that the prediction results of SUMOsp combined with experimental verifications will propel our understanding of sumoylation mechanisms to a new level. SUMOsp has been implemented on a freely accessible web server at: http://bioinformatics.lcd-ustc.org/sumosp/.
| S-EPMC1538802 | biostudies-other
Project description:Antimicrobial resistance (AMR) is a major problem and an immediate alternative to antibiotics is the need of the hour. Research on the possible alternative products to tackle bacterial infections is ongoing worldwide. One of the most promising alternatives to antibiotics is the use of bacteriophages (phage) or phage-driven antibacterial drugs to cure bacterial infections caused by AMR bacteria. Phage-driven proteins, including holins, endolysins, and exopolysaccharides, have shown great potential in the development of antibacterial drugs. Likewise, phage virion proteins (PVPs) might also play an important role in the development of antibacterial drugs. Here, we have developed a machine learning-based prediction method to predict PVPs using phage protein sequences. We have employed well-known basic and ensemble machine learning methods with protein sequence composition features for the prediction of PVPs. We found that the gradient boosting classifier (GBC) method achieved the best accuracy of 80% on the training dataset and an accuracy of 83% on the independent dataset. The performance on the independent dataset is better than other existing methods. A user-friendly web server developed by us is freely available to all users for the prediction of PVPs from phage protein sequences. The web server might facilitate the large-scale prediction of PVPs and hypothesis-driven experimental study design.
| S-EPMC10004995 | biostudies-literature
Project description:Gene expression profiles were generated from 199 primary breast cancer patients. Samples 1-176 were used in another study, GEO Series GSE22820, and form the training data set in this study. Sample numbers 200-222 form a validation set. This data is used to model a machine learning classifier for Estrogen Receptor Status.
2013-01-01 | GSE29210 | GEO
Project description:Mycobacterium tuberculosis genome comprises approximately 10% of two families of poorly characterised genes due to their high GC content and highly repetitive nature. The largest sub-group, the proline-glutamic acid polymorphic guanine-cytosine-rich sequence (PE_PGRS) family, is thought to be involved in host response and disease pathogenicity. Due to their high genetic variability and complexity of analysis, they are typically disregarded for further research in genomic studies. There are currently limited online resources and homology computational tools that can identify and analyse PE_PGRS proteins. In addition, they are computational-intensive and time-consuming, and lack sensitivity. Therefore, computational methods that can rapidly and accurately identify PE_PGRS proteins are valuable to facilitate the functional elucidation of the PE_PGRS family proteins. In this study, we developed the first machine learning-based bioinformatics approach, termed PEPPER, to allow users to identify PE_PGRS proteins rapidly and accurately. PEPPER was built upon a comprehensive evaluation of 13 popular machine learning algorithms with various sequence and physicochemical features. Empirical studies demonstrated that PEPPER achieved significantly better performance than alignment-based approaches, BLASTP and PHMMER, in both prediction accuracy and speed. PEPPER is anticipated to facilitate community-wide efforts to conduct high-throughput identification and analysis of PE_PGRS proteins.
| S-EPMC8804200 | biostudies-literature
Project description:BackgroundThe liquid-liquid phase separation (LLPS) of biomolecules in cell underpins the formation of membraneless organelles, which are the condensates of protein, nucleic acid, or both, and play critical roles in cellular function. Dysregulation of LLPS is implicated in a number of diseases. Although the LLPS of biomolecules has been investigated intensively in recent years, the knowledge of the prevalence and distribution of phase separation proteins (PSPs) is still lag behind. Development of computational methods to predict PSPs is therefore of great importance for comprehensive understanding of the biological function of LLPS.ResultsBased on the PSPs collected in LLPSDB, we developed a sequence-based prediction tool for LLPS proteins (PSPredictor), which is an attempt at general purpose of PSP prediction that does not depend on specific protein types. Our method combines the componential and sequential information during the protein embedding stage, and, adopts the machine learning algorithm for final predicting. The proposed method achieves a tenfold cross-validation accuracy of 94.71%, and outperforms previously reported PSPs prediction tools. For further applications, we built a user-friendly PSPredictor web server ( http://www.pkumdl.cn/PSPredictor ), which is accessible for prediction of potential PSPs.ConclusionsPSPredictor could identifie novel scaffold proteins for stress granules and predict PSPs candidates in the human genome for further study. For further applications, we built a user-friendly PSPredictor web server ( http://www.pkumdl.cn/PSPredictor ), which provides valuable information for potential PSPs recognition.
| S-EPMC8845408 | biostudies-literature
Project description:Rectangular concrete-filled steel tubular (RCFST) columns are widely used in structural engineering due to their excellent load-carrying capacity and ductility. However, existing design equations often yield different design results for the same column properties, leading to uncertainty for engineering designers. Furthermore, basic regression analysis fails to precisely forecast the complicated relation between the column properties and its compressive strength. To overcome these challenges, this study suggests two machine learning (ML) models, including the Gaussian process (GPR) and the extreme gradient boosting model (XGBoost). These models employ a range of input variables, such as the geometric and material properties of RCFST columns, to estimate their strength. The models are trained and evaluated based on two datasets consisting of 958 axially loaded RCFST columns and 405 eccentrically loaded RCFST columns. In addition, a unitless output variable, termed the strength index, is introduced to enhance model performance. From evolution metrics, the GPR model emerged as the most accurate and reliable model, with nearly 99% of specimens with less than 20% error. In addition, the prediction results of ML models were compared with the predictions of two existing standard codes and different ML studies. The results indicated that the developed ML models achieved notable enhancement in prediction accuracy. In addition, the Shapley additive interpretation (SHAP) technique is employed for feature analysis. The feature analysis results reveal that the column length and load end-eccentricity parameters negatively impact compressive strength.
| S-EPMC10682462 | biostudies-literature
Project description:Machine learning (ML) systems can model quantitative structure-property relationships (QSPR) using existing experimental data and make property predictions for new molecules. With the advent of modalities such as targeted protein degraders (TPD), the applicability of QSPR models is questioned and ML usage in TPD-centric projects remains limited. Herein, ML models are developed and evaluated for TPDs' property predictions, including passive permeability, metabolic clearance, cytochrome P450 inhibition, plasma protein binding, and lipophilicity. Interestingly, performance on TPDs is comparable to that of other modalities. Predictions for glues and heterobifunctionals often yield lower and higher errors, respectively. For permeability, CYP3A4 inhibition, and human and rat microsomal clearance, misclassification errors into high and low risk categories are lower than 4% for glues and 15% for heterobifunctionals. For all modalities, misclassification errors range from 0.8% to 8.1%. Investigated transfer learning strategies improve predictions for heterobifunctionals. This is the first comprehensive evaluation of ML for the prediction of absorption, distribution, metabolism, and excretion (ADME) and physicochemical properties of TPD molecules, including heterobifunctional and molecular glue sub-modalities. Taken together, our investigations show that ML-based QSPR models are applicable to TPDs and support ML usage for TPDs' design, to potentially accelerate drug discovery.
| S-EPMC11233499 | biostudies-literature