Deep Neural Networks to Remove Photoacoustic Reflection Artifacts in Ex Vivo and in Vivo Tissue

Background: Among all the major Post-translational modification, lipid modifications possess special significance due to their widespread functional importance in eukaryotic cells. There exist multiple types of lipid modifications and Palmitoylation, among them, is one of the broader types of modification, having three different types. The N-Palmitoylation is carried out by attachment of palmitic acid to an N-terminal cysteine. Due to the association of N-Palmitoylation with various biological functions and diseases such as Alzheimer’s and other neurodegenerative diseases, carrying out important processes in the life cycle of various pathogens, its identification is very important. Objective: The in vitro, ex vivo and in vivo identification of Palmitoylation is laborious, time-taking and costly. There is a dire need of an efficient and accurate computational model to help researchers and biologists identifying these sites, in an easy manner. Herein, we propose a novel prediction model for identification of N-Palmitoylation sites in proteins. Method: Proposed prediction model is developed by combining the Chou’s Pseudo Amino Acid Composition (PseAAC) with deep neural networks. We used well-known deep neural networks (DNNs) for both the tasks of learning a feature representation of peptide sequences and developing prediction model to perform classification. Results: Among different DNNs, Gated Recurrent Unit (GRU) based RNN model showed highest scores in terms of accuracy, and all other computed measures, and outperforms all the previously reported predictors. Conclusion: The proposed GRU based RNN model can help identifying N-Palmitoylation in a very efficient and accurate manner which can help scientists understand the mechanism of this modification in proteins.

Download Full-text

Computational identification of 4-carboxyglutamate sites to supplement physiological studies using deep learning

Scientific Reports ◽

10.1038/s41598-021-03895-4 ◽

2022 ◽

Vol 12 (1) ◽

Author(s):

Sheraz Naseer ◽

Rao Faizan Ali ◽

Suliman Mohamed Fati ◽

Amgad Muneer

Keyword(s):

Neural Networks ◽

Amino Acid ◽

Glutamic Acid ◽

Deep Neural Networks ◽

Ex Vivo ◽

Protein Biosynthesis ◽

Feature Representation ◽

Post Translational Modification

AbstractIn biological systems, Glutamic acid is a crucial amino acid which is used in protein biosynthesis. Carboxylation of glutamic acid is a significant post-translational modification which plays important role in blood coagulation by activating prothrombin to thrombin. Contrariwise, 4-carboxy-glutamate is also found to be involved in diseases including plaque atherosclerosis, osteoporosis, mineralized heart valves, bone resorption and serves as biomarker for onset of these diseases. Owing to the pathophysiological significance of 4-carboxyglutamate, its identification is important to better understand pathophysiological systems. The wet lab identification of prospective 4-carboxyglutamate sites is costly, laborious and time consuming due to inherent difficulties of in-vivo, ex-vivo and in vitro experiments. To supplement these experiments, we proposed, implemented, and evaluated a different approach to develop 4-carboxyglutamate site predictors using pseudo amino acid compositions (PseAAC) and deep neural networks (DNNs). Our approach does not require any feature extraction and employs deep neural networks to learn feature representation of peptide sequences and performing classification thereof. Proposed approach is validated using standard performance evaluation metrics. Among different deep neural networks, convolutional neural network-based predictor achieved best scores on independent dataset with accuracy of 94.7%, AuC score of 0.91 and F1-score of 0.874 which shows the promise of proposed approach. The iCarboxE-Deep server is deployed at https://share.streamlit.io/sheraz-n/carboxyglutamate/app.py.

Download Full-text

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

Bioinformatics ◽

10.1093/bioinformatics/btz318 ◽

2019 ◽

Vol 35 (14) ◽

pp. i501-i509 ◽

Cited By ~ 28

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.

Download Full-text

Deciphering the rules of mRNA structure differentiation in Saccharomyces cerevisiae in vivo and in vitro with deep neural networks

RNA Biology ◽

10.1080/15476286.2019.1612692 ◽

2019 ◽

Vol 16 (8) ◽

pp. 1044-1054 ◽

Cited By ~ 4

Author(s):

Haopeng Yu ◽

Wenjing Meng ◽

Yuanhui Mao ◽

Yi Zhang ◽

Qing Sun ◽

...

