Proceedings. International Conference on Intelligent Systems for Molecular Biology最新文献

In this paper we present a method for classifying proteins into families using sparse Markov transducers (SMTs). Sparse Markov transducers, similar to probabilistic suffix trees, estimate a probability distribution conditioned on an input sequence. SMTs generalize probabilistic suffix trees by allowing for wild-cards in the conditioning sequences. Because substitutions of amino acids are common in protein families, incorporating wildcards into the model significantly improves classification performance. We present two models for building protein family classifiers using SMTs. We also present efficient data structures to improve the memory usage of the models. We evaluate SMTs by building protein family classifiers using the Pfam database and compare our results to previously published results.

The next phase of human genomics will involve large-scale screens of populations for significant DNA polymorphisms, notably single nucleotide polymorphisms (SNP's). Dense human SNP maps are currently under construction. However, the utility of those maps and screens will be limited by the fact that humans are diploid, and that it is presently difficult to get separate data on the two "copies". Hence genotype (blended) SNP data will be collected, and the desired haplotype (partitioned) data must then be (partially) inferred. A particular non-deterministic inference algorithm was proposed and studied before SNP data was available, and extensively applied more recently to study the first available SNP data. In this paper, we consider the question of whether we can obtain an efficient, deterministic variant of that method to optimize the obtained inferences. Although we have shown elsewhere that the optimization problem is NP-hard, we present here a practical approach based on (integer) linear programming. The method either returns the optimal answer, and a declaration that it is the optimal, or declares that it has failed to find the optimal. The approach works quickly and correctly, finding the optimal on all simulated data tested, data that is expected to be more demanding than realistic biological data.

We present in this paper a pragmatic strategy to perform information extraction from biologic texts. Since the emergence of the information extraction field, techniques have evolved, become more robust and proved their efficiency on specific domains. We are using a combination of existing linguistic and knowledge processing tools to automatically extract information about gene interactions in the literature. Our ultimate goal is to build a network of gene interactions. The methodologies used and the current results are discussed in this paper.

We describe a new algorithm for amino acid sequence classification and the detection of remote homologues. The rationale is to exploit both vertical and horizontal information of a multiple alignment in a well balanced manner. This is in contrast to established methods like profiles and hidden Markov models which focus on vertical information as they model the columns of the alignment independently. In our setting, we want to select from a given database of "candidate sequences" those proteins that belong to a given superfamily. In order to do so, each candidate sequence is separately tested against a multiple alignment of the known members of the superfamily by means of a new jumping alignment algorithm. This algorithm is an extension of the Smith-Waterman algorithm and computes a local alignment of a single sequence and a multiple alignment. In contrast to traditional methods, however, this alignment is not based on a summary of the individual columns of the multiple alignment. Rather, the candidate sequence at each position is aligned to one sequence of the multiple alignment, called the "reference sequence". In addition, the reference sequence may change within the alignment, while each such jump is penalized. To evaluate the discriminative quality of the jumping alignment algorithm, we compared it to hidden Markov models on a subset of the SCOP database of protein domains. The discriminative quality was assessed by counting the number of false positives that ranked higher than the first true positive (FP-count). For moderate FP-counts above five, the number of successful searches with our method was considerably higher than with hidden Markov models.

A recent, popular method of finding promoter sequences is to look for conserved motifs upstream of genes clustered on the basis of expression data. This method presupposes that the clustering is correct. Theoretically, one should be better able to find promoter sequences and create more relevant gene clusters by taking a unified approach to these two problems. We present a likelihood function for a "sequence-expression" model giving a joint likelihood for a promoter sequence and its corresponding expression levels. An algorithm to estimate sequence-expression model parameters using Gibbs sampling and Expectation/Maximization is described. A program, called kimono, that implements this algorithm has been developed: the source code is freely available on the Internet.

A new approach to gene finding is introduced called the "Conserved Exon Method" (CEM). It is based on the idea of looking for conserved protein sequences by comparing pairs of DNA sequences, identifying putative exon pairs based on conserved regions and splice junction signals then chaining pairs of putative exons together. It simultaneously predicts gene structures in both human and mouse genomic sequences (or in other pairs of sequences at the appropriate evolutionary distance). Experimental results indicate the potential usefulness of this approach.

We present a computational approach to predicting operons in the genomes of prokaryotic organisms. Our approach uses machine learning methods to induce predictive models for this task from a rich variety of data types including sequence data, gene expression data, and functional annotations associated with genes. We use multiple learned models that individually predict promoters, terminators and operons themselves. A key part of our approach is a dynamic programming method that uses our predictions to map every known and putative gene in a given genome into its most probable operon. We evaluate our approach using data from the E. coli K-12 genome.

The availability of genome-wide mRNA expression data for organisms whose genome is fully sequenced provides a unique data set from which to decipher how transcription is regulated by the upstream control region of a gene. A new algorithm is presented which decomposes DNA sequence into the most probable "dictionary" of motifs or words. Identification of words is based on a probabilistic segmentation model in which the significance of longer words is deduced from the frequency of shorter words of various length. This eliminates the need for a separate set of reference data to define probabilities, and genome-wide applications are therefore possible. For the 6,000 upstream regulatory regions in the yeast genome, the 500 strongest motifs from a dictionary of size 1,200 match at a significance level of 15 standard deviations to a database of cis-regulatory elements. Analysis of sets of genes such as those up-regulated during sporulation reveals many new putative regulatory sites in addition to identifying previously known sites.