SEARCH · PubMed Health

Results for “machine learning algorithms”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

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

At least 811 records · Page 45Linked to original sources

PubMed2005

A robust meta-classification strategy for cancer diagnosis from gene expression data.

One of the major challenges in cancer diagnosis from microarray data is to develop robust classification models which are independent of the analysis techniques used and can combine data from different laboratories. We propose a meta-classification scheme which uses a robust multivariate gene selection procedure and integrates the results of several machine learning tools trained on raw and pattern data. We validate our method by applying it to distinguish diffuse large B-cell lymphoma (DLBCL) from follicular lymphoma (FL) on two independent datasets: the HuGeneFL Affmetrixy dataset of Shipp et al. (www. genome.wi.mit.du/MPR /lymphoma) and the Hu95Av2 Affymetrix dataset (DallaFavera's laboratory, Columbia University). Our meta-classification technique achieves higher predictive accuracies than each of the individual classifiers trained on the same dataset and is robust against various data perturbations. We also find that combinations of p53 responsive genes (e.g., p53, PLK1 and CDK2) are highly predictive of the phenotype.

Algorithms↗

PubMed2005

Support vector machines for prediction and analysis of beta and gamma-turns in proteins.

Tight turns have long been recognized as one of the three important features of proteins, together with alpha-helix and beta-sheet. Tight turns play an important role in globular proteins from both the structural and functional points of view. More than 90% tight turns are beta-turns and most of the rest are gamma-turns. Analysis and prediction of beta-turns and gamma-turns is very useful for design of new molecules such as drugs, pesticides, and antigens. In this paper we investigated two aspects of applying support vector machine (SVM), a promising machine learning method for bioinformatics, to prediction and analysis of beta-turns and gamma-turns. First, we developed two SVM-based methods, called BTSVM and GTSVM, which predict beta-turns and gamma-turns in a protein from its sequence. When compared with other methods, BTSVM has a superior performance and GTSVM is competitive. Second, we used SVMs with a linear kernel to estimate the support of amino acids for the formation of beta-turns and gamma-turns depending on their position in a protein. Our analysis results are more comprehensive and easier to use than the previous results in designing turns in proteins.

Algorithms↗

PubMedDate not supplied

Significance of gene ranking for classification of microarray samples.

Many methods for classification and gene selection with microarray data have been developed. These methods usually give a ranking of genes. Evaluating the statistical significance of the gene ranking is important for understanding the results and for further biological investigations, but this question has not been well addressed for machine learning methods in existing works. Here, we address this problem by formulating it in the framework of hypothesis testing and propose a solution based on resampling. The proposed r-test methods convert gene ranking results into position p-values to evaluate the significance of genes. The methods are tested on three real microarray data sets and three simulation data sets with support vector machines as the method of classification and gene selection. The obtained position p-values help to determine the number of genes to be selected and enable scientists to analyze selection results by sophisticated multivariate methods under the same statistical inference paradigm as for simple hypothesis testing methods.

Algorithms↗

PubMed2005

Causal protein-signaling networks derived from multiparameter single-cell data.

Machine learning was applied for the automated derivation of causal influences in cellular signaling networks. This derivation relied on the simultaneous measurement of multiple phosphorylated protein and phospholipid components in thousands of individual primary human immune system cells. Perturbing these cells with molecular interventions drove the ordering of connections between pathway components, wherein Bayesian network computational methods automatically elucidated most of the traditionally reported signaling relationships and predicted novel interpathway network causalities, which we verified experimentally. Reconstruction of network models from physiologically relevant primary single cells might be applied to understanding native-state tissue signaling biology, complex drug actions, and dysfunctional signaling in diseased cells.

Algorithms↗

PubMed2003

Towards a computational model for -1 eukaryotic frameshifting sites.

