scholarly journals DeepSELEX: inferring DNA-binding preferences from HT-SELEX data using multi-class CNNs

2020 ◽  
Vol 36 (Supplement_2) ◽  
pp. i634-i642
Author(s):  
Maor Asif ◽  
Yaron Orenstein
Keyword(s):  
Neural Networks ◽  
Dna Binding ◽  
High Throughput ◽  
Dna Sequences ◽  
Deep Neural Networks ◽  
High Throughput Sequencing ◽  
Supplementary Information ◽  
Computational Technique ◽  
Model Parameters ◽  
Binding Prediction

Abstract Motivation Transcription factor (TF) DNA-binding is a central mechanism in gene regulation. Biologists would like to know where and when these factors bind DNA. Hence, they require accurate DNA-binding models to enable binding prediction to any DNA sequence. Recent technological advancements measure the binding of a single TF to thousands of DNA sequences. One of the prevailing techniques, high-throughput SELEX, measures protein–DNA binding by high-throughput sequencing over several cycles of enrichment. Unfortunately, current computational methods to infer the binding preferences from high-throughput SELEX data do not exploit the richness of these data, and are under-using the most advanced computational technique, deep neural networks. Results To better characterize the binding preferences of TFs from these experimental data, we developed DeepSELEX, a new algorithm to infer intrinsic DNA-binding preferences using deep neural networks. DeepSELEX takes advantage of the richness of high-throughput sequencing data and learns the DNA-binding preferences by observing the changes in DNA sequences through the experimental cycles. DeepSELEX outperforms extant methods for the task of DNA-binding inference from high-throughput SELEX data in binding prediction in vitro and is on par with the state of the art in in vivo binding prediction. Analysis of model parameters reveals it learns biologically relevant features that shed light on TFs’ binding mechanism. Availability and implementation DeepSELEX is available through github.com/OrensteinLab/DeepSELEX/. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Trigonometric Inference Providing Learning in Deep Neural Networks

2021 ◽  
Vol 11 (15) ◽  
pp. 6704
Author(s):  
Jingyong Cai ◽  
Masashi Takemoto ◽  
Yuming Qiu ◽  
Hironori Nakajo
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Activation Function ◽  
Trigonometric Approximation ◽  
Model Parameters ◽  
Training Algorithms ◽  
Activation Functions ◽  
Classical Training ◽  
Sum Formula

Despite being heavily used in the training of deep neural networks (DNNs), multipliers are resource-intensive and insufficient in many different scenarios. Previous discoveries have revealed the superiority when activation functions, such as the sigmoid, are calculated by shift-and-add operations, although they fail to remove multiplications in training altogether. In this paper, we propose an innovative approach that can convert all multiplications in the forward and backward inferences of DNNs into shift-and-add operations. Because the model parameters and backpropagated errors of a large DNN model are typically clustered around zero, these values can be approximated by their sine values. Multiplications between the weights and error signals are transferred to multiplications of their sine values, which are replaceable with simpler operations with the help of the product to sum formula. In addition, a rectified sine activation function is utilized for further converting layer inputs into sine values. In this way, the original multiplication-intensive operations can be computed through simple add-and-shift operations. This trigonometric approximation method provides an efficient training and inference alternative for devices with insufficient hardware multipliers. Experimental results demonstrate that this method is able to obtain a performance close to that of classical training algorithms. The approach we propose sheds new light on future hardware customization research for machine learning.

scholarly journals Reconfigurable Binary Neural Network Accelerator with Adaptive Parallelism Scheme

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 230
Author(s):  
Jaechan Cho ◽  
Yongchul Jung ◽  
Seongjoo Lee ◽  
Yunho Jung
Keyword(s):  
Neural Networks ◽  
High Throughput ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Throughput Performance ◽  
Adaptive Parallelism ◽  
Sensor Applications ◽  
Binary Neural Network ◽  
Target Layer ◽  
Network Topologies

Binary neural networks (BNNs) have attracted significant interest for the implementation of deep neural networks (DNNs) on resource-constrained edge devices, and various BNN accelerator architectures have been proposed to achieve higher efficiency. BNN accelerators can be divided into two categories: streaming and layer accelerators. Although streaming accelerators designed for a specific BNN network topology provide high throughput, they are infeasible for various sensor applications in edge AI because of their complexity and inflexibility. In contrast, layer accelerators with reasonable resources can support various network topologies, but they operate with the same parallelism for all the layers of the BNN, which degrades throughput performance at certain layers. To overcome this problem, we propose a BNN accelerator with adaptive parallelism that offers high throughput performance in all layers. The proposed accelerator analyzes target layer parameters and operates with optimal parallelism using reasonable resources. In addition, this architecture is able to fully compute all types of BNN layers thanks to its reconfigurability, and it can achieve a higher area–speed efficiency than existing accelerators. In performance evaluation using state-of-the-art BNN topologies, the designed BNN accelerator achieved an area–speed efficiency 9.69 times higher than previous FPGA implementations and 24% higher than existing VLSI implementations for BNNs.

scholarly journals Generalized Born radii computation using linear models and neural networks

2019 ◽  
Vol 36 (6) ◽  
pp. 1757-1764
Author(s):  
Saida Saad Mohamed Mahmoud ◽  
Gennaro Esposito ◽  
Giuseppe Serra ◽  
Federico Fogolari
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Linear Model ◽  
Correlation Coefficient ◽  
Linear Models ◽  
Reference Method ◽  
Supplementary Information ◽  
Model Parameters ◽  
Generalized Born ◽  
Supplementary Material

Abstract Motivation Implicit solvent models play an important role in describing the thermodynamics and the dynamics of biomolecular systems. Key to an efficient use of these models is the computation of generalized Born (GB) radii, which is accomplished by algorithms based on the electrostatics of inhomogeneous dielectric media. The speed and accuracy of such computations are still an issue especially for their intensive use in classical molecular dynamics. Here, we propose an alternative approach that encodes the physics of the phenomena and the chemical structure of the molecules in model parameters which are learned from examples. Results GB radii have been computed using (i) a linear model and (ii) a neural network. The input is the element, the histogram of counts of neighbouring atoms, divided by atom element, within 16 Å. Linear models are ca. 8 times faster than the most widely used reference method and the accuracy is higher with correlation coefficient with the inverse of ‘perfect’ GB radii of 0.94 versus 0.80 of the reference method. Neural networks further improve the accuracy of the predictions with correlation coefficient with ‘perfect’ GB radii of 0.97 and ca. 20% smaller root mean square error. Availability and implementation We provide a C program implementing the computation using the linear model, including the coefficients appropriate for the set of Bondi radii, as Supplementary Material. We also provide a Python implementation of the neural network model with parameter and example files in the Supplementary Material as well. Supplementary information Supplementary data are available at Bioinformatics online.

ADFinder: accurate detection of programmed DNA elimination using NGS high-throughput sequencing data

2020 ◽  
Vol 36 (12) ◽  
pp. 3632-3636 ◽  
Author(s):  
Weibo Zheng ◽  
Jing Chen ◽  
Thomas G Doak ◽  
Weibo Song ◽  
Ying Yan
Keyword(s):  
High Throughput ◽  
Large Scale ◽  
High Throughput Sequencing ◽  
Supplementary Information ◽  
Sequencing Data ◽  
Source Codes ◽  
High Throughput Sequencing Data ◽  
Dna Elimination ◽  
Multiple Alternative ◽  
Dna Splicing

Abstract Motivation Programmed DNA elimination (PDE) plays a crucial role in the transitions between germline and somatic genomes in diverse organisms ranging from unicellular ciliates to multicellular nematodes. However, software specific for the detection of DNA splicing events is scarce. In this paper, we describe Accurate Deletion Finder (ADFinder), an efficient detector of PDEs using high-throughput sequencing data. ADFinder can predict PDEs with relatively low sequencing coverage, detect multiple alternative splicing forms in the same genomic location and calculate the frequency for each splicing event. This software will facilitate research of PDEs and all down-stream analyses. Results By analyzing genome-wide DNA splicing events in two micronuclear genomes of Oxytricha trifallax and Tetrahymena thermophila, we prove that ADFinder is effective in predicting large scale PDEs. Availability and implementation The source codes and manual of ADFinder are available in our GitHub website: https://github.com/weibozheng/ADFinder. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Geometric potentials from deep learning improve prediction of CDR H3 loop structures

