Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Representation Machine Learning”

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 145 records · Page 8Linked to original sources
PubMed2001

The constraint based decomposition (CBD) training architecture.

The Constraint Based Decomposition (CBD) is a constructive neural network technique that builds a three or four layer network, has guaranteed convergence and can deal with binary, n-ary, class labeled and real-value problems. CBD is shown to be able to solve complicated problems in a simple, fast and reliable manner. The technique is further enhanced by two modifications (locking detection and redundancy elimination) which address the training speed and the efficiency of the internal representation built by the network. The redundancy elimination aims at building more compact architectures while the locking detection aims at improving the training speed. The computational cost of the redundancy elimination is negligible and this enhancement can be used for any problem. However, the computational cost of the locking detection is exponential in the number of dimensions and should only be used in low dimensional spaces. The experimental results show the performance of the algorithm presented in a series of classical benchmark problems including the 2-spiral problem and the Iris, Wine, Glass, Lenses, Ionosphere, Lung cancer, Pima Indians, Bupa, TicTacToe, Balance and Zoo data sets from the UCI machine learning repository. CBD's generalization accuracy is compared with that of C4.5, C4.5 with rules, incremental decision trees, oblique classifiers, linear machine decision trees, CN2, learning vector quantization (LVQ), backpropagation, nearest neighbor, Q* and radial basis functions (RBFs). CBD provides the second best average accuracy on the problems tested as well as the best reliability (the lowest standard deviation).

Algorithms↗
PubMed2004

Refinement of generated fuzzy production rules by using a fuzzy neural network.

Fuzzy production rules (FPRs) have been used for years to capture and represent fuzzy, vague, imprecise and uncertain domain knowledge in many fuzzy systems. There have been a lot of researches on how to generate or obtain FPRs. There exist two methods to obtain FPRs. One is by painstakingly, repeatedly and time-consuming interviewing domain experts to extract the domain knowledge. The other is by using some machine learning techniques to generate and extract FPRs from some training samples. These extracted rules, however, are found to be nonoptimal and sometimes redundant. Furthermore, these generated rules suffer from the problem of low accuracy of classifying or recognizing unseen examples. The reasons for having these problems are 1) the FPRs generated are not powerful enough to represent the domain knowledge, 2) the techniques used to generate FPRs are pre-matured, ad-hoc or may not be suitable for the problem, and 3) further refinement of the extracted rules has not been done. In this paper we look into the solutions of the above problems by 1) enhancing the representation power of FPRs by including local and global weights, 2) developing a fuzzy neural network (FNN) with enhanced learning algorithm, and 3) using this FNN to refine the local and global weights of FPRs. By experimenting our method with some existing benchmark examples, the proposed method is found to have high accuracy in classifying unseen samples without increasing the number of the FPRs extracted and the time required to consult with domain experts is greatly reduced.

Journal Article↗
PubMed2002

Natural discriminant analysis using interactive Potts models.

Natural discriminant analysis based on interactive Potts models is developed in this work. A generative model composed of piece-wise multivariate gaussian distributions is used to characterize the input space, exploring the embedded clustering and mixing structures and developing proper internal representations of input parameters. The maximization of a log-likelihood function measuring the fitness of all input parameters to the generative model, and the minimization of a design cost summing up square errors between posterior outputs and desired outputs constitutes a mathematical framework for discriminant analysis. We apply a hybrid of the mean-field annealing and the gradient-descent methods to the optimization of this framework and obtain multiple sets of interactive dynamics, which realize coupled Potts models for discriminant analysis. The new learning process is a whole process of component analysis, clustering analysis, and labeling analysis. Its major improvement compared to the radial basis function and the support vector machine is described by using some artificial examples and a real-world application to breast cancer diagnosis.

Journal Article↗
PubMed2005

A support vector machine approach to the identification of phosphorylation sites.

We describe a bioinformatics tool that can be used to predict the position of phosphorylation sites in proteins based only on sequence information. The method uses the support vector machine (SVM) statistical learning theory. The statistical models for phosphorylation by various types of kinases are built using a dataset of short (9-amino acid long) sequence fragments. The sequence segments are dissected around post-translationally modified sites of proteins that are on the current release of the Swiss-Prot database, and that were experimentally confirmed to be phosphorylated by any kinase. We represent them as vectors in a multidimensional abstract space of short sequence fragments. The prediction method is as follows. First, a given query protein sequence is dissected into overlapping short segments. All the fragments are then projected into the multidimensional space of sequence fragments via a collection of different representations. Those points are classified with pre-built statistical models (the SVM method with linear, polynomial and radial kernel functions) either as phosphorylated or inactive ones. The resulting list of plausible sites for phosphorylation by various types of kinases in the query protein is returned to the user. The efficiency of the method for each type of phosphorylation is estimated using leave-one-out tests and presented here. The sensitivities of the models can reach over 70%, depending on the type of kinase. The additional information from profile representations of short sequence fragments helps in gaining a higher degree of accuracy in some phosphorylation types. The further development of an automatic phosphorylation site annotation predictor based on our algorithm should yield a significant improvement when using statistical algorithms in order to quantify the results.

Algorithms↗
PubMed2006

Classification of faces in man and machine.

We attempt to shed light on the algorithms humans use to classify images of human faces according to their gender. For this, a novel methodology combining human psychophysics and machine learning is introduced. We proceed as follows. First, we apply principal component analysis (PCA) on the pixel information of the face stimuli. We then obtain a data set composed of these PCA eigenvectors combined with the subjects' gender estimates of the corresponding stimuli. Second, we model the gender classification process on this data set using a separating hyperplane (SH) between both classes. This SH is computed using algorithms from machine learning: the support vector machine (SVM), the relevance vector machine, the prototype classifier, and the K-means classifier. The classification behavior of humans and machines is then analyzed in three steps. First, the classification errors of humans and machines are compared for the various classifiers, and we also assess how well machines can recreate the subjects' internal decision boundary by studying the training errors of the machines. Second, we study the correlations between the rank-order of the subjects' responses to each stimulus-the gender estimate with its reaction time and confidence rating-and the rank-order of the distance of these stimuli to the SH. Finally, we attempt to compare the metric of the representations used by humans and machines for classification by relating the subjects' gender estimate of each stimulus and the distance of this stimulus to the SH. While we show that the classification error alone is not a sufficient selection criterion between the different algorithms humans might use to classify face stimuli, the distance of these stimuli to the SH is shown to capture essentials of the internal decision space of humans. Furthermore, algorithms such as the prototype classifier using stimuli in the center of the classes are shown to be less adapted to model human classification behavior than algorithms such as the SVM based on stimuli close to the boundary between the classes.

Algorithms↗
PubMed1990

A gene mapping expert system.

Expert systems are now commonly developed to solve practical problems. Nevertheless, genetics has just begun to benefit from this new technology, since genetic expert systems are extremely rare and often purely experimental. A prototype for risk calculation in pedigrees was developed at the University of Utah, using a commercial frames/rules developmental shell (Intelligence Compiler), which runs on an IBM PC. When small data sets were used, the implementation functioned well, but it could not handle larger data sets. Performance became a major issue, with two possible solutions. The first possibility would have been to port the system to a more powerful machine, and the second would have been to use several different shells or languages, each efficiently representing a specific type of knowledge. Neither of these solutions was applicable in this case. From this experience, we learned that performance, portability, and modifiability were three major requirements for genetic expert systems. To achieve these goals, we implemented the gene mapping expert system GMES: (GMES is unrelated to the gene mapping system, GMS in Lisp combined with a frame/object shell (FROBS). We were able to efficiently represent, control, and optimize a gene mapping experiment, achieving portability by building GMES on top of a C-based version of Common Lisp. Lisp combined with the FROBS expert system shell permitted a declarative representation of each of the components of the experiment, resulting in a transplant specification of the problem within a maintainable system.

Algorithms↗
PubMed2006

Recovering 3D human pose from monocular images.

