DeepCrystal: a deep learning framework for sequence-based protein crystallization prediction

2018 ◽  
Vol 35 (13) ◽  
pp. 2216-2225 ◽  
Author(s):  
Abdurrahman Elbasir ◽  
Balasubramanian Moovarkumudalvan ◽  
Khalid Kunji ◽  
Prasanna R Kolatkar ◽  
Raghvendra Mall ◽  
...  
Keyword(s):  
Deep Learning ◽  
Protein Crystallization ◽  
Protein Sequences ◽  
Structural Features ◽  
Attrition Rate ◽  
Supplementary Information ◽  
Learning Framework ◽  
Average Improvement ◽  
Independent Test ◽  
Test Sets

Abstract Motivation Protein structure determination has primarily been performed using X-ray crystallography. To overcome the expensive cost, high attrition rate and series of trial-and-error settings, many in-silico methods have been developed to predict crystallization propensities of proteins based on their sequences. However, the majority of these methods build their predictors by extracting features from protein sequences, which is computationally expensive and can explode the feature space. We propose DeepCrystal, a deep learning framework for sequence-based protein crystallization prediction. It uses deep learning to identify proteins which can produce diffraction-quality crystals without the need to manually engineer additional biochemical and structural features from sequence. Our model is based on convolutional neural networks, which can exploit frequently occurring k-mers and sets of k-mers from the protein sequences to distinguish proteins that will result in diffraction-quality crystals from those that will not. Results Our model surpasses previous sequence-based protein crystallization predictors in terms of recall, F-score, accuracy and Matthew’s correlation coefficient (MCC) on three independent test sets. DeepCrystal achieves an average improvement of 1.4, 12.1% in recall, when compared to its closest competitors, Crysalis II and Crysf, respectively. In addition, DeepCrystal attains an average improvement of 2.1, 6.0% for F-score, 1.9, 3.9% for accuracy and 3.8, 7.0% for MCC w.r.t. Crysalis II and Crysf on independent test sets. Availability and implementation The standalone source code and models are available at https://github.com/elbasir/DeepCrystal and a web-server is also available at https://deeplearning-protein.qcri.org. Supplementary information Supplementary data are available at Bioinformatics online.

Deep learning to predict subtypes of poorly differentiated lung cancer from biopsy whole slide images.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 8536-8536
Author(s):  
Gouji Toyokawa ◽  
Fahdi Kanavati ◽  
Seiya Momosaki ◽  
Kengo Tateishi ◽  
Hiroaki Takeoka ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Deep Learning ◽  
Learning Model ◽  
Test Set ◽  
Cancer Subtypes ◽  
Independent Test ◽  
Poorly Differentiated ◽  
Test Sets ◽  
Deep Learning Model ◽  
Whole Slide Images

8536 Background: Lung cancer is the leading cause of cancer-related death in many countries, and its prognosis remains unsatisfactory. Since treatment approaches differ substantially based on the subtype, such as adenocarcinoma (ADC), squamous cell carcinoma (SCC) and small cell lung cancer (SCLC), an accurate histopathological diagnosis is of great importance. However, if the specimen is solely composed of poorly differentiated cancer cells, distinguishing between histological subtypes can be difficult. The present study developed a deep learning model to classify lung cancer subtypes from whole slide images (WSIs) of transbronchial lung biopsy (TBLB) specimens, in particular with the aim of using this model to evaluate a challenging test set of indeterminate cases. Methods: Our deep learning model consisted of two separately trained components: a convolutional neural network tile classifier and a recurrent neural network tile aggregator for the WSI diagnosis. We used a training set consisting of 638 WSIs of TBLB specimens to train a deep learning model to classify lung cancer subtypes (ADC, SