The applicability of recurrent neural networks for biological sequence analysis

Selection of machine learning techniques requires a certain sensitivity to the requirements of the problem. In particular, the problem can be made more tractable by deliberately using algorithms that are biased toward solutions of the requisite kind. In this paper, we argue that recurrent neural networks have a natural bias toward a problem domain of which biological sequence analysis tasks are a subset. We use experiments with synthetic data to illustrate this bias. We then demonstrate that this bias can be exploitable using a data set of protein sequences containing several classes of subcellular localization targeting peptides. The results show that, compared with feed forward, recurrent neural networks will generally perform better on sequence analysis tasks. Furthermore, as the patterns within the sequence become more ambiguous, the choice of specific recurrent architecture becomes more critical.

A First Order Predicate Logic Formulation of the 3D Reconstruction Problem and its Solution Space

This paper defines the 3D reconstruction problem as the process of reconstructing a 3D scene from numerous 2D visual images of that scene. It is well known that this problem is ill-posed, and numerous constraints and assumptions are used in 3D reconstruction algorithms in order to reduce the solution space. Unfortunately, most constraints only work in a certain range of situations and often constraints are built into the most fundamental methods (e.g. Area Based Matching assumes that all the pixels in the window belong to the same object). This paper presents a novel formulation of the 3D reconstruction problem, using a voxel framework and first order logic equations, which does not contain any additional constraints or assumptions. Solving this formulation for a set of input images gives all the possible solutions for that set, rather than picking a solution that is deemed most likely. Using this formulation, this paper studies the problem of uniqueness in 3D reconstruction and how the solution space changes for different configurations of input images. It is found that it is not possible to guarantee a unique solution, no matter how many images are taken of the scene, their orientation or even how much color variation is in the scene itself. Results of using the formulation to reconstruct a few small voxel spaces are also presented. They show that the number of solutions is extremely large for even very small voxel spaces (5 x 5 voxel space gives 10 to 10(7) solutions). This shows the need for constraints to reduce the solution space to a reasonable size. Finally, it is noted that because of the discrete nature of the formulation, the solution space size can be easily calculated, making the formulation a useful tool to numerically evaluate the usefulness of any constraints that are added.

Off-line signature verification and forgery detection using fuzzy modeling

Automatic signature verification is a well-established and an active area of research with numerous applications such as bank check verification, ATM access, etc. This paper proposes a novel approach to the problem of automatic off-line signature verification and forgery detection. The proposed approach is based on fuzzy modeling that employs the Takagi-Sugeno (TS) model. Signature verification and forgery detection are carried out using angle features extracted from box approach. Each feature corresponds to a fuzzy set. The features are fuzzified by an exponential membership function involved in the TS model, which is modified to include structural parameters. The structural parameters are devised to take account of possible variations due to handwriting styles and to reflect moods. The membership functions constitute weights in the TS model. The optimization of the output of the TS model with respect to the structural parameters yields the solution for the parameters. We have also derived two TS models by considering a rule for each input feature in the first formulation (Multiple rules) and by considering a single rule for all input features in the second formulation. In this work, we have found that TS model with multiple rules is better than TS model with single rule for detecting three types of forgeries; random, skilled and unskilled from a large database of sample signatures in addition to verifying genuine signatures. We have also devised three approaches, viz., an innovative approach and two intuitive approaches using the TS model with multiple rules for improved performance. (C) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

Extreme learning machine for predicting HLA-peptide binding

Machine learning techniques have been recognized as powerful tools for learning from data. One of the most popular learning techniques, the Back-Propagation (BP) Artificial Neural Networks, can be used as a computer model to predict peptides binding to the Human Leukocyte Antigens (HLA). The major advantage of computational screening is that it reduces the number of wet-lab experiments that need to be performed, significantly reducing the cost and time. A recently developed method, Extreme Learning Machine (ELM), which has superior properties over BP has been investigated to accomplish such tasks. In our work, we found that the ELM is as good as, if not better than, the BP in term of time complexity, accuracy deviations across experiments, and most importantly - prevention from over-fitting for prediction of peptide binding to HLA.

Low mannose-binding lectin function is associated with sepsis in adult patients

Mannose-binding lectin (MBL) is an innate immune system pattern recognition molecule that kills a wide range of pathogens via the lectin complement pathway. MBL deficiency is associated with severe infection but the best measure of this deficiency is undecided. We investigated the influence of MBL functional deficiency on the development of sepsis in 195 adult patients, 166 of whom had bloodstream infection and 35 had pneumonia. Results were compared with 236 blood donor controls. MBL function (C4b deposition) and levels were measured by enzyme-linked immunosorbent assay. Using receiver-operator characteristics of MBL function in healthy controls, we identified a level of < 0.2 U mu L-1 as a highly discriminative marker of low MBL2 genotypes. Median MBL function was lower in sepsis patients (0.18 U mu L-1) than in controls (0.48 U mu L-1, P < 0.001). MBL functional deficiency was more common in sepsis patients than controls (P < 0.001). MBL functional deficient patients had significantly higher sequential organ failure assessment (SOFA) scores and higher MBL function and levels were found in patients with SOFA scores predictive of good outcome. Deficiency of MBL function appears to be associated with bloodstream infection and the development of septic shock. High MBL levels may be protective against severe sepsis. © 2006 Federation of European Microbiological Societies Published by Blackwell Publishing Ltd. All rights reserved.