2020 ◽  
Vol 36 (Supplement_1) ◽  
pp. i268-i275 ◽  
Author(s):  
Jeffrey A Ruffolo ◽  
Carlos Guerra ◽  
Sai Pooja Mahajan ◽  
Jeremias Sulam ◽  
Jeffrey J Gray
Keyword(s):  
Deep Neural Networks ◽  
De Novo ◽  
Probability Distributions ◽  
Supplementary Information ◽  
Model Parameters ◽  
Loop Structure ◽  
Variable Loops ◽  
Chain Sequence ◽  
Antibody Structure ◽  
Complementarity Determining Region

Abstract Motivation Antibody structure is largely conserved, except for a complementarity-determining region featuring six variable loops. Five of these loops adopt canonical folds which can typically be predicted with existing methods, while the remaining loop (CDR H3) remains a challenge due to its highly diverse set of observed conformations. In recent years, deep neural networks have proven to be effective at capturing the complex patterns of protein structure. This work proposes DeepH3, a deep residual neural network that learns to predict inter-residue distances and orientations from antibody heavy and light chain sequence. The output of DeepH3 is a set of probability distributions over distances and orientation angles between pairs of residues. These distributions are converted to geometric potentials and used to discriminate between decoy structures produced by RosettaAntibody and predict new CDR H3 loop structures de novo. Results When evaluated on the Rosetta antibody benchmark dataset of 49 targets, DeepH3-predicted potentials identified better, same and worse structures [measured by root-mean-squared distance (RMSD) from the experimental CDR H3 loop structure] than the standard Rosetta energy function for 33, 6 and 10 targets, respectively, and improved the average RMSD of predictions by 32.1% (1.4 Å). Analysis of individual geometric potentials revealed that inter-residue orientations were more effective than inter-residue distances for discriminating near-native CDR H3 loops. When applied to de novo prediction of CDR H3 loop structures, DeepH3 achieves an average RMSD of 2.2 ± 1.1 Å on the Rosetta antibody benchmark. Availability and Implementation DeepH3 source code and pre-trained model parameters are freely available at https://github.com/Graylab/deepH3-distances-orientations. Supplementary information Supplementary data are available at Bioinformatics online.

Minirmd: accurate and fast duplicate removal tool for short reads via multiple minimizers

2020 ◽  
Author(s):  
Yuansheng Liu ◽  
Xiaocai Zhang ◽  
Quan Zou ◽  
Xiangxiang Zeng
Keyword(s):  
High Throughput ◽  
High Throughput Sequencing ◽  
De Novo ◽  
Supplementary Information ◽  
Supplementary Data ◽  
Complementary Strand ◽  
Short Reads ◽  
Sequencing Technologies ◽  
Computational Resources

Abstract Summary Removing duplicate and near-duplicate reads, generated by high-throughput sequencing technologies, is able to reduce computational resources in downstream applications. Here we develop minirmd, a de novo tool to remove duplicate reads via multiple rounds of clustering using different length of minimizer. Experiments demonstrate that minirmd removes more near-duplicate reads than existing clustering approaches and is faster than existing multi-core tools. To the best of our knowledge, minirmd is the first tool to remove near-duplicates on reverse-complementary strand. Availability and implementation https://github.com/yuansliu/minirmd. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals MOLI: multi-omics late integration with deep neural networks for drug response prediction

2019 ◽  
Vol 35 (14) ◽  
pp. i501-i509 ◽  
Author(s):  
Hossein Sharifi-Noghabi ◽  
Olga Zolotareva ◽  
Colin C Collins ◽  
Martin Ester
Keyword(s):  
Gene Expression ◽  
Neural Networks ◽  
Prediction Accuracy ◽  
Drug Response ◽  
Deep Neural Networks ◽  
Response Prediction ◽  
Supplementary Information ◽  
Precision Oncology