MOTIVATION: Unconventional decoding events are now well acknowledged, but not yet well formalized. In this study, we present a bioinformatics analysis of eukaryotic -1 frameshifting, in order to model this event. RESULTS: A consensus model has already been established for -1 frameshifting sites. Our purpose here is to provide new constraints which make the model more precise. We show how a machine learning approach can be used to refine the current model. We identify new properties that may be involved in frameshifting. Each of the properties found was experimentally validated. Initially, we identify features of the overall model that are to be simultaneously satisfied. We then focus on the following two components: the spacer and the slippery sequence. As a main result, we point out that the identity of the primary structure of the so-called spacer is of great importance. AVAILABILITY: Sequences of the oligonucleotides in the functional tests are available at http://www.igmors.u-psud.fr/rousset/bioinformatics/.

Algorithms↗

PubMed1995

Predicting protein folding classes without overly relying on homology.

An important open problem in molecular biology is how to use computational methods to understand the structure and function of proteins given only their primary sequences. We describe and evaluate an original machine-learning approach to classifying protein sequences according to their structural folding class. Our work is novel in several respects: we use a set of protein classes that previously have not been used for classifying primary sequences, and we use a unique set of attributes to represent protein sequences to the learners. We evaluate our approach by measuring its ability to correctly classify proteins that were not in its training set. We compare our input representation to a commonly used input representation--amino acid composition--and show that our approach more accurately classifies proteins that have very limited homology to the sequences on which the systems are trained.

Algorithms↗

PubMed2005

Knowledge-based computational search for genes associated with the metabolic syndrome.

MOTIVATION: A methodology to search for genes associated with multifactorial diseases by integrating the large amount of accumulated knowledge is seriously needed. A comprehensive understanding derived from a holistic view of gene relationship structures can be gained from our proposed analysis called the cross-subspace analysis (CSA). In this analysis, gene objects are generated by machine learning using their term occurrence patterns in MEDLINE abstracts and the degree of relationship between gene objects is quantified by matching these patterns. RESULTS: Structuralization of relationships of a set of genes was performed using CSA, which were retrieved using the terms, 'obesity', 'diabetes', 'hypertriglyceridemia' and 'hypertension' that refer to diseases comprising metabolic syndrome, on a 2D plane inferring important biomedical concepts from the gene distribution. Then, we prioritized the significance of 6131 well-annotated human genes in terms of the distance on the plane from the centroid of 'metabolic syndrome'-related genes distribution. The validity was confirmed by comparing the knowledge extracted by the ordering with existing medical knowledge.

Abstracting and Indexing↗

PubMed2026

Artificial intelligence for anticancer drug discovery from natural products of macroalgae and sponges: A systematic review.

Marine natural products (MNPs) from macroalgae and marine sponges have inspired clinically important anticancer agents, including the cytarabine pharmacophore and the eribulin scaffold, while cyanobacterial dolastatin chemistry supplies the auristatin payloads of several marine-inspired antibody-drug conjugates (ADCs) such as brentuximab vedotin. Artificial intelligence (AI) methods, encompassing both classical machine learning (ML) with hand-engineered features and modern deep learning (DL) with many-layered neural networks, are increasingly supporting key decisions in natural-product anticancer drug discovery, including bioactivity prediction, target identification, absorption, distribution, metabolism, excretion and toxicity (ADMET) filtering, generative analogue design, and the selection of preclinical candidates. DL architectures relevant to this field include graph neural networks, transformer-based molecular generators, diffusion models for protein-ligand docking, and convolutional networks for mass spectrometry, while classical ML contributes interpretable fingerprint-based bioactivity models and molecular networking for dereplication. This review follows a systematic literature review methodology to organize the landscape of AI methods now applied to MNP anticancer discovery, distinguishing ML and DL approaches where relevant, situating them within the chemical context of macroalgal and sponge-derived oncology leads, and critically examining published case studies, including validation level (computational, in vitro, in vivo, clinical). The principal bottleneck for medical translation has shifted partly from algorithmic capability toward data infrastructure and experimental validation. Sparse, heterogeneous, and taxonomically biased bioactivity records limit what current models can learn and reduce the reliability of AI-prioritized candidates entering the preclinical pipeline. A roadmap is proposed that prioritizes open MNP-specific benchmarks, symbiont-aware modeling, and active learning loops with synthesizability and ADMET constraints. These AI workflows may accelerate the prioritization of marine-derived anticancer leads and support earlier, more evidence-based translational decisions in oncology drug development.

