A note on computing with Kolmogorov Superpositions without iterations

We extend Kolmogorov's Superpositions to approximating arbitrary continuous functions with a noniterative approach that can be used by any neural network that uses these superpositions. Our approximation algorithm uses a modified dimension reducing function that allows for an increased number of summands to achieve an error bound commensurate with that of r iterations for any r. This new variant of Kolmogorov's Superpositions improves upon the original parallelism inherent in them by performing highly distributed parallel computations without synchronization. We note that this approach makes implementation much easier and more efficient on networks of modern parallel hardware, and thus makes it a more practical tool.

A novel computational approach to the silencing of Sugarcane Bacilliform Guadeloupe A Virus determines potential host-derived MicroRNAs in sugarcane (Saccharum officinarum L.)

Sugarcane Bacilliform Guadeloupe A Virus (SCBGAV, genus Badnavirus, family Caulimoviridae) is an emerging, deleterious pathogen of sugarcane which presents a substantial barrier to producing high sugarcane earnings. Sugarcane bacilliform viruses (SCBVs) are one of the main species that infect sugarcane. During the last 30 years, significant genetic changes in SCBV strains have been observed with a high risk of disease incidence associated with crop damage. SCBV infection may lead to significant losses in biomass production in susceptible sugarcane cultivars. The circular, double-stranded (ds) DNA genome of SCBGAV (7.4 Kb) is composed of three open reading frames (ORFs) on the positive strand that replicate by a reverse transcriptase. SCBGAV can infect sugarcane in a semipersistent manner via the insect vectors sugarcane mealybug species. In the current study, we used miRNA target prediction algorithms to identify and comprehensively analyze the genome-wide sugarcane (Saccharum officinarum L.)-encoded microRNA (miRNA) targets against the SCBGAV. Mature miRNA target sequences were retrieved from the miRBase (miRNA database) and were further analyzed for hybridization to the SCBGAV genome. Multiple computational approaches—including miRNA-target seed pairing, multiple target positions, minimum free energy, target site accessibility, maximum complementarity, pattern recognition and minimum folding energy for attachments—were considered by all algorithms. Among them, sof-miR396 was identified as the top effective candidate, capable of targeting the vital ORF3 of the SCBGAV genome. miRanda, RNA22 and RNAhybrid algorithms predicted hybridization of sof-miR396 at common locus position 3394. The predicted sugarcane miRNAs against viral mRNA targets possess antiviral activities, leading to translational inhibition by mRNA cleavage. Interaction network of sugarcane-encoded miRNAs with SCBGAV genes, created using Circos, allow analyze new targets. The finding of the present study acts as a first step towards the creation of SCBGAV-resistant sugarcane through the expression of the identified miRNAs.

Computational Algorithms that Effectively Reduce Report Defects in Surgical Pathology

Background:

Pathology report defects refer to errors in the pathology reports, such as transcription/voice recognition errors and incorrect nondiagnostic information. Examples of the latter include incorrect gender, incorrect submitting physician, incorrect description of tissue blocks submitted, report formatting issues, and so on. Over the past 5 years, we have implemented computational algorithms to identify and correct these report defects.

Materials and Methods:

Report texts, tissue blocks submitted, and other relevant information are retrieved from the pathology information system database. Two complementary algorithms are used to identify the voice recognition errors by parsing the gross description texts to either (i) identify previously encountered error patterns or (ii) flag sentences containing previously-unused two-word sequences (bigrams). A third algorithm based on identifying conflicting information from two different sources is used to identify tissue block designation errors in the gross description; the information on actual block submission is compared with the block designation information parsed from the gross description text.

Results:

The computational algorithms identify voice recognition errors in approximately 8%–10% of the cases and block designation errors in approximately 0.5%–1% of all the cases.

Conclusions:

The algorithms described here have been effective in reducing pathology report defects. In addition to detecting voice recognition and block designation errors, these algorithms have also be used to detect other report defects, such as wrong gender, wrong provider, special stains or immunostains performed but not reported, and so on.

Computational Prediction of sRNA in Acinetobacter baumannii

Small RNAs in bacteria are noncoding RNAs that act as posttranscriptional regulators of gene expression. Over time, they have gained importance as fine-tuners of expression of genes involved in critical biological processes like metabolism, fitness, virulence, and antibiotic resistance. The availability of various high-throughput strategies enable the detection of these molecules but are technically challenging and time-intensive. Thus, to fulfil the need of a simple computational algorithm pipeline to predict these sRNAs in bacterial species, we detail a user-friendly ensemble method with specific application in Acinetobacter spp. The developed algorithms primarily look for intergenic regions in the genome of related Acinetobacter spp., thermodynamic stability, and conservation of RNA secondary structures to generate a model input for the sRNAPredict3 tool which utilizes all this information to generate a list of putative sRNA. We confirmed the accuracy of the method by comparing its output with the RNA-seq data and found the method to be faster and more accurate for Acinetobacter baumannii ATCC 17978. Thus, this method improves the identification of sRNA in Acinetobacter and other bacterial species.

Brain Cancer Imaging Phenomics Toolkit (brain-CaPTk): An Interactive Platform for Quantitative Analysis of Glioblastoma

Quantitative research, especially in the field of radio(geno)mics, has helped us understand fundamental mechanisms of neurologic diseases. Such research is integrally based on advanced algorithms to derive extensive radiomic features and integrate them into diagnostic and predictive models. To exploit the benefit of such complex algorithms, their swift translation into clinical practice is required, currently hindered by their complicated nature. brain-CaPTk is a modular platform, with components spanning across image processing, segmentation, feature extraction, and machine learning, that facilitates such translation, enabling quantitative analyses without requiring substantial computational background. Thus, brain-CaPTk can be seamlessly integrated into the typical quantification, analysis and reporting workflow of a radiologist, underscoring its clinical potential. This paper describes currently available components of brain-CaPTk and example results from their application in glioblastoma.