Keyword(s):

Saccharomyces Cerevisiae ◽

Neural Networks ◽

Deep Neural Networks ◽

Mrna Structure

Download Full-text

MOLI: Multi-Omics Late Integration with deep neural networks for drug response prediction

10.1101/531327 ◽

2019 ◽

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 ◽

Precision Oncology ◽

Early Integration

AbstractMotivationHistorically, 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.ResultsWe 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 subnetworks 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 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 of the implemented codeshttps://github.com/hosseinshn/[email protected] and [email protected]

Download Full-text

Modeling positional effects of regulatory sequences with spline transformations increases prediction accuracy of deep neural networks

10.1101/165183 ◽

2017 ◽

Cited By ~ 1

Author(s):

Žiga Avsec ◽

Mohammadamin Barekatain ◽

Jun Cheng ◽

Julien Gagneur

Keyword(s):

Neural Network ◽

Neural Networks ◽

Deep Learning ◽

Prediction Accuracy ◽

Deep Neural Networks ◽

Rna Binding ◽

Piecewise Linear ◽

Regulatory Sequences ◽

Link Type

AbstractMotivationRegulatory sequences are not solely defined by their nucleic acid sequence but also by their relative distances to genomic landmarks such as transcription start site, exon boundaries, or polyadenylation site. Deep learning has become the approach of choice for modeling regulatory sequences because of its strength to learn complex sequence features. However, modeling relative distances to genomic landmarks in deep neural networks has not been addressed.ResultsHere we developed spline transformation, a neural network module based on splines to flexibly and robustly model distances. Modeling distances to various genomic landmarks with spline transformations significantly increased state-of-the-art prediction accuracy of in vivo RNA-binding protein binding sites for 114 out of 123 proteins. We also developed a deep neural network for human splice branchpoint based on spline transformations that outperformed the current best, already distance-based, machine learning model. Compared to piecewise linear transformation, as obtained by composition of rectified linear units, spline transformation yields higher prediction accuracy as well as faster and more robust training. As spline transformation can be applied to further quantities beyond distances, such as methylation or conservation, we foresee it as a versatile component in the genomics deep learning toolbox.AvailabilitySpline transformation is implemented as a Keras layer in the CONCISE python package: https://github.com/gagneurlab/concise. Analysis code is available at goo.gl/[email protected]; [email protected]

Download Full-text

Deep Learning for RNA Synthetic Biology

10.1101/872077 ◽

2019 ◽

Cited By ~ 2

Author(s):

Nicolaas M. Angenent-Mari ◽

Alexander S. Garruss ◽

Luis R. Soenksen ◽

George Church ◽

James J. Collins

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Synthetic Biology ◽

Small Molecules ◽

Deep Neural Networks ◽

Failure Modes ◽

Major Step ◽

Viral Genomes ◽

Previous State

AbstractEngineered RNA elements are programmable tools capable of detecting small molecules, proteins, and nucleic acids. Predicting the behavior of these tools remains a challenge, a situation that could be addressed through enhanced pattern recognition from deep learning. Thus, we investigate Deep Neural Networks (DNN) to predict toehold switch function as a canonical riboswitch model in synthetic biology. To facilitate DNN training, we synthesized and characterized in vivo a dataset of 91,534 toehold switches spanning 23 viral genomes and 906 human transcription factors. DNNs trained on nucleotide sequences outperformed (R2=0.43-0.70) previous state-of-the-art thermodynamic and kinetic models (R2=0.04-0.15) and allowed for human-understandable attention-visualizations (VIS4Map) to identify success and failure modes. This deep learning approach constitutes a major step forward in engineering and understanding of RNA synthetic biology.One Sentence SummaryDeep neural networks are used to improve functionality prediction and provide insights on toehold switches as a model for RNA synthetic biology tools.

Download Full-text

Leveraging high-throughput screening data, deep neural networks, and conditional generative adversarial networks to advance predictive toxicology

PLoS Computational Biology ◽

10.1371/journal.pcbi.1009135 ◽

2021 ◽

Vol 17 (7) ◽

pp. e1009135

Author(s):

Adrian J. Green ◽

Martin J. Mohlenkamp ◽

Jhuma Das ◽

Meenal Chaudhari ◽

Lisa Truong ◽

...