We describe a learning-based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor prior labeling of body parts in the image. Instead, it recovers pose by direct nonlinear regression against shape descriptor vectors extracted automatically from image silhouettes. For robustness against local silhouette segmentation errors, silhouette shape is encoded by histogram-of-shape-contexts descriptors. We evaluate several different regression methods: ridge regression, Relevance Vector Machine (RVM) regression, and Support Vector Machine (SVM) regression over both linear and kernel bases. The RVMs provide much sparser regressors without compromising performance, and kernel bases give a small but worthwhile improvement in performance. The loss of depth and limb labeling information often makes the recovery of 3D pose from single silhouettes ambiguous. To handle this, the method is embedded in a novel regressive tracking framework, using dynamics from the previous state estimate together with a learned regression value to disambiguate the pose. We show that the resulting system tracks long sequences stably. For realism and good generalization over a wide range of viewpoints, we train the regressors on images resynthesized from real human motion capture data. The method is demonstrated for several representations of full body pose, both quantitatively on independent but similar test data and qualitatively on real image sequences. Mean angular errors of 4-6 degrees are obtained for a variety of walking motions.

Algorithms↗
PubMed2003

Learning to control a brain-machine interface for reaching and grasping by primates.

Reaching and grasping in primates depend on the coordination of neural activity in large frontoparietal ensembles. Here we demonstrate that primates can learn to reach and grasp virtual objects by controlling a robot arm through a closed-loop brain-machine interface (BMIc) that uses multiple mathematical models to extract several motor parameters (i.e., hand position, velocity, gripping force, and the EMGs of multiple arm muscles) from the electrical activity of frontoparietal neuronal ensembles. As single neurons typically contribute to the encoding of several motor parameters, we observed that high BMIc accuracy required recording from large neuronal ensembles. Continuous BMIc operation by monkeys led to significant improvements in both model predictions and behavioral performance. Using visual feedback, monkeys succeeded in producing robot reach-and-grasp movements even when their arms did not move. Learning to operate the BMIc was paralleled by functional reorganization in multiple cortical areas, suggesting that the dynamic properties of the BMIc were incorporated into motor and sensory cortical representations.

Animals↗
PubMed2025

Efficient detection and characterization of targets of natural selection using transfer learning.

Natural selection leaves detectable patterns of altered spatial diversity within genomes, and identifying affected regions is crucial for understanding species evolution. Recently, machine learning approaches applied to raw population genomic data have been developed to uncover these adaptive signatures. Convolutional neural networks (CNNs) are particularly effective for this task, as they handle large data arrays while maintaining element correlations. However, shallow CNNs may miss complex patterns due to their limited capacity, while deep CNNs can capture these patterns but require extensive data and computational power. Transfer learning addresses these challenges by utilizing a deep CNN pre-trained on a large dataset as a feature extraction tool for downstream classification and evolutionary parameter prediction. This approach reduces extensive training data generation requirements and computational needs while maintaining high performance. In this study, we developed TrIdent, a tool that uses transfer learning to enhance detection of adaptive genomic regions from image representations of multilocus variation. We evaluated TrIdent across various genetic, demographic, and adaptive settings, in addition to unphased data and other confounding factors. TrIdent demonstrated improved detection of adaptive regions compared to recent methods using similar data representations. We further explored model interpretability through class activation maps and adapted TrIdent to infer selection parameters for identified adaptive candidates. Using whole-genome haplotype data from European and African populations, TrIdent effectively recapitulated known sweep candidates and identified novel cancer, and other disease-associated genes as potential sweeps.

Journal Article↗
PubMed1993

Likelihood linkage analysis (LLA) classification method: an example treated by hand.

This paper describes a very general method of data analysis using a hierarchical classification. The data can be provided by observation, experiment or knowledge; their nature can be numerical, qualitative or logical. First, the classical view of the context of data representation, in which the algorithm of hierarchical ascendant construction of the classification tree is set, is treated in a synthetic manner. The main notion in our method is one of 'similarity'. This must be elaborated in the best way, taking into account the mathematical nature of the objects to be compared. Here we adopt a set of theoretical and combinatorial representation of the descriptive attributes, which are interpreted in terms of relations. Then we introduce a probability scale for similarity measurement by using a likelihood concept. The largest part of the paper concerns an illustrating example, moderately sized, detailing very minutely the different steps and the different calculations assumed by the method. The data structure handled with this example is the simplest possible. Then, general aspects and methodological extensions are evoked. We end by indicating the interest of the described approach in future works, in which we are involved, concerning typological organization of genetic sequences. We emphasize the 'explanation' aspect of the obtained results, with respect to a given description. For this purpose, classifications (on the object set and on the attribute set) on the one hand and machine learning techniques on the other, intervene efficiently.