Biological Products↗

PubMed2004

Predicting genetic regulatory response using classification.

MOTIVATION: Studying gene regulatory mechanisms in simple model organisms through analysis of high-throughput genomic data has emerged as a central problem in computational biology. Most approaches in the literature have focused either on finding a few strong regulatory patterns or on learning descriptive models from training data. However, these approaches are not yet adequate for making accurate predictions about which genes will be up- or down-regulated in new or held-out experiments. By introducing a predictive methodology for this problem, we can use powerful tools from machine learning and assess the statistical significance of our predictions. RESULTS: We present a novel classification-based method for learning to predict gene regulatory response. Our approach is motivated by the hypothesis that in simple organisms such as Saccharomyces cerevisiae, we can learn a decision rule for predicting whether a gene is up- or down-regulated in a particular experiment based on (1) the presence of binding site subsequences ('motifs') in the gene's regulatory region and (2) the expression levels of regulators such as transcription factors in the experiment ('parents'). Thus, our learning task integrates two qualitatively different data sources: genome-wide cDNA microarray data across multiple perturbation and mutant experiments along with motif profile data from regulatory sequences. We convert the regression task of predicting real-valued gene expression measurements to a classification task of predicting +1 and -1 labels, corresponding to up- and down-regulation beyond the levels of biological and measurement noise in microarray measurements. The learning algorithm employed is boosting with a margin-based generalization of decision trees, alternating decision trees. This large-margin classifier is sufficiently flexible to allow complex logical functions, yet sufficiently simple to give insight into the combinatorial mechanisms of gene regulation. We observe encouraging prediction accuracy on experiments based on the Gasch S.cerevisiae dataset, and we show that we can accurately predict up- and down-regulation on held-out experiments. We also show how to extract significant regulators, motifs and motif-regulator pairs from the learned models for various stress responses. Our method thus provides predictive hypotheses, suggests biological experiments, and provides interpretable insight into the structure of genetic regulatory networks. AVAILABILITY: The MLJava package is available upon request to the authors. Supplementary: Additional results are available from http://www.cs.columbia.edu/compbio/geneclass

Binding Sites↗

PubMed2005

Profile-based string kernels for remote homology detection and motif extraction.

We introduce novel profile-based string kernels for use with support vector machines (SVMs) for the problems of protein classification and remote homology detection. These kernels use probabilistic profiles, such as those produced by the PSI-BLAST algorithm, to define position-dependent mutation neighborhoods along protein sequences for inexact matching of k-length subsequences ("k-mers") in the data. By use of an efficient data structure, the kernels are fast to compute once the profiles have been obtained. For example, the time needed to run PSI-BLAST in order to build the profiles is significantly longer than both the kernel computation time and the SVM training time. We present remote homology detection experiments based on the SCOP database where we show that profile-based string kernels used with SVM classifiers strongly outperform all recently presented supervised SVM methods. We further examine how to incorporate predicted secondary structure information into the profile kernel to obtain a small but significant performance improvement. We also show how we can use the learned SVM classifier to extract "discriminative sequence motifs"--short regions of the original profile that contribute almost all the weight of the SVM classification score--and show that these discriminative motifs correspond to meaningful structural features in the protein data. The use of PSI-BLAST profiles can be seen as a semi-supervised learning technique, since PSI-BLAST leverages unlabeled data from a large sequence database to build more informative profiles. Recently presented "cluster kernels" give general semi-supervised methods for improving SVM protein classification performance. We show that our profile kernel results also outperform cluster kernels while providing much better scalability to large datasets.

Algorithms↗

PubMed1995

Machine learning to support diagnostics in the domain of asymptomatic liver disease.

