AlexSys: a knowledge-based expert system for multiple sequence alignment construction and analysis

Multiple sequence alignment (MSA) is a cornerstone of modern molecular biology and represents a unique means of investigating the patterns of conservation and diversity in complex biological systems. Many different algorithms have been developed to construct MSAs, but previous studies have shown that no single aligner consistently outperforms the rest. This has led to the development of a number of ‘meta-methods’ that systematically run several aligners and merge the output into one single solution. Although these methods generally produce more accurate alignments, they are inefficient because all the aligners need to be run first and the choice of the best solution is made a posteriori. Here, we describe the development of a new expert system, AlexSys, for the multiple alignment of protein sequences. AlexSys incorporates an intelligent inference engine to automatically select an appropriate aligner a priori, depending only on the nature of the input sequences. The inference engine was trained on a large set of reference multiple alignments, using a novel machine learning approach. Applying AlexSys to a test set of 178 alignments, we show that the expert system represents a good compromise between alignment quality and running time, making it suitable for high throughput projects. AlexSys is freely available from http://alnitak.u-strasbg.fr/∼aniba/alexsys.     

An expert system applied to the physiological analysis of early stage of beer fermentation

A fuzzy expert system was applied to the knowledge analysis of yeast physiology in the early stage of beer fermentation, when the wort was aerated. We used ergosterol and glycogen concentration in the wort as a suitable marker of physiological state of the cell population. The amount of both compounds influences the rate of fermentation, cell growth and the final taste of beer. The concentrations of ergosterol and glycogen including the number of cells can not be measured immediately during the relatively short aeration period, and incomplete experimental data are therefore found in laboratory logbooks. We therefore suggested that the fuzzy relation between the directly measurable dissolved oxygen concentration and the rate of ergosterol or glycogen formation should be identified and a fuzzy expert system should be used to analyze the behavior of the yeast.     

The PARTICLE expert system for tumor grading by automated image analysis

While automated microscopic image analysis of histologic sections has been helpful in objectivizing histologic tumor grading and investigating the relationships between grading and prognosis, expert systems have the potential of linking image analysis and other data for statistical analysis and application to a wider range of tumors. One such expert system is PARTICLE, whose development was based on many years of experience in resolving histologic problems by image analysis. This paper discusses the philosophy of expert system for tumor grading and describes its implementation in the PARTICLE system. The system's structure, operations and applications are briefly presented. PARTICLE is essentially based on the evaluation of karyometric data.     

An image analysis system for cervical cytology automation using nuclear DNA content.

An experimental computer/image analysis system has been used to investigate cytology automation techniques based on nuclear DNA measurement and morphological artefact rejector tests. The system automatically measures and normalizes the integrated optical density of cell nuclei in specially prepared cervical cytology specimens, and selects any objects with abnormally high values for further analysis. These are then analyzed by morphological and densitometric tests designed to eliminate false positive signals caused by non-nuclear artefacts. The coordinates of the remaining abnormal nuclei are recorded so that they can subsequently be relocated and examined by a cytotechnician. Preliminary results are given showing the measurement accuracy of the system and the performance of the artefact rejection tests.     

An automatic image analysis system for RLGS films

The RLGS (Restriction Landmark Genome Scanning) method was originally developed as a powerful method for enabling viewing of thousands of restriction landmarks. It offers a tool for obtaining information about genetic loci, with a single RLGS profile displaying approximately 2000 restriction landmarks as spots. One of the most useful applications is RLGS spot mapping, which allows the efficient, low-cost construction of the genetic map of any organism. However, analyses of the profiles depend mainly on human visual observation and are tedious and laborious. Although several commercially available image analyzing systems for profile comparison have been examined, they cannot be used for the RLGS spot mapping system owing to the background characteristics of the RLGS profiles, unsatisfactory rates of correspondence, and inefficient correction of informative genetic data. We therefore developed a novel automatic image analysis system for RLGS spot mapping, using an original algorithm based on the binary image transferred from the original RLGS profile. This system was employed for identifying non-polymorphic and parental strain-specific polymorphic spots of the F₁ mouse profile and yielded efficient initial screening of RLGS profiles. Received: 5 December 1997 / Accepted: 6 April 1998     

A digital image microscopy system for rare-event detection using fluorescent probes

Instrumentation for rare-event analysis should be capable of reliably detecting infrequent cells (less than 1:10,000) while both excluding false-positive signals and including true positive cells found in multicell clumps. We have developed a digital image microscopy (DIM) system in which a cytospin of 2 million cells is scanned with an intensified video camera (ISIT) using an IBM PC AT microcomputer-controlled microscope stage. PASCAL software controls the stage and analyzes video input, storing the location of positive cells to magnetic disk. The user can then "replay" each positive cell under computer control for either visual confirmation or analysis using other fluorescent probes. The computer requires 24 min to scan a cytoprep of 2 million cells, while playback for visual confirmation by the user averages 5 min. Using Hoechst-33342 premarked cells seeded into bone marrow as a model system, we found that the DIM system reliably detects one target cell per million marrow cells. With appropriate immunological markers, this system will aid in evaluating bone marrow purged of tumor cells prior to transplantation and should also be useful for detection of minimal residual disease in blood or bone marrow from patients with leukemia or solid tumors.     