Algorithms↗
PubMed1986

Representation and semiautomatic acquisition of medical knowledge in CADIAG-1 and CADIAG-2.

CADIAG-1 and CADIAG-2 (Computer-Assisted DIAGnosis) are medical expert systems especially designed for ill-defined areas such as internal medicine. Both systems are being tested in the setting of a medical information system. With respect to their knowledge representation, CADIAG-1 has obvious advantages in totally ill-defined areas such as syndromes in internal medicine, whereas CADIAG-2 seems more suited for domains with basic laboratory programs, e.g., hepatology or gall bladder and bile duct diseases. The formalization of relationships between medical entities led to first-order predicate calculus formulas in the case of CADIAG-1 and to a model based on fuzzy set theory in the case of CADIAG-2. In both systems two kinds of relationships between medical entities are considered: (1) necessity of occurrence and (2) sufficiency of occurrence. Statistical interpretations using the 2 X 2 table paradigm yield a way to calculate these relationships automatically from samples of patient data. Results obtained by exploiting 3530 patient records from a rheumatological hospital are presented. The described application is a machine-learning program that allows inductive learning from examples under statistical uncertainty.

Artificial Intelligence↗
PubMed2005

Graph kernels for chemical informatics.

Increased availability of large repositories of chemical compounds is creating new challenges and opportunities for the application of machine learning methods to problems in computational chemistry and chemical informatics. Because chemical compounds are often represented by the graph of their covalent bonds, machine learning methods in this domain must be capable of processing graphical structures with variable size. Here, we first briefly review the literature on graph kernels and then introduce three new kernels (Tanimoto, MinMax, Hybrid) based on the idea of molecular fingerprints and counting labeled paths of depth up to d using depth-first search from each possible vertex. The kernels are applied to three classification problems to predict mutagenicity, toxicity, and anti-cancer activity on three publicly available data sets. The kernels achieve performances at least comparable, and most often superior, to those previously reported in the literature reaching accuracies of 91.5% on the Mutag dataset, 65-67% on the PTC (Predictive Toxicology Challenge) dataset, and 72% on the NCI (National Cancer Institute) dataset. Properties and tradeoffs of these kernels, as well as other proposed kernels that leverage 1D or 3D representations of molecules, are briefly discussed.

Anticarcinogenic Agents↗
PubMed2025

Knowledge-enhanced protein subcellular localization prediction from 3D fluorescence microscope images.

MOTIVATION: Pinpointing the subcellular location of proteins is essential for studying protein function and related diseases. Advances in spatial proteomics have shown that automatic recognition of protein subcellular localization from images could highly facilitate protein translocation analysis and biomarker discovery, but existing machine-learning works have been mostly limited to processing 2D images. By contrast, 3D images have higher spatial resolution and allow researchers to observe cellular structures in their natural context, but currently, there are only a few studies of 3D image processing for protein distribution analysis due to the lack of data and complexity of modeling. RESULTS: We developed a knowledge-enhanced protein subcellular localization model, KE3DLoc, which could recognize distribution patterns in 3D fluorescence microscope images using deep learning methods. The model designs an image feature extraction module that incorporates information from 3D and 2D projected cells and implements asymmetric loss and confidence weights to address data imbalance and weak cell annotation issues. Besides, considering that the biological knowledge in the Gene Ontology (GO) database can provide valuable support for protein location understanding, the KE3DLoc model incorporates a novel knowledge enhancement module that optimizes the protein representation by related knowledge graphs derived from the GO. Since the image module and the knowledge module calculate features from different levels, KE3DLoc designs protein ID aggregation to enhance the consistency of protein features across different cells. Experimental results on three public datasets have demonstrated that the KE3DLoc significantly outperforms existing methods and provides valuable insights for spatial proteomics research. AVAILABILITY AND IMPLEMENTATION: All datasets and codes used in this study are available at GitHub: https://github.com/PRBioimages/KE3DLoc.