Machine learning procedures, in unsupervised and supervised manner, can enable their users to achieve knowledge hardly comprehensible by even the best experts. This is true also if the clinical knowledge has been carefully assembled in a prospective way. A data set including 165 patients with elevated routine laboratory tests was extensively studied according to clinical history, laboratory profile and liver biopsy. Unsupervised learning by Kohonen feature map disclosed 4 groups of patients: the largest one with no or slight histopathological changes (116) and three smaller, more homogenous, with more diseased patients. Standardized histopathological scorings of the liver specimens defined patients into two groups. Fifty-eight of them were, according to the analysis, recommended for a liver biopsy, due to more severe degrees of inflammation and fibrosis. One-hundred and seven of the patients, in whom liver biopsy was retrospectively considered unnecessary, had only minor degrees of inflammation, fibrosis and/or steatosis. Supervised learning, using the inductive systems based on Quinlan's ID3 and CART algorithms, extracted knowledge in the form of decision trees. This approach could define a need for biopsy either with a very few significant findings or by pathways containing quotients and multiplications of the different basic items. These procedures were analyzed and compared for their theoretical and applicative performances. The cluster and Fischerian discriminant analyses were performed in order to compare the classification performance. The medical appropriateness of the obtained results is satisfying, therefore decision support systems, outlined in this study, should be evaluated in wider clinical practice. To achieve this goal, an example of a Medical Logical Module (MLM), based on the Arden Syntax, is given.

Adult↗

PubMed2004

Benign/malignant classifier of soft tissue tumors using MR imaging.

UNLABELLED: This article presents a pattern-recognition approach to the soft tissue tumors (STT) benign/malignant character diagnosis using magnetic resonance (MR) imaging applied to a large multicenter database. OBJECTIVE: To develop and test an automatic classifier of STT into benign or malignant by using classical MR imaging findings and epidemiological information. MATERIALS AND METHODS: A database of 430 patients (62% benign and 38% malignant) from several European multicenter registers. There were 61 different histologies (36 with benign and 25 with malignant nature). Three pattern-recognition methods (artificial neural networks, support vector machine, k-nearest neighbor) were applied to learn the discrimination between benignity and malignancy based on a defined MR imaging findings protocol. After the systems had learned by using training samples (with 302 cases), the clinical decision support system was tested in the diagnosis of 128 new STT cases. RESULTS: An 88-92% efficacy was obtained in a not-viewed set of tumors using the pattern-recognition techniques. The best results were obtained with a back-propagation artificial neural network. CONCLUSION: Benign vs. malignant STT discrimination is accurate by using pattern-recognition methods based on classical MR image findings. This objective tool will assist radiologists in STT grading.

Algorithms↗

PubMed2006

Support vector analysis of color-Doppler images: a new approach for estimating indices of left ventricular function.

Reliable noninvasive estimators of global left ventricular (LV) chamber function remain unavailable. We have previously demonstrated a potential relationship between color-Doppler M-mode (CDMM) images and two basic indices of LV function: peak-systolic elastance (Emax) and the time-constant of LV relaxation (tau). Thus, we hypothesized that these two indices could be estimated noninvasively by adequate postprocessing of CDMM recordings. A semiparametric regression (SR) version of support vector machine (SVM) is here proposed for building a blind model, capable of analyzing CDMM images automatically, as well as complementary clinical information. Simultaneous invasive and Doppler tracings were obtained in nine mini-pigs in a high-fidelity experimental setup. The model was developed using a test and validation leave-one-out design. Reasonably acceptable prediction accuracy was obtained for both Emax (intraclass correlation coefficient Ric, = 0.81) and tau (Ric, = 0.61). For the first time, a quantitative, noninvasive estimation of cardiovascular indices is addressed by processing Doppler-echocardiography recordings using a learning-from-samples method.

Algorithms↗

PubMedDate not supplied

An intelligent system approach to higher-dimensional classification of volume data.

In volume data visualization, the classification step is used to determine voxel visibility and is usually carried out through the interactive editing of a transfer function that defines a mapping between voxel value and color/opacity. This approach is limited by the difficulties in working effectively in the transfer function space beyond two dimensions. We present a new approach to the volume classification problem which couples machine learning and a painting metaphor to allow more sophisticated classification in an intuitive manner. The user works in the volume data space by directly painting on sample slices of the volume and the painted voxels are used in an iterative training process. The trained system can then classify the entire volume. Both classification and rendering can be hardware accelerated, providing immediate visual feedback as painting progresses. Such an intelligent system approach enables the user to perform classification in a much higher dimensional space without explicitly specifying the mapping for every dimension used. Furthermore, the trained system for one data set may be reused to classify other data sets with similar characteristics.