Keyword(s):

Neural Networks ◽

High Throughput ◽

Environmental Protection Agency ◽

High Throughput Screening ◽

Deep Neural Networks ◽

Generative Adversarial Networks ◽

Support Vector ◽

Large Set ◽

Toxicity Data

There are currently 85,000 chemicals registered with the Environmental Protection Agency (EPA) under the Toxic Substances Control Act, but only a small fraction have measured toxicological data. To address this gap, high-throughput screening (HTS) and computational methods are vital. As part of one such HTS effort, embryonic zebrafish were used to examine a suite of morphological and mortality endpoints at six concentrations from over 1,000 unique chemicals found in the ToxCast library (phase 1 and 2). We hypothesized that by using a conditional generative adversarial network (cGAN) or deep neural networks (DNN), and leveraging this large set of toxicity data we could efficiently predict toxic outcomes of untested chemicals. Utilizing a novel method in this space, we converted the 3D structural information into a weighted set of points while retaining all information about the structure. In vivo toxicity and chemical data were used to train two neural network generators. The first was a DNN (Go-ZT) while the second utilized cGAN architecture (GAN-ZT) to train generators to produce toxicity data. Our results showed that Go-ZT significantly outperformed the cGAN, support vector machine, random forest and multilayer perceptron models in cross-validation, and when tested against an external test dataset. By combining both Go-ZT and GAN-ZT, our consensus model improved the SE, SP, PPV, and Kappa, to 71.4%, 95.9%, 71.4% and 0.673, respectively, resulting in an area under the receiver operating characteristic (AUROC) of 0.837. Considering their potential use as prescreening tools, these models could provide in vivo toxicity predictions and insight into the hundreds of thousands of untested chemicals to prioritize compounds for HT testing.

Download Full-text

Separable Fully Connected Layers Improve Deep Learning Models For Genomics

10.1101/146431 ◽

2017 ◽

Cited By ~ 4

Author(s):

Amr Mohamed Alexandari ◽

Avanti Shrikumar ◽

Anshul Kundaje

Keyword(s):

Neural Networks ◽

Deep Neural Networks ◽

Biologically Inspired ◽

Outer Product ◽

Link Type ◽

Current State ◽

Conventional Models ◽

Model Setup ◽

Fully Connected

ABSTRACTConvolutional neural networks are rapidly gaining popularity in regulatory genomics. Typically, these networks have a stack of convolutional and pooling layers, followed by one or more fully connected layers. In genomics, the same positional patterns are often present across multiple convolutional channels. Therefore, in current state-of-the-art networks, there exists significant redundancy in the representations learned by standard fully connected layers. We present a new separable fully connected layer that learns a weights tensor that is the outer product of positional weights and cross-channel weights, thereby allowing the same positional patterns to be applied across multiple convolutional channels. Decomposing positional and cross-channel weights further enables us to readily impose biologically-inspired constraints on positional weights, such as symmetry. We also propose a novel regularizer and constraint that act on curvature in the positional weights. Using experiments on simulated and in vivo datasets, we show that networks that incorporate our separable fully connected layer outperform conventional models with analogous architectures and the same number of parameters. Additionally, our networks are more robust to hyperparameter tuning, have more informative gradients, and produce importance scores that are more consistent with known biology than conventional deep neural networks.AvailabilityImplementation: https://github.com/kundajelab/keras/tree/keras_1A gist illustrating model setup is at: goo.gl/gYooaa

Download Full-text

The Role of Polyphenols in the Modulation of Plasma Non-Enzymatic Antioxidant Capacity (NEAC)

International Journal for Vitamin and Nutrition Research ◽

10.1024/0300-9831/a000116 ◽

2012 ◽

Vol 82 (3) ◽

pp. 228-232 ◽

Cited By ~ 7

Author(s):

Mauro Serafini ◽

Giuseppa Morabito

Keyword(s):

Antioxidant Capacity ◽

Dietary Intervention ◽

Ex Vivo ◽

The Body ◽

Dietary Polyphenols ◽

Enzymatic Antioxidant ◽

Endogenous Antioxidant

Dietary polyphenols have been shown to scavenge free radicals, modulating cellular redox transcription factors in different in vitro and ex vivo models. Dietary intervention studies have shown that consumption of plant foods modulates plasma Non-Enzymatic Antioxidant Capacity (NEAC), a biomarker of the endogenous antioxidant network, in human subjects. However, the identification of the molecules responsible for this effect are yet to be obtained and evidences of an antioxidant in vivo action of polyphenols are conflicting. There is a clear discrepancy between polyphenols (PP) concentration in body fluids and the extent of increase of plasma NEAC. The low degree of absorption and the extensive metabolism of PP within the body have raised questions about their contribution to the endogenous antioxidant network. This work will discuss the role of polyphenols from galenic preparation, food extracts, and selected dietary sources as modulators of plasma NEAC in humans.

Download Full-text