An application of an expert system to potentiometric stripping analysis

In this paper, a potentiometric stripping analysis (PSA) system controlled by an expert system, designed and constructed by us, is examined for the analysis of cadmium, lead and copper. PSA has gained a place in trace metal analysis, with many applications of this technique reported in the past decade. The simpler equipment required and lack of organic interference have made this technique an alternative method to the well established anodic stripping voltammetric (ASV) procedure. The expert system not only provides direct equipment control but also interprets the results based on its knowledge base and provides adjustments of the experimental parameters to optimize the analysis. The selected expert system builder, Crystal, is an extremely simple programming environment, the instruction being almost in the form of standard English. This allows the user to build up a knowledge base without the need for great computing skill.     

A rapid identification system for metallothionein proteins using expert system

Metallothioneins (MT) are low molecular weight proteins mostly rich in cysteine residues with high metal content. Generally, MT proteins are responsible for regulating the intracellular supply of biologically essential metal ions and they protect cells from the deleterious effects of non-essential polarizable transition and post-transition metal ions. Due to their biological importance, proper characterization of MT is necessary. Here we describe a computer program (ID3 algorithm, a part of Artificial Intelligence) developed using available data for the rapid identification of MT. Tissue samples contains several low molecular weight proteins with different physical, chemical and biological characteristics. The described software solution proposes to categorize MT proteins without aromatic amino acids and high metal content. The proposed solution can be expanded to other types of proteins with specific known characteristics.     

An expert system for interpretation of X-ray fluorescence spectra

The complexity of X-ray fluorescence (XRF) spectra has lead to a number of computerised interpretation and element identification systems being developed and reported in the literature. In practice, however, human operators can generally perform the task better. The system outlined here uses a strategy based upon the recorded experience of experts, and employs an expert system with fuzzy logic to analyse and interpret XRF spectra. The aim has been to develop and implement a heuristically based scheme able to perform XRF qualitative analysis efficiently and effectively. Future developments and improvements to the system are discussed.     

Morphometric requirements for image analysis and the IBAS interactive automatic image analysis system

The morphometric demands made on an image analysis system are discussed, as is the IBAS interactive automatic system, which meets those requirements. The modular design of the IBAS image analysis system, with its tailor-made processors for image processing, system control and pattern recognition, gives speed and flexibility. The IMAGE image analysis language guarantees user friendliness, and, last but not least, the enormous amount of software offers accurate, reproducible measurements and dedicated evaluation programs.     

CASSIOPE: An expert system for conserved regions searches

Background  

Understanding genome evolution provides insight into biological mechanisms. For many years comparative genomics and analysis of conserved chromosomal regions have helped to unravel the mechanisms involved in genome evolution and their implications for the study of biological systems. Detection of conserved regions (descending from a common ancestor) not only helps clarify genome evolution but also makes it possible to identify quantitative trait loci (QTLs) and investigate gene function.     

Quantitative ultrastructural immunocytochemistry using a computerized image analysis system

Secretory granules in human pituitary adenoma cells have been examined indirectly for hormone epitopes by immunogold labelling of resin-embedded ultrathin sections. The specific binding of different immunoglobulin-gold complexes to the antigrowth hormone antibodies over the secretory granules was measured using a computerized image analysis system. This facilitated the assessment of the preferential binding to the target granules of gold particles with three different average particle diameters (Au7, Au11, Au17). The time of pretreatment of sections with H2O2 or a buffer was found to influence the staining considerably. The scanning electron microscopic findings of protruded secretory granules with a mountain-like surface might be relevant to the uneven distribution of immunolabels seen over the secretory granules in the adenohypophysis.     

An automated system for detection and analysis of locomotor behavior in crustaceans

An efficient and simple system is presented for the analysis of crustacean locomotor behavior. The system is composed by six dual-compartment actographic chambers with photocoupling circuits for movement detection, and a device for acquisition and analysis of data. Such device is made by a digital interface which feeds into a microcomputer with disc unit and printer. Information is processed in real time during the experiment, with a simultaneous printout and storage in a floppy disc.     

Mobile image sensors for object detection using color segmentation

The intelligent mobile robot with sensors and image processing embedded system combines the suction and aerodynamic attraction to achieve good balance between strong adhesion force and high mobility. Experimental results showed that the robot can move upward on the wall at the speed of 2.9 m/min and carry 5 kg payload in addition to 2.5 kg self-weight, which record the highest payload capacity among climbing robots of similar size. It also implements object detection ability using effective color transform and segmentation technique for the exact target detection on the wall using a embedded camera system, communication module and several active sensors.     

An expert system for diagnosis of coronary artery stenosis based on 201TI scintigrams using the Dempster-Shafer theory of evidence

An expert system for the diagnosis of stenoses in the threemain coronary arteries (left anterior descending, right coronaryartery and circumflex) is described. First, the knowledge basedomain—²⁰¹Tl scintigrams-is explained and the method ofpreprocessing the original heart images is given. Next, themethod of dealing with the uncertainties present both in thecardiologist-specified rules and the data using the Dempster-Shafertheory of evidence is explained. Finally, the constructed expertsystem and the results are discussed and several graphical examplesare shown. Received on December 15, 1989; accepted on April 15, 1990