Abstract Motivation Historically, gene expression has been shown to be the most informative data for drug response prediction. Recent evidence suggests that integrating additional omics can improve the prediction accuracy which raises the question of how to integrate the additional omics. Regardless of the integration strategy, clinical utility and translatability are crucial. Thus, we reasoned a multi-omics approach combined with clinical datasets would improve drug response prediction and clinical relevance. Results We propose MOLI, a multi-omics late integration method based on deep neural networks. MOLI takes somatic mutation, copy number aberration and gene expression data as input, and integrates them for drug response prediction. MOLI uses type-specific encoding sub-networks to learn features for each omics type, concatenates them into one representation and optimizes this representation via a combined cost function consisting of a triplet loss and a binary cross-entropy loss. The former makes the representations of responder samples more similar to each other and different from the non-responders, and the latter makes this representation predictive of the response values. We validate MOLI on in vitro and in vivo datasets for five chemotherapy agents and two targeted therapeutics. Compared to state-of-the-art single-omics and early integration multi-omics methods, MOLI achieves higher prediction accuracy in external validations. Moreover, a significant improvement in MOLI’s performance is observed for targeted drugs when training on a pan-drug input, i.e. using all the drugs with the same target compared to training only on drug-specific inputs. MOLI’s high predictive power suggests it may have utility in precision oncology. Availability and implementation https://github.com/hosseinshn/MOLI. Supplementary information Supplementary data are available at Bioinformatics online.

Dataset-aware multi-task learning approaches for biomedical named entity recognition

2020 ◽  
Vol 36 (15) ◽  
pp. 4331-4338
Author(s):  
Mei Zuo ◽  
Yang Zhang
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Named Entity Recognition ◽  
Entity Recognition ◽  
Quality Data ◽  
Supplementary Information ◽  
Named Entity ◽  
Task Learning ◽  
Biomedical Named Entity Recognition

Abstract Motivation Named entity recognition is a critical and fundamental task for biomedical text mining. Recently, researchers have focused on exploiting deep neural networks for biomedical named entity recognition (Bio-NER). The performance of deep neural networks on a single dataset mostly depends on data quality and quantity while high-quality data tends to be limited in size. To alleviate task-specific data limitation, some studies explored the multi-task learning (MTL) for Bio-NER and achieved state-of-the-art performance. However, these MTL methods did not make full use of information from various datasets of Bio-NER. The performance of state-of-the-art MTL method was significantly limited by the number of training datasets. Results We propose two dataset-aware MTL approaches for Bio-NER which jointly train all models for numerous Bio-NER datasets, thus each of these models could discriminatively exploit information from all of related training datasets. Both of our two approaches achieve substantially better performance compared with the state-of-the-art MTL method on 14 out of 15 Bio-NER datasets. Furthermore, we implemented our approaches by incorporating Bio-NER and biomedical part-of-speech (POS) tagging datasets. The results verify Bio-NER and POS can significantly enhance one another. Availability and implementation Our source code is available at https://github.com/zmmzGitHub/MTL-BC-LBC-BioNER and all datasets are publicly available at https://github.com/cambridgeltl/MTL-Bioinformatics-2016. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals CRAFT: Compact genome Representation towards large-scale Alignment-Free daTabase

2020 ◽  
Author(s):  
Yang Young Lu ◽  
Jiaxing Bai ◽  
Yiwen Wang ◽  
Ying Wang ◽  
Fengzhu Sun
Keyword(s):  
Dna Sequences ◽  
Sequence Comparison ◽  
Large Scale ◽  
High Throughput Sequencing ◽  
Sequence Data ◽  
Practical Interest ◽  
Supplementary Information ◽  
Computationally Efficient ◽  
Sequencing Technologies ◽  
Alignment Free

AbstractMotivationRapid developments in sequencing technologies have boosted generating high volumes of sequence data. To archive and analyze those data, one primary step is sequence comparison. Alignment-free sequence comparison based on k-mer frequencies offers a computationally efficient solution, yet in practice, the k-mer frequency vectors for large k of practical interest lead to excessive memory and storage consumption.ResultsWe report CRAFT, a general genomic/metagenomic search engine to learn compact representations of sequences and perform fast comparison between DNA sequences. Specifically, given genome or high throughput sequencing (HTS) data as input, CRAFT maps the data into a much smaller embedding space and locates the best matching genome in the archived massive sequence repositories. With 102 – 104-fold reduction of storage space, CRAFT performs fast query for gigabytes of data within seconds or minutes, achieving comparable performance as six state-of-the-art alignment-free measures.AvailabilityCRAFT offers a user-friendly graphical user interface with one-click installation on Windows and Linux operating systems, freely available at https://github.com/jiaxingbai/[email protected]; [email protected] informationSupplementary data are available at Bioinformatics online.

Sign in / Sign up

Export Citation Format

Share Document