Algorithms↗

PubMed2006

Prediction of protein continuum secondary structure with probabilistic models based on NMR solved structures.

BACKGROUND: The structure of proteins may change as a result of the inherent flexibility of some protein regions. We develop and explore probabilistic machine learning methods for predicting a continuum secondary structure, i.e. assigning probabilities to the conformational states of a residue. We train our methods using data derived from high-quality NMR models. RESULTS: Several probabilistic models not only successfully estimate the continuum secondary structure, but also provide a categorical output on par with models directly trained on categorical data. Importantly, models trained on the continuum secondary structure are also better than their categorical counterparts at identifying the conformational state for structurally ambivalent residues. CONCLUSION: Cascaded probabilistic neural networks trained on the continuum secondary structure exhibit better accuracy in structurally ambivalent regions of proteins, while sustaining an overall classification accuracy on par with standard, categorical prediction methods.

Algorithms↗

PubMed2005

Gene/protein name recognition based on support vector machine using dictionary as features.

BACKGROUND: Automated information extraction from biomedical literature is important because a vast amount of biomedical literature has been published. Recognition of the biomedical named entities is the first step in information extraction. We developed an automated recognition system based on the SVM algorithm and evaluated it in Task 1.A of BioCreAtIvE, a competition for automated gene/protein name recognition. RESULTS: In the work presented here, our recognition system uses the feature set of the word, the part-of-speech (POS), the orthography, the prefix, the suffix, and the preceding class. We call these features "internal resource features", i.e., features that can be found in the training data. Additionally, we consider the features of matching against dictionaries to be external resource features. We investigated and evaluated the effect of these features as well as the effect of tuning the parameters of the SVM algorithm. We found that the dictionary matching features contributed slightly to the improvement in the performance of the f-score. We attribute this to the possibility that the dictionary matching features might overlap with other features in the current multiple feature setting. CONCLUSION: During SVM learning, each feature alone had a marginally positive effect on system performance. This supports the fact that the SVM algorithm is robust on the high dimensionality of the feature vector space and means that feature selection is not required.

Algorithms↗

PubMed2006

A bio-basis function neural network for protein peptide cleavage activity characterisation.

This paper presents a novel neural learning algorithm for analysing protein peptides which comprise amino acids as non-numerical attributes. The algorithm is derived from the radial basis function neural networks (RBFNNs) and is referred to as a bio-basis function neural network (BBFNN). The basic principle is to replace the radial basis function used by RBFNNs with a bio-basis function. Each basis in BBFNN is supported by a peptide. The bases collectively form a feature space, in which each basis represents a feature dimension. A linear classifier is constructed in the feature space for characterising a protein peptide in terms of functional status. The theoretical basis of BBFNN is that peptides, which perform the same function will have similar compositions of amino acids. Because of this, the similarity between peptides can have statistical significance for modelling while the proposed bio-basis function can well code this information from data. The application to two real cases shows that BBFNN outperformed multi-layer perceptrons and support vector machines.

Algorithms↗

PubMedDate not supplied

Introducing the consensus modeling concept in genetic algorithms: application to interpretable discriminant analysis.

An evolutionary statistical learning method was applied to classify drugs according to their biological target and also to discriminate between a compilation of oral and nonoral drugs. The emphasis was placed not only on how well the models predict but also on their interpretability. In an enhancement to previous studies, the consistency of the model weights over several runs of the genetic algorithm was considered with the goal of producing comprehensible models. Via this approach, the descriptors and their ranges that contribute most to class discrimination were identified. Selecting a bin step size that enables the average descriptor properties of the class being trained to be captured improves the interpretability and discriminatory power of a model. The performance, consistency, and robustness of such models were further enhanced by using two novel approaches that reduce the variability between individual solutions: consensus and splice modeling. Finally, the ability of the genetic algorithm to discriminate between activity classes was compared with a similarity searching method, while naïve Bayes classifiers and support vector machines were applied in discriminating the oral and nonoral drugs.

Algorithms↗