Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Machine learning model”

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 1,063 records · Page 59Linked to original sources
PubMed2007

Evaluation of machine-learning methods for ligand-based virtual screening.

Machine-learning methods can be used for virtual screening by analysing the structural characteristics of molecules of known (in)activity, and we here discuss the use of kernel discrimination and naive Bayesian classifier (NBC) methods for this purpose. We report a kernel method that allows the processing of molecules represented by binary, integer and real-valued descriptors, and show that it is little different in screening performance from a previously described kernel that had been developed specifically for the analysis of binary fingerprint representations of molecular structure. We then evaluate the performance of an NBC when the training-set contains only a very few active molecules. In such cases, a simpler approach based on group fusion would appear to provide superior screening performance, especially when structurally heterogeneous datasets are to be processed.

Artificial Intelligence↗
PubMed1998

Population size and quality in genetics-based rule learning from medical data.

Population size and quality are parameters which control the performance of genetic algorithms. We researched these parameters in a genetic-based machine learning system Galactica which was used to discover the differential diagnostic rules for female urinary incontinence from case data. The performance of the system was measured with on-line and off-line criteria. Surprisingly, randomly generated small populations (30 and 70 rules) did not promote the best on-line performance as earlier results suggested. Probable explanation is the lack of diversity in initial populations. The seeding of population with positive learning examples was used to obtain more divergent populations. As expected, the seeding increased the on-line performance of small populations. The results are mainly in accord with the earlier results indicating that large randomly generated populations (150 rules) lead to the better off-line performance. Again, the seeding of small populations was successful producing even the better off-line performance than a large population. In conclusion, the seeding allowed the small populations to converge to good rules in relatively short period of time.

Algorithms↗
PubMed2004

Gene name ambiguity of eukaryotic nomenclatures.

MOTIVATION: With more and more scientific literature published online, the effective management and reuse of this knowledge has become problematic. Natural language processing (NLP) may be a potential solution by extracting, structuring and organizing biomedical information in online literature in a timely manner. One essential task is to recognize and identify genomic entities in text. 'Recognition' can be accomplished using pattern matching and machine learning. But for 'identification' these techniques are not adequate. In order to identify genomic entities, NLP needs a comprehensive resource that specifies and classifies genomic entities as they occur in text and that associates them with normalized terms and also unique identifiers so that the extracted entities are well defined. Online organism databases are an excellent resource to create such a lexical resource. However, gene name ambiguity is a serious problem because it affects the appropriate identification of gene entities. In this paper, we explore the extent of the problem and suggest ways to address it. RESULTS: We obtained gene information from 21 organisms and quantified naming ambiguities within species, across species, with English words and with medical terms. When the case (of letters) was retained, official symbols displayed negligible intra-species ambiguity (0.02%) and modest ambiguities with general English words (0.57%) and medical terms (1.01%). In contrast, the across-species ambiguity was high (14.20%). The inclusion of gene synonyms increased intra-species ambiguity substantially and full names contributed greatly to gene-medical-term ambiguity. A comprehensive lexical resource that covers gene information for the 21 organisms was then created and used to identify gene names by using a straightforward string matching program to process 45,000 abstracts associated with the mouse model organism while ignoring case and gene names that were also English words. We found that 85.1% of correctly retrieved mouse genes were ambiguous with other gene names. When gene names that were also English words were included, 233% additional 'gene' instances were retrieved, most of which were false positives. We also found that authors prefer to use synonyms (74.7%) to official symbols (17.7%) or full names (7.6%) in their publications. CONTACT: lifeng.chen@dbmi.columbia.edu

Abstracting and Indexing↗
PubMed2006

A multi-step approach to time series analysis and gene expression clustering.

MOTIVATION: The huge growth in gene expression data calls for the implementation of automatic tools for data processing and interpretation. RESULTS: We present a new and comprehensive machine learning data mining framework consisting in a non-linear PCA neural network for feature extraction, and probabilistic principal surfaces combined with an agglomerative approach based on Negentropy aimed at clustering gene microarray data. The method, which provides a user-friendly visualization interface, can work on noisy data with missing points and represents an automatic procedure to get, with no a priori assumptions, the number of clusters present in the data. Cell-cycle dataset and a detailed analysis confirm the biological nature of the most significant clusters. AVAILABILITY: The software described here is a subpackage part of the ASTRONEURAL package and is available upon request from the corresponding author. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Artificial Intelligence↗
PubMed2006

Protein solubility: sequence based prediction and experimental verification.

