arXiv subjects

Homayoun Valafar

Publications and source records attributed to Homayoun Valafar.

At least 37 records · Page 2Linked to original sources

arXiv2020

Distributed Global Optimization (DGO)

A new technique of global optimization and its applications in particular to neural networks are presented. The algorithm is also compared to other global optimization algorithms such as Gradient descent (GD), Monte Carlo (MC), Genetic Algorithm (GA) and other commercial packages. This new optimization technique proved itself worthy of further study after observing its accuracy of convergence, speed of convergence and ease of use. Some of the advantages of this new optimization technique are listed below: 1. Optimizing function does not have to be continuous or differentiable. 2. No random mechanism is used, therefore this algorithm does not inherit the slow speed of random searches. 3. There are no fine-tuning parameters (such as the step rate of G.D. or temperature of S.A.) needed for this technique. 4. This algorithm can be implemented on parallel computers so that there is little increase in computation time (compared to linear increase) as the number of dimensions increases. The time complexity of O(n) is achieved.

cs.DC↗

arXiv2020

TALI: Protein Structure Alignment Using Backbone Torsion Angles

This article introduces a novel protein structure alignment method (named TALI) based on the protein backbone torsion angle instead of the more traditional distance matrix. Because the structural alignment of the two proteins is based on the comparison of two sequences of numbers (backbone torsion angles), we can take advantage of a large number of well-developed methods such as Smith-Waterman or Needleman-Wunsch. Here we report the result of TALI in comparison to other structure alignment methods such as DALI, CE, and SSM ass well as sequence alignment based on PSI-BLAST. TALI demonstrated great success over all other methods in application to challenging proteins. TALI was more successful in recognizing remote structural homology. TALI also demonstrated an ability to identify structural homology between two proteins where the structural difference was due to a rotation of internal domains by nearly 180$^\circ$.

q-bio.BM↗

arXiv2020

An Investigation in Optimal Encoding of Protein Primary Sequence for Structure Prediction by Artificial Neural Networks

Machine learning and the use of neural networks has increased precipitously over the past few years primarily due to the ever-increasing accessibility to data and the growth of computation power. It has become increasingly easy to harness the power of machine learning for predictive tasks. Protein structure prediction is one area where neural networks are becoming increasingly popular and successful. Although very powerful, the use of ANN require selection of most appropriate input/output encoding, architecture, and class to produce the optimal results. In this investigation we have explored and evaluated the effect of several conventional and newly proposed input encodings and selected an optimal architecture. We considered 11 variations of input encoding, 11 alternative window sizes, and 7 different architectures. In total, we evaluated 2,541 permutations in application to the training and testing of more than 10,000 protein structures over the course of 3 months. Our investigations concluded that one-hot encoding, the use of LSTMs, and window sizes of 9, 11, and 15 produce the optimal outcome. Through this optimization, we were able to improve the quality of protein structure prediction by predicting the ϕ dihedrals to within 14° - 16° and ψ dihedrals to within 23°- 25°. This is a notable improvement compared to previously similar investigations.

cs.LG↗

arXiv2020

Process of Efficiently Parallelizing a Protein Structure Determination Algorithm

Computational protein structure determination involves optimization in a problem space much too large to exhaustively search. Existing approaches include optimization algorithms such as gradient descent and simulated annealing, but these typically only find local minima. One novel approach implemented in REDcRAFT is to instead of folding a protein all at the same time, fold it residue by residue. This simulates a protein folding as each residue exits from the generating ribosome. While REDcRAFT exponentially reduces the problem space so it can be explored in polynomial time, it is still extremely computationally demanding. This algorithm does have the advantage that most of the execution time is spent in inherently parallelizable code. However, preliminary results from parallel execution indicate that approximately two-thirds of execution time is dedicated to system overhead. Additionally, by carefully analyzing and timing the structure of the program the major bottlenecks can be identified. After addressing these issues, REDcRAFT becomes a scalable parallel application with nearly two orders of magnitude improvement.

cs.DC↗

arXiv2020

A Comparative study of Artificial Neural Networks Using Reinforcement learning and Multidimensional Bayesian Classification Using Parzen Density Estimation for Identification of GC-EIMS Spectra of Partially Methylated Alditol Acetates