Screening of obstructive and central apnoea/hypopnoea in children using variability: A preliminary study

Aim: Polysomnography (PSG) is the current standard protocol for sleep disordered breathing (SDB) investigation in children. Presently, there are limited reliable screening tests for both central (CE) and obstructive (OE) respiratory events. This study compared three indices, derived from pulse oximetry and electrocardiogram ( ECG), with the PSG gold standard. These indices were heart rate (HR) variability, arterial blood oxygen de-saturation (SaO(2)) and pulse transit time (PTT). Methods: 15 children (12 male) from routine PSG studies were recruited (aged 3 - 14 years). The characteristics of the three indices were based on known criteria for respiratory events (RPE). Their estimation singly and in combination was evaluated with simultaneous scored PSG recordings. Results: 215 RPE and 215 tidal breathing events were analysed. For OE, the obtained sensitivity was HR (0.703), SaO(2) (0.047), PTT (0.750), considering all three indices (0) and either of the indices (0.828) while specificity was (0.891), (0.938), (0.922), (0.953) and (0.859) respectively. For CE, the sensitivity was HR (0.715), SaO(2) (0.278), PTT (0.662), considering all indices (0.040) and either of the indices (0.868) while specificity was (0.815), (0.954), (0.901), (0.960) and (0.762) accordingly. Conclusions: Preliminary findings herein suggest that the later combination of these non-invasive indices to be a promising screening method of SDB in children.

Boosting the tree augmented naive bayes classifier

The Tree Augmented Naïve Bayes (TAN) classifier relaxes the sweeping independence assumptions of the Naïve Bayes approach by taking account of conditional probabilities. It does this in a limited sense, by incorporating the conditional probability of each attribute given the class and (at most) one other attribute. The method of boosting has previously proven very effective in improving the performance of Naïve Bayes classifiers and in this paper, we investigate its effectiveness on application to the TAN classifier.

Predicting structural disruption of proteins caused by crossover

We present a machine learning model that predicts a structural disruption score from a protein’s primary structure. SCHEMA was introduced by Frances Arnold and colleagues as a method for determining putative recombination sites of a protein on the basis of the full (PDB) description of its structure. The present method provides an alternative to SCHEMA that is able to determine the same score from sequence data only. Circumventing the need for resolving the full structure enables the exploration of yet unresolved and even hypothetical sequences for protein design efforts. Deriving the SCHEMA score from a primary structure is achieved using a two step approach: first predicting a secondary structure from the sequence and then predicting the SCHEMA score from the predicted secondary structure. The correlation coefficient for the prediction is 0.88 and indicates the feasibility of replacing SCHEMA with little loss of precision. ©2005 IEEE

Heuristic algorithm for computing reversal distance with multigene families via binary integer programming

Hannenhalli and Pevzner developed the first polynomial-time algorithm for the combinatorial problem of sorting of signed genomic data. Their algorithm solves the minimum number of reversals required for rearranging a genome to another when gene duplication is nonexisting. In this paper, we show how to extend the Hannenhalli-Pevzner approach to genomes with multigene families. We propose a new heuristic algorithm to compute the reversal distance between two genomes with multigene families via the concept of binary integer programming without removing gene duplicates. The experimental results on simulated and real biological data demonstrate that the proposed algorithm is able to find the reversal distance accurately. ©2005 IEEE

Exploiting sequence dependencies in the prediction of peroxisomal proteins

Prediction of peroxisomal matrix proteins generally depends on the presence of one of two distinct motifs at the end of the amino acid sequence. PTS1 peroxisomal proteins have a well conserved tripeptide at the C-terminal end. However, the preceding residues in the sequence arguably play a crucial role in targeting the protein to the peroxisome. Previous work in applying machine learning to the prediction of peroxisomal matrix proteins has failed W capitalize on the full extent of these dependencies. We benchmark a range of machine learning algorithms, and show that a classifier - based on the Support Vector Machine - produces more accurate results when dependencies between the conserved motif and the preceding section are exploited. We publish an updated and rigorously curated data set that results in increased prediction accuracy of most tested models.

Predicting peroxisomal proteins

PTS1 proteins are peroxisomal matrix proteins that have a well conserved targeting motif at the C-terminal end. However, this motif is present in many non peroxisomal proteins as well, thus predicting peroxisomal proteins involves differentiating fake PTS1 signals from actual ones. In this paper we report on the development of an SVM classifier with a separately trained logistic output function. The model uses an input window containing 12 consecutive residues at the C-terminus and the amino acid composition of the full sequence. The final model gives a Matthews Correlation Coefficient of 0.77, representing an increase of 54% compared with the well-known PeroxiP predictor. We test the model by applying it to several proteomes of eukaryotes for which there is no evidence of a peroxisome, producing a false positive rate of 0.088%.