Microscopy, Fluorescence↗
PubMed2026

HXMS: a standardized file format for HX-MS data.

MOTIVATION: Hydrogen/deuterium exchange-mass spectrometry (HX-MS) is a rapidly expanding technique used to investigate protein conformational ensembles. The growing popularity and utility of HX-MS has driven the development of diverse instrumentation and software, resulting in inconsistent, non-standardized data analysis and representation. Most HX-MS data formats also employ only mean deuteration representations of the data rather than full isotopic mass spectra, which reduces the information content of the data and limits downstream quantitative analysis. RESULTS: Inspired by reliable protein structure and genomics data formats, we present HXMS, a unified, lightweight, scalable, and human-readable file format for HX-MS data. The HXMS format preserves the isotopic mass envelopes for all peptides, captures the full experimental time-course including fully deuterated control samples, and contains all other key information. It supports multimodal distributions, post-translational modifications (PTMs), and experimental replicates. To promote compatibility with existing HX-MS workflows, we also developed PFLink, a Python package that converts exported data files from commonly used HX-MS software to the HXMS format. PFLink and the HXMS format will enable quantitative, higher-resolution data processing, improved data sharing and storage among HX-MS practitioners, future machine learning applications, and further developments in HX-MS analysis. AVAILABILITY AND IMPLEMENTATION: PFLink is publicly available to install locally on HuggingFace, alongside documentation, or use online at HuggingFace (https://huggingface.co/spaces/glasgow-lab/PFlink). The supplementary information includes sample input files, sample HXMS files, and a generic unfilled PFlink custom CSV file that users may populate with key experimental conditions and results, which can then be read and converted into the HXMS format.

Software↗
PubMed1995

Information, intelligence, and interface: the pillars of a successful medical information system.

This paper addresses three key issues facing developers of clinical and/or research medical information systems. 1. INFORMATION. The basic function of every database is to store information about the phenomenon under investigation. There are many ways to organize information in a computer; however only a few will prove optimal for any real life situation. Computer Science theory has developed several approaches to database structure, with relational theory leading in popularity among end users [8]. Strict conformance to the rules of relational database design rewards the user with consistent data and flexible access to that data. A properly defined database structure minimizes redundancy i.e.,multiple storage of the same information. Redundancy introduces problems when updating a database, since the repeated value has to be updated in all locations--missing even a single value corrupts the whole database, and incorrect reports are produced [8]. To avoid such problems, relational theory offers a formal mechanism for determining the number and content of data files. These files not only preserve the conceptual schema of the application domain, but allow a virtually unlimited number of reports to be efficiently generated. 2. INTELLIGENCE. Flexible access enables the user to harvest additional value from collected data. This value is usually gained via reports defined at the time of database design. Although these reports are indispensable, with proper tools more information can be extracted from the database. For example, machine learning, a sub-discipline of artificial intelligence, has been successfully used to extract knowledge from databases of varying size by uncovering a correlation among fields and records[1-6, 9]. This knowledge, represented in the form of decision trees, production rules, and probabilistic networks, clearly adds a flavor of intelligence to the data collection and manipulation system. 3. INTERFACE. Despite the obvious importance of collecting data and extracting knowledge, current systems often impede these processes. Problems stem from the lack of user friendliness and functionality. To overcome these problems, several features of a successful human-computer interface have been identified [7], including the following "golden" rules of dialog design [7]: consistency, use of shortcuts for frequent users, informative feedback, organized sequence of actions, simple error handling, easy reversal of actions, user-oriented focus of control, and reduced short-term memory load. To this list of rules, we added visual representation of both data and query results, since our experience has demonstrated that users react much more positively to visual rather than textual information. In our design of the Orthopaedic Trauma Registry--under development at the Carolinas Medical Center--we have made every effort to follow the above rules. The results were rewarding--the end users actually not only want to use the product, but also to participate in its development.

Artificial Intelligence↗
PubMed2002

Scalable hybrid computation with spikes.