MOTIVATION: Obtaining soluble proteins in sufficient concentrations is a recurring limiting factor in various experimental studies. Solubility is an individual trait of proteins which, under a given set of experimental conditions, is determined by their amino acid sequence. Accurate theoretical prediction of solubility from sequence is instrumental for setting priorities on targets in large-scale proteomics projects. RESULTS: We present a machine-learning approach called PROSO to assess the chance of a protein to be soluble upon heterologous expression in Escherichia coli based on its amino acid composition. The classification algorithm is organized as a two-layered structure in which the output of primary support vector machine (SVM) classifiers serves as input for a secondary Naive Bayes classifier. Experimental progress information from the TargetDB database as well as previously published datasets were used as the source of training data. In comparison with previously published methods our classification algorithm possesses improved discriminatory capacity characterized by the Matthews Correlation Coefficient (MCC) of 0.434 between predicted and known solubility states and the overall prediction accuracy of 72% (75 and 68% for positive and negative class, respectively). We also provide experimental verification of our predictions using solubility measurements for 31 mutational variants of two different proteins.

Amino Acid Sequence↗
PubMed2025

IgStrand: A universal residue numbering scheme for the immunoglobulin-fold (Ig-fold) to study Ig-proteomes and Ig-interactomes.

The Immunoglobulin fold (Ig-fold) is found in proteins from all domains of life and represents the most populous fold in the human genome, with current estimates ranging from 2 to 3% of protein coding regions. That proportion is much higher in the surfaceome where Ig and Ig-like domains orchestrate cell-cell recognition, adhesion and signaling. The ability of Ig-domains to reliably fold and self-assemble through highly specific interfaces represents a remarkable property of these domains, making them key elements of molecular interaction systems: the immune system, the nervous system, the vascular system and the muscular system. We define a universal residue numbering scheme, common to all domains sharing the Ig-fold in order to study the wide spectrum of Ig-domain variants constituting the Ig-proteome and Ig-Ig interactomes at the heart of these systems. The "IgStrand numbering scheme" enables the identification of Ig structural proteomes and interactomes in and between any species, and comparative structural, functional, and evolutionary analyses. We review how Ig-domains are classified today as topological and structural variants and highlight the "Ig-fold irreducible structural signature" shared by all of them. The IgStrand numbering scheme lays the foundation for the systematic annotation of structural proteomes by detecting and accurately labeling Ig-, Ig-like and Ig-extended domains in proteins, which are poorly annotated in current databases and opens the door to accurate machine learning. Importantly, it sheds light on the robust Ig protein folding algorithm used by nature to form beta sandwich supersecondary structures. The numbering scheme powers an algorithm implemented in the interactive structural analysis software iCn3D to systematically recognize Ig-domains, annotate them and perform detailed analyses comparing any domain sharing the Ig-fold in sequence, topology and structure, regardless of their diverse topologies or origin. The scheme provides a robust fold detection and labeling mechanism that reveals unsuspected structural homologies among protein structures beyond currently identified Ig- and Ig-like domain variants. Indeed, multiple folds classified independently contain a common structural signature, in particular jelly-rolls. Examples of folds that harbor an "Ig-extended" architecture are given. Applications in protein engineering around the Ig-architecture are straightforward based on the universal numbering.

Humans↗
PubMed2004

Understanding protein dispensability through machine-learning analysis of high-throughput data.

MOTIVATION: Protein dispensability is fundamental to the understanding of gene function and evolution. Recent advances in generating high-throughput data such as genomic sequence data, protein-protein interaction data, gene-expression data and growth-rate data of mutants allow us to investigate protein dispensability systematically at the genome scale. RESULTS: In our studies, protein dispensability is represented as a fitness score that is measured by the growth rate of gene-deletion mutants. By the analyses of high-throughput data in yeast Saccharomyces cerevisiae, we found that a protein's dispensability had significant correlations with its evolutionary rate and duplication rate, as well as its connectivity in protein-protein interaction network and gene-expression correlation network. Neural network and support vector machine were applied to predict protein dispensability through high-throughput data. Our studies shed some lights on global characteristics of protein dispensability and evolution. AVAILABILITY: The original datasets for protein dispensability analysis and prediction, together with related scripts, are available at http://digbio.missouri.edu/~ychen/ProDispen/ CONTACT: xudong@missouri.edu.

Artificial Intelligence↗
PubMed2006

Protein disorder prediction by condensed PSSM considering propensity for order or disorder.

BACKGROUND: More and more disordered regions have been discovered in protein sequences, and many of them are found to be functionally significant. Previous studies reveal that disordered regions of a protein can be predicted by its primary structure, the amino acid sequence. One observation that has been widely accepted is that ordered regions usually have compositional bias toward hydrophobic amino acids, and disordered regions are toward charged amino acids. Recent studies further show that employing evolutionary information such as position specific scoring matrices (PSSMs) improves the prediction accuracy of protein disorder. As more and more machine learning techniques have been introduced to protein disorder detection, extracting more useful features with biological insights attracts more attention. RESULTS: This paper first studies the effect of a condensed position specific scoring matrix with respect to physicochemical properties (PSSMP) on the prediction accuracy, where the PSSMP is derived by merging several amino acid columns of a PSSM belonging to a certain property into a single column. Next, we decompose each conventional physicochemical property of amino acids into two disjoint groups which have a propensity for order and disorder respectively, and show by experiments that some of the new properties perform better than their parent properties in predicting protein disorder. In order to get an effective and compact feature set on this problem, we propose a hybrid feature selection method that inherits the efficiency of uni-variant analysis and the effectiveness of the stepwise feature selection that explores combinations of multiple features. The experimental results show that the selected feature set improves the performance of a classifier built with Radial Basis Function Networks (RBFN) in comparison with the feature set constructed with PSSMs or PSSMPs that adopt simply the conventional physicochemical properties. CONCLUSION: Distinguishing disordered regions from ordered regions in protein sequences facilitates the exploration of protein structures and functions. Results based on independent testing data reveal that the proposed predicting model DisPSSMP performs the best among several of the existing packages doing similar tasks, without either under-predicting or over-predicting the disordered regions. Furthermore, the selected properties are demonstrated to be useful in finding discriminating patterns for order/disorder classification.

Amino Acid Sequence↗
PubMed2004

Prediction of ultrasound-mediated disruption of cell membranes using machine learning techniques and statistical analysis of acoustic spectra.

Although biological effects of ultrasound must be avoided for safe diagnostic applications, ultrasound's ability to disrupt cell membranes has attracted interest as a method to facilitate drug and gene delivery. This paper seeks to develop "prediction rules" for predicting the degree of cell membrane disruption based on specified ultrasound parameters and measured acoustic signals. Three techniques for generating prediction rules (regression analysis, classification trees and discriminant analysis) are applied to data obtained from a sequence of experiments on bovine red blood cells. For each experiment, the data consist of four ultrasound parameters, acoustic measurements at 400 frequencies, and a measure of cell membrane disruption. To avoid over-training, various combinations of the 404 predictor variables are used when applying the rule generation methods. The results indicate that the variable combination consisting of ultrasound exposure time and acoustic signals measured at the driving frequency and its higher harmonics yields the best rule for all three rule generation methods. The methods used for deriving the prediction rules are broadly applicable, and could be used to develop prediciton rules in other scenarios involving different cell types or tissues. These rules and the methods used to derive them could be used for real-time feedback about ultrasound's biological effects.

Animals↗
PubMed2004

A Bayesian approach to joint feature selection and classifier design.

This paper adopts a Bayesian approach to simultaneously learn both an optimal nonlinear classifier and a subset of predictor variables (or features) that are most relevant to the classification task. The approach uses heavy-tailed priors to promote sparsity in the utilization of both basis functions and features; these priors act as regularizers for the likelihood function that rewards good classification on the training data. We derive an expectation-maximization (EM) algorithm to efficiently compute a maximum a posteriori (MAP) point estimate of the various parameters. The algorithm is an extension of recent state-of-the-art sparse Bayesian classifiers, which in turn can be seen as Bayesian counterparts of support vector machines. Experimental comparisons using kernel classifiers demonstrate both parsimonious feature selection and excellent classification accuracy on a range of synthetic and benchmark data sets.

Algorithms↗
PubMed2005

Decision tree based information integration for automated protein classification.

We propose a novel technique for automatically generating the SCOP classification of a protein structure with high accuracy. We achieve accurate classification by combining the decisions of multiple methods using the consensus of a committee (or an ensemble) classifier. Our technique, based on decision trees, is rooted in machine learning which shows that by judicially employing component classifiers, an ensemble classifier can be constructed to outperform its components. We use two sequence- and three structure-comparison tools as component classifiers. Given a protein structure and using the joint hypothesis, we first determine if the protein belongs to an existing category (family, superfamily, fold) in the SCOP hierarchy. For the proteins that are predicted as members of the existing categories, we compute their family-, superfamily-, and fold-level classifications using the consensus classifier. We show that we can significantly improve the classification accuracy compared to the individual component classifiers. In particular, we achieve error rates that are 3-12 times less than the individual classifiers' error rates at the family level, 1.5-4.5 times less at the superfamily level, and 1.1-2.4 times less at the fold level.

Algorithms↗
PubMed2001

A novel method of protein secondary structure prediction with high segment overlap measure: support vector machine approach.

We have introduced a new method of protein secondary structure prediction which is based on the theory of support vector machine (SVM). SVM represents a new approach to supervised pattern classification which has been successfully applied to a wide range of pattern recognition problems, including object recognition, speaker identification, gene function prediction with microarray expression profile, etc. In these cases, the performance of SVM either matches or is significantly better than that of traditional machine learning approaches, including neural networks.The first use of the SVM approach to predict protein secondary structure is described here. Unlike the previous studies, we first constructed several binary classifiers, then assembled a tertiary classifier for three secondary structure states (helix, sheet and coil) based on these binary classifiers. The SVM method achieved a good performance of segment overlap accuracy SOV=76.2 % through sevenfold cross validation on a database of 513 non-homologous protein chains with multiple sequence alignments, which out-performs existing methods. Meanwhile three-state overall per-residue accuracy Q(3) achieved 73.5 %, which is at least comparable to existing single prediction methods. Furthermore a useful "reliability index" for the predictions was developed. In addition, SVM has many attractive features, including effective avoidance of overfitting, the ability to handle large feature spaces, information condensing of the given data set, etc. The SVM method is conveniently applied to many other pattern classification tasks in biology.

Computer Simulation↗
PubMed2002

The brain-machine disanalogy revisited.

Michael Conrad was a pioneer in investigating biological information processing. He believed that there are fundamental lessons to be learned from the structure and behavior of biological brains that we are far from understanding or have implemented in our computers. Accumulation of advances in several fields have confirmed his views in broad outline but not necessarily in some of the strong forms he had tried to establish. For example, his assertion that programmable computers are intrinsically incapable of the brain's efficient and adaptive behavior has not received much examination. Yet, this is clearly a direction that could afford much insight into fundamental differences between brain and machine. In this paper, we pay tribute to Michael, by examining his pioneering thoughts on the brain-machine disanalogy in some depth and from the hindsight of a decade later. We argue that as long as we stay within the frame of reference of classical computation, it is not possible to confirm that programmability places a fundamental limitation on computing power, although the resources required to implement a programmable interface leave fewer resources for actual problem-solving work. However, if we abandon the classical computational frame and adopt one in which the user interacts with the system (artificial or natural) in real time, it becomes easier to examine the key attributes that Michael believed place biological brains on a higher plane of capability than artificial ones. While we then see some of these positive distinctions confirmed (e.g. the limitations of symbol manipulation systems in addressing real-world perception problems), we also see attributes in which the implementation in bioware constrains the behavior of real brains. We conclude by discussing how new insights are emerging, that look at the time-bound problem-solving constraints under which organisms have had to survive and how their so-called 'fast and frugal' faculties are tuned to the environments that coevolved with them. These directions open new paths for a multifaceted understanding of what biological brains do and what we can learn from them. We close by suggesting how the discrete event modeling and simulation paradigm offers a suitable medium for exploring these paths.

Behavior↗
PubMed2004

Predicting functional family of novel enzymes irrespective of sequence similarity: a statistical learning approach.

The function of a protein that has no sequence homolog of known function is difficult to assign on the basis of sequence similarity. The same problem may arise for homologous proteins of different functions if one is newly discovered and the other is the only known protein of similar sequence. It is desirable to explore methods that are not based on sequence similarity. One approach is to assign functional family of a protein to provide useful hint about its function. Several groups have employed a statistical learning method, support vector machines (SVMs), for predicting protein functional family directly from sequence irrespective of sequence similarity. These studies showed that SVM prediction accuracy is at a level useful for functional family assignment. But its capability for assignment of distantly related proteins and homologous proteins of different functions has not been critically and adequately assessed. Here SVM is tested for functional family assignment of two groups of enzymes. One consists of 50 enzymes that have no homolog of known function from PSI-BLAST search of protein databases. The other contains eight pairs of homologous enzymes of different families. SVM correctly assigns 72% of the enzymes in the first group and 62% of the enzyme pairs in the second group, suggesting that it is potentially useful for facilitating functional study of novel proteins. A web version of our software, SVMProt, is accessible at http://jing.cz3.nus.edu.sg/cgi-bin/svmprot.cgi.

Artificial Intelligence↗
PubMed2005

Fast modular network implementation for support vector machines.

Support vector machines (SVMs) have been extensively used. However, it is known that SVMs face difficulty in solving large complex problems due to the intensive computation involved in their training algorithms, which are at least quadratic with respect to the number of training examples. This paper proposes a new, simple, and efficient network architecture which consists of several SVMs each trained on a small subregion of the whole data sampling space and the same number of simple neural quantizer modules which inhibit the outputs of all the remote SVMs and only allow a single local SVM to fire (produce actual output) at any time. In principle, this region-computing based modular network method can significantly reduce the learning time of SVM algorithms without sacrificing much generalization performance. The experiments on a few real large complex benchmark problems demonstrate that our method can be significantly faster than single SVMs without losing much generalization performance.

Algorithms↗
PubMed2001

Definition of the Bacillus subtilis PurR operator using genetic and bioinformatic tools and expansion of the PurR regulon with glyA, guaC, pbuG, xpt-pbuX, yqhZ-folD, and pbuO.

The expression of the pur operon, which encodes enzymes of the purine biosynthetic pathway in Bacillus subtilis, is subject to control by the purR gene product (PurR) and phosphoribosylpyrophosphate. This control is also exerted on the purA and purR genes. A consensus sequence for the binding of PurR, named the PurBox, has been suggested (M. Kilstrup, S. G. Jessing, S. B. Wichmand-Jørgensen, M. Madsen, and D. Nilsson, J. Bacteriol. 180:3900-3906, 1998). To determine whether the expression of other genes might be regulated by PurR, we performed a search for PurBox sequences in the B. subtilis genome sequence and found several candidate PurBoxes. By the use of transcriptional lacZ fusions, five selected genes or operons (glyA, yumD, yebB, xpt-pbuX, and yqhZ-folD), all having a putative PurBox in their upstream regulatory regions, were found to be regulated by PurR. Using a machine-learning algorithm developed for sequence pattern finding, we found that all of the genes identified as being PurR regulated have two PurBoxes in their upstream control regions. The two boxes are divergently oriented, forming a palindromic sequence with the inverted repeats separated by 16 or 17 nucleotides. A computerized search revealed one additional PurR-regulated gene, ytiP. The significance of the tandem PurBox motifs was demonstrated in vivo by deletion analysis and site-directed mutagenesis of the two PurBox sequences located upstream of glyA. All six genes or operons encode enzymes or transporters playing a role in purine nucleotide metabolism. Functional analysis showed that yebB encodes the previously characterized hypoxanthine-guanine permease PbuG and that ytiP encodes another guanine-hypoxanthine permease and is now named pbuO. yumD encodes a GMP reductase and is now named guaC.

Bacillus subtilis↗
PubMed1992

IPSA-Inductive Protein Structure Analysis.

The Inductive Structure Protein Analysis (IPSA) project presents a new method for investigating protein structure. IPSA includes the creation of a new database which was designed specifically for the analysis of protein structure by statistics and machine learning. The Protein Representation Language (PRL) database includes explicit and symbolic representations of geometrical, topological and chemophysical information about secondary structures and the relationships between secondary structures. The IPSA methodology consists of: the use of PRL information to produce a new database of examples of secondary structures which associate together (examples of possible super-secondary structures); then the use of a variety of clustering techniques to produce a consensus clustering of these examples (super-secondary structures); these super-secondary structures are finally examined to uncover any biological features of significance. We have applied this method to find simple super-secondary structures consisting of pairs of alpha-helices. We found four well-defined super-secondary structures, one formed exclusively by long range interactions, and another in association with an additional element of secondary structure (alpha t alpha-motif). Examinations were carried out using homologous pairs and conformational fits which confirm our clustering.

Cluster Analysis↗
PubMed1999

Exploiting the past and the future in protein secondary structure prediction.

MOTIVATION: Predicting the secondary structure of a protein (alpha-helix, beta-sheet, coil) is an important step towards elucidating its three-dimensional structure, as well as its function. Presently, the best predictors are based on machine learning approaches, in particular neural network architectures with a fixed, and relatively short, input window of amino acids, centered at the prediction site. Although a fixed small window avoids overfitting problems, it does not permit capturing variable long-rang information. RESULTS: We introduce a family of novel architectures which can learn to make predictions based on variable ranges of dependencies. These architectures extend recurrent neural networks, introducing non-causal bidirectional dynamics to capture both upstream and downstream information. The prediction algorithm is completed by the use of mixtures of estimators that leverage evolutionary information, expressed in terms of multiple alignments, both at the input and output levels. While our system currently achieves an overall performance close to 76% correct prediction--at least comparable to the best existing systems--the main emphasis here is on the development of new algorithmic ideas. AVAILABILITY: The executable program for predicting protein secondary structure is available from the authors free of charge. CONTACT: pfbaldi@ics.uci.edu, gpollast@ics.uci.edu, brunak@cbs.dtu.dk, paolo@dsi.unifi.it.

Algorithms↗