Biomedical subjects

J W Shavlik

Publications and source records attributed to J W Shavlik.

6 recordsLinked to original sources

PubMed2002

Evaluating machine learning approaches for aiding probe selection for gene-expression arrays.

MOTIVATION: Microarrays are a fast and cost-effective method of performing thousands of DNA hybridization experiments simultaneously. DNA probes are typically used to measure the expression level of specific genes. Because probes greatly vary in the quality of their hybridizations, choosing good probes is a difficult task. If one could accurately choose probes that are likely to hybridize well, then fewer probes would be needed to represent each gene in a gene-expression microarray, and, hence, more genes could be placed on an array of a given physical size. Our goal is to empirically evaluate how successfully three standard machine-learning algorithms-naïve Bayes, decision trees, and artificial neural networks-can be applied to the task of predicting good probes. Fortunately it is relatively easy to get training examples for such a learning task: place various probes on a gene chip, add a sample where the corresponding genes are highly expressed, and then record how well each probe measures the presence of its corresponding gene. With such training examples, it is possible that an accurate predictor of probe quality can be learned. RESULTS: Two of the learning algorithms we investigate-naïve Bayes and neural networks-learn to predict probe quality surprisingly well. For example, in the top ten predicted probes for a given gene not used for training, on average about five rank in the top 2.5% of that gene's hundreds of possible probes. Decision-tree induction and the simple approach of using predicted melting temperature to rank probes perform significantly worse than these two algorithms. The features we use to represent probes are very easily computed and the time taken to score each candidate probe after training is minor. Training the naïve Bayes algorithm takes very little time, and while it takes over 10 times as long to train a neural network, that time is still not very substantial (on the order of a few hours on a desktop workstation). We also report the information contained in the features we use to describe the probes. We find the fraction of cytosine in the probe to be the most informative feature. We also find, not surprisingly, that the nucleotides in the middle of the probes sequence are more informative than those at the ends of the sequence.

Algorithms↗

PubMed1999

Neural network input representations that produce accurate consensus sequences from DNA fragment assemblies.

MOTIVATION: Given inputs extracted from an aligned column of DNA bases and the underlying Perkin Elmer Applied Biosystems (ABI) fluorescent traces, our goal is to train a neural network to determine correctly the consensus base for the column. Choosing an appropriate network input representation is critical to success in this task. We empirically compare five representations; one uses only base calls and the others include trace information. RESULTS: We attained the most accurate results from networks that incorporate trace information into their input representations. Based on estimates derived from using 10-fold cross-validation, the best network topology produces consensus accuracies ranging from 99.26% to >99.98% for coverages from two to six aligned sequences. With a coverage of six, it makes only three errors in 20 000 consensus calls. In contrast, the network that only uses base calls in its input representation has over double that error rate: eight errors in 20 000 consensus calls. CONTACT: allex@cs.wisc.edu

Base Sequence↗

PubMed1997

Understanding time series networks: a case study in rule extraction.

A significant limitation of neural networks is that the representations they learn are usually incomprehensible to humans. We have developed an algorithm, called TREPAN, for extracting comprehensible, symbolic representations from trained neural networks. Given a trained network, TREPAN produces a decision tree that approximates the concept represented by the network. In this article, we discuss the application of TREPAN to a neural network trained on a noisy time series task: predicting the Dollar-Mark exchange rate. We present experiments that show that TREPAN is able to extract a decision tree from this network that equals the network in terms of predictive accuracy, yet provides a comprehensible concept representation. Moreover, our experiments indicate that decision trees induced directly from the training data using conventional algorithms do not match the accuracy nor the comprehensibility of the tree extracted by TREPAN.

Artificial Intelligence↗

PubMed1997

Increasing consensus accuracy in DNA fragment assemblies by incorporating fluorescent trace representations.

We present a new method for determining the consensus sequence in DNA fragment assemblies. The new method, Trace-Evidence, directly incorporates aligned ABI trace information into consensus calculations via our previously described representation, Trace-Data Classifications. The new method extracts and sums evidence indicated by the representation to determine consensus calls. Using the Trace-Evidence method results in automatically produced consensus sequences that are more accurate and less ambiguous than those produced with standard majority-voting methods. Additionally, these improvements are achieved with less coverage than required by the standard methods-using Trace-Evidence and a coverage of only three, error rates are as low as those with a coverage of over ten sequences.

Algorithms↗

PubMed1996

Improving the quality of automatic DNA sequence assembly using fluorescent trace-data classifications.

Virtually all large-scale sequencing projects use automatic sequence-assembly programs to aid in the determination of DNA sequences. The computer-generated assemblies required substantial hand-editing to transform them into submissions for GenBank. As the size of sequencing projects increases, it becomes essential to improve the quality of the automated assemblies so that this time consuming hand-editing may be reduced. Current ABI sequencing technology uses base calls made from fluorescently-labeled DNA fragments run on gels. We present a new representation for the fluorescent trace data associated with individual base calls. This representation can be used before, during, and after fragment assembly to improve the quality of assemblies. We demonstrate one such use-end-trimming of sub-optimal data-that results in a significant improvement in the quality of subsequent assemblies.

Algorithms↗

PubMed1993

Protein structure prediction: selecting salient features from large candidate pools.

We introduce a parallel approach, "DT-SELECT," for selecting features used by inductive learning algorithms to predict protein secondary structure. DT-SELECT is able to rapidly choose small, nonredundant feature sets from pools containing hundreds of thousands of potentially useful features. It does this by building a decision tree, using features from the pool, that classifies a set of training examples. The features included in the tree provide a compact description of the training data and are thus suitable for use as inputs to other inductive learning algorithms. Empirical experiments in the protein secondary-structure task, in which sets of complex features chosen by DT-SELECT are used to augment a standard artificial neural network representation, yield surprisingly little performance gain, even though features are selected from very large feature pools. We discuss some possible reasons for this result.

Algorithms↗