We outline a hybrid analog-digital scheme for computing with three important features that enable it to scale to systems of large complexity: First, like digital computation, which uses several one-bit precise logical units to collectively compute a precise answer to a computation, the hybrid scheme uses several moderate-precision analog units to collectively compute a precise answer to a computation. Second, frequent discrete signal restoration of the analog information prevents analog noise and offset from degrading the computation. And, third, a state machine enables complex computations to be created using a sequence of elementary computations. A natural choice for implementing this hybrid scheme is one based on spikes because spike-count codes are digital, while spike-time codes are analog. We illustrate how spikes afford easy ways to implement all three components of scalable hybrid computation. First, as an important example of distributed analog computation, we show how spikes can create a distributed modular representation of an analog number by implementing digital carry interactions between spiking analog neurons. Second, we show how signal restoration may be performed by recursive spike-count quantization of spike-time codes. And, third, we use spikes from an analog dynamical system to trigger state transitions in a digital dynamical system, which reconfigures the analog dynamical system using a binary control vector; such feedback interactions between analog and digital dynamical systems create a hybrid state machine (HSM). The HSM extends and expands the concept of a digital finite-state-machine to the hybrid domain. We present experimental data from a two-neuron HSM on a chip that implements error-correcting analog-to-digital conversion with the concurrent use of spike-time and spike-count codes. We also present experimental data from silicon circuits that implement HSM-based pattern recognition using spike-time synchrony. We outline how HSMs may be used to perform learning, vector quantization, spike pattern recognition and generation, and how they may be reconfigured.

Action Potentials↗
PubMed2006

Will my protein crystallize? A sequence-based predictor.

We propose a machine-learning approach to sequence-based prediction of protein crystallizability in which we exploit subtle differences between proteins whose structures were solved by X-ray analysis [or by both X-ray and nuclear magnetic resonance (NMR) spectroscopy] and those proteins whose structures were solved by NMR spectroscopy alone. Because the NMR technique is usually applied on relatively small proteins, sequence length distributions of the X-ray and NMR datasets were adjusted to avoid predictions biased by protein size. As feature space for classification, we used frequencies of mono-, di-, and tripeptides represented by the original 20-letter amino acid alphabet as well as by several reduced alphabets in which amino acids were grouped by their physicochemical and structural properties. The classification algorithm was constructed as a two-layered structure in which the output of primary support vector machine classifiers operating on peptide frequencies was combined by a second-level Naive Bayes classifier. Due to the application of metamethods for cost sensitivity, our method is able to handle real datasets with unbalanced class representation. An overall prediction accuracy of 67% [65% on the positive (crystallizable) and 69% on the negative (noncrystallizable) class] was achieved in a 10-fold cross-validation experiment, indicating that the proposed algorithm may be a valuable tool for more efficient target selection in structural genomics. A Web server for protein crystallizability prediction called SECRET is available at http://webclu.bio.wzw.tum.de:8080/secret.

Amino Acid Sequence↗
PubMed2004

Does computation provide a model for creativity? An epistemological perspective in neuroscience.

In 1939 Alan Turing, a major scholar in the field of mechanical computation, described a system whose computational power was beyond that of a discrete, finite state machine (Turing Machine). The composition of this system was likely the first example of what is now called an hybrid computational system. Since then, development of neural networks and brain automata has made aware that forms of computation might exist that are likely to go beyond Turing's limits. Natural systems, like the central nervous system in Mammals and man, are likely to use such a type of computation, especially to perform highly integrating activities, like feedback controls and mental creative processes. The latter are usually understood as processes that involve infinitary procedures, ending up in a complex information network, the computational maps, in which both digital, Turing-like computation and continuous, analog forms of calculus are expected to occur. Pictorial representation may be a fruitful example, mostly metaphorical, to analyze the use of this hybrid forms of computation by higher order computational maps, and the possible role of these types of computational processes in painting creativity is briefly analyzed in comparing 15th vs 16th century Renaissance Art. An open challenge for neuroscience in the 21st century is to clarify whether a hybrid neural learning network might represent a reasonable clue to scientifically interpret the theme of "creativity".

Art↗