This study reports the development of a pattern recognition search engine for a World Wide Web-based database of gas chromatography-electron impact mass spectra (GC-EIMS) of partially methylated Alditol Acetates (PMAAs). Here, we also report comparative results for two pattern recognition techniques that were employed for this study. The first technique is a statistical technique using Bayesian classifiers and Parzen density estimators. The second technique involves an artificial neural network module trained with reinforcement learning. We demonstrate here that both systems perform well in identifying spectra with small amounts of noise. Both system's performance degrades with degrading signal-to-noise ratio (SNR). When dealing with partial spectra (missing data), the artificial neural network system performs better. The developed system is implemented on the world wide web, and is intended to identify PMAAs using submitted spectra of these molecules recorded on any GC-EIMS instrument. The system, therefore, is insensitive to instrument and column dependent variations in GC-EIMS spectra.

eess.SP↗

arXiv2020

Identification of 1H-NMR Spectra of Xyloglucan Oligosaccharides: A Comparative Study of Artificial Neural Networks and Bayesian Classification Using Nonparametric Density Estimation

Proton nuclear magnetic resonance (1H-NMR) is a widely used tool for chemical structural analysis. However, 1H-NMR spectra suffer from natural aberrations that render computer-assisted automated identification of these spectra difficult, and at times impossible. Previous efforts have successfully implemented instrument dependent or conditional identification of these spectra. In this paper, we report the first instrument independent computer-assisted automated identification system for a group of complex carbohydrates known as the xyloglucan oligosaccharides. The developed system is also implemented on the world wide web (http://www.ccrc.uga.edu) as part of an identification package called the CCRC-Net and is intended to recognize any submitted 1H-NMR spectrum of these structures with reasonable signal-to-noise ratio, recorded on any 500 MHz NMR instrument. The system uses Artificial Neural Networks (ANNs) technology and is insensitive to the instrument and environment-dependent variations in 1H-NMR spectroscopy. In this paper, comparative results of the ANN engine versus a multidimensional Bayes' classifier is also presented.

q-bio.BM↗

arXiv2020

Parallel, Self Organizing, Consensus Neural Networks

A new neural network architecture (PSCNN) is developed to improve performance and speed of such networks. The architecture has all the advantages of the previous models such as self-organization and possesses some other superior characteristics such as input parallelism and decision making based on consensus. Due to the properties of this network, it was studied with respect to implementation on a Parallel Processor (Ncube Machine) as well as a regular sequential machine. The architecture self organizes its own modules in a way to maximize performance. Since it is completely parallel, both recall and learning procedures are very fast. The performance of the network was compared to the Backpropagation networks in problems of language perception, remote sensing and binary logic (Exclusive-Or). PSCNN showed superior performance in all cases studied.

cs.NE↗

arXiv2020

A Preliminary Investigation in the Molecular Basis of Host Shutoff Mechanism in SARS-CoV

Recent events leading to the worldwide pandemic of COVID-19 have demonstrated the effective use of genomic sequencing technologies to establish the genetic sequence of this virus. In contrast, the COVID-19 pandemic has demonstrated the absence of computational approaches to understand the molecular basis of this infection rapidly. Here we present an integrated approach to the study of the nsp1 protein in SARS-CoV-1, which plays an essential role in maintaining the expression of viral proteins and further disabling the host protein expression, also known as the host shutoff mechanism. We present three independent methods of evaluating two potential binding sites speculated to participate in host shutoff by nsp1. We have combined results from computed models of nsp1, with deep mining of all existing protein structures (using PDBMine), and binding site recognition (using msTALI) to examine the two sites consisting of residues 55-59 and 73-80. Based on our preliminary results, we conclude that the residues 73-80 appear as the regions that facilitate the critical initial steps in the function of nsp1. Given the 90% sequence identity between nsp1 from SARS-CoV-1 and SARS-CoV-2, we conjecture the same critical initiation step in the function of COVID-19 nsp1.

q-bio.BM↗

arXiv2020

Assessing the Precision and Recall of msTALI as Applied to an Active-Site Study on Fold Families

Proteins execute various activities required by biological cells. Further, they structurally support and pro-mote important biochemical reactions which functionally are sparked by active-sites. Active-sites are regions where reac-tions and binding events take place directly; they foster pro-tein purpose. Describing functional relationships depends on factors that incorporate sequence, structure, and the biochem-ical properties of amino acids that form proteins. Our ap-proach to active-site description is computational, and many other approaches utilizing available protein data fall short of ideal. Successful recognition of functional interactions is cru-cial to advancements in protein annotation and the bioinfor-matics field at large. This research outlines our Multiple Structure Torsion Angle Alignment (msTALI) as a suitable strategy for addressing active-site identification by comparing results to other existing methods. Specifically, we address the precision of msTALI across three protein families. Our target proteins are PDBIDs 1A2B, 1B4V, 1B8S, 1COY, 1CXZ, 3COX, 1D7E, 1DPF, 1F9I, 1FTN, 1IJH, 1KOU, 1NWZ, 2PHY, and 1SIC.

q-bio.QM↗

arXiv2020

Recognition of Smoking Gesture Using Smart Watch Technology

Diseases resulting from prolonged smoking are the most common preventable causes of death in the world today. In this report we investigate the success of utilizing accelerometer sensors in smart watches to identify smoking gestures. Early identification of smoking gestures can help to initiate the appropriate intervention method and prevent relapses in smoking. Our experiments indicate 85%-95% success rates in identification of smoking gesture among other similar gestures using Artificial Neural Networks (ANNs). Our investigations concluded that information obtained from the x-dimension of accelerometers is the best means of identifying the smoking gesture, while y and z dimensions are helpful in eliminating other gestures such as: eating, drinking, and scratch of nose. We utilized sensor data from the Apple Watch during the training of the ANN. Using sensor data from another participant collected on Pebble Steel, we obtained a smoking identification accuracy of greater than 90% when using an ANN trained on data previously collected from the Apple Watch. Finally, we have demonstrated the possibility of using smart watches to perform continuous monitoring of daily activities.

cs.LG↗

arXiv2020

An Artificial Neural Network Based Approach for Identification of Native Protein Structures using an Extended ForceField

Current protein forcefields like the ones seen in CHARMM or Xplor-NIH have many terms that include bonded and non-bonded terms. Yet the forcefields do not take into account the use of hydrogen bonds which are important for secondary structure creation and stabilization of proteins. SCOPE is an open-source program that generates proteins from rotamer space. It then creates a forcefield that uses only non-bonded and hydrogen bond energy terms to create a profile for a given protein. The profiles can then be used in an artificial neural network to create a linear model that is funneled to the true protein conformation.

q-bio.BM↗

arXiv2020

An Investigation of Minimum Data Requirement for Successful Structure Determination of Pf2048.1 with REDCRAFT

Traditional approaches to elucidation of protein structures by NMR spectroscopy rely on distance restraints also know as nuclear Overhauser effects (NOEs). The use of NOEs as the primary source of structure determination by NMR spectroscopy is time consuming and expensive. Residual Dipolar Couplings (RDCs) have become an alternate approach for structure calculation by NMR spectroscopy. In this work we report our results for structure calculation of the novel protein PF2048.1 from RDC data and establish the minimum data requirement for successful structure calculation using the software package REDCRAFT. Our investigations start with utilizing four sets of synthetic RDC data in two alignment media and proceed by reducing the RDC data to the final limit of {CN, NH} and {NH} from two alignment media respectively. Our results indicate that structure elucidation of this protein is possible with as little as {CN, NH} and {NH} to within 0.533Å of the target structure.

q-bio.BM↗

arXiv2020

De Novo Assembly of Uca minax Transcriptome from Next Generation Sequencing

High-throughput cDNA sequencing (RNA-seq) is a very powerful technique to quantify gene expression in an unbiased way. The Crustacean family is among the groups of organisms sparsely represented in current genomic databases. Here we present transcriptome data from Uca minax (red-jointed fiddler crab) as an opportunity to extend our knowledge. Next generation sequencing was performed on six tissue samples from Uca minax using the Illumina HiSeq system. Six Transcriptome libraries were created using Trinity; a free, open-source software tool for de novo transcriptome assembly of high-throughput mRNA sequencing (RNA-seq) data with the absence of a reference genome. In addition, several tools that aid in management of data were used, such as RSEM, Bowtie, Blast, and IGV; a tool for visualizing RNA-seq analysis results. Fast quality control (FastQC) analysis of the raw sequenced files revealed that both adapter and PCR primer sequences were prevalently present, which may require a preprocessing step.

q-bio.GN↗

arXiv2020

State Transition Modeling of the Smoking Behavior using LSTM Recurrent Neural Networks

The use of sensors has pervaded everyday life in several applications including human activity monitoring, healthcare, and social networks. In this study, we focus on the use of smartwatch sensors to recognize smoking activity. More specifically, we have reformulated the previous work in detection of smoking to include in-context recognition of smoking. Our presented reformulation of the smoking gesture as a state-transition model that consists of the mini-gestures hand-to-lip, hand-on-lip, and hand-off-lip, has demonstrated improvement in detection rates nearing 100% using conventional neural networks. In addition, we have begun the utilization of Long-Short-Term Memory (LSTM) neural networks to allow for in-context detection of gestures with accuracy nearing 97%.

cs.CV↗

arXiv2019

Automated Analysis of Femoral Artery Calcification Using Machine Learning Techniques

We report an object tracking algorithm that combines geometrical constraints, thresholding, and motion detection for tracking of the descending aorta and the network of major arteries that branch from the aorta including the iliac and femoral arteries. Using our automated identification and analysis, arterial system was identified with more than 85% success when compared to human annotation. Furthermore, the reported automated system is capable of producing a stenosis profile, and a calcification score similar to the Agatston score. The use of stenosis and calcification profiles will lead to the development of better-informed diagnostic and prognostic tools.

eess.IV↗

arXiv2019

An AI model for Rapid and Accurate Identification of Chemical Agents in Mass Casualty Incidents

In this report we examine the effectiveness of WISER in identification of a chemical culprit during a chemical based Mass Casualty Incident (MCI). We also evaluate and compare Binary Decision Tree (BDT) and Artificial Neural Networks (ANN) using the same experimental conditions as WISER. The reverse engineered set of Signs/Symptoms from the WISER application was used as the training set and 31,100 simulated patient records were used as the testing set. Three sets of simulated patient records were generated by 5%, 10% and 15% perturbation of the Signs/Symptoms of each chemical record. While all three methods achieved a 100% training accuracy, WISER, BDT and ANN produced performances in the range of: 1.8%-0%, 65%-26%, 67%-21% respectively. A preliminary investigation of dimensional reduction using ANN illustrated a dimensional collapse from 79 variables to 40 with little loss of classification performance.

stat.ML↗

arXiv2019

Modelling of Sickle Cell Anemia Patients Response to Hydroxyurea using Artificial Neural Networks

Hydroxyurea (HU) has been shown to be effective in alleviating the symptoms of Sickle Cell Anemia disease. While Hydroxyurea reduces the complications associated with Sickle Cell Anemia in some patients, others do not benefit from this drug and experience deleterious effects since it is also a chemotherapeutic agent. Therefore, to whom, should the administration of HU be considered as a viable option, is the main question asked by the responsible physician. We address this question by developing modeling techniques that can predict a patient's response to HU and therefore spare the non-responsive patients from the unnecessary effects of HU on the values of 22 parameters that can be obtained from blood samples in 122 patients. Using this data, we developed Deep Artificial Neural Network models that can predict with 92.6% accuracy, the final HbF value of a subject after undergoing HU therapy. Our current studies are focussing on forecasting a patient's HbF response, 30 days ahead of time.

q-bio.QM↗

arXiv2019

Improvements of the REDCRAFT Software Package

Traditional approaches to elucidation of protein structures by NMR spectroscopy rely on distance restraints also known as nuclear Overhauser effects (NOEs). The use of NOEs as the primary source of structure determination by NMR spectroscopy is time consuming and expensive. Residual Dipolar Couplings (RDCs) have become an alternate approach for structure calculation by NMR spectroscopy. In previous works, the software package REDCRAFT has been presented as a means of harnessing the information containing in RDCs for structure calculation of proteins. In this work, we present significant improvements to the REDCRAFT package including: refinement of the decimation procedure, the inclusion of graphical user interface, adoption of NEF standards, and addition of scripts for enhanced protein modeling options. The improvements to REDCRAFT have resulted in the ability to fold proteins that the previous versions were unable to fold. For instance, we report the results of folding of the protein 1A1Z in the presence of highly erroneous data.

q-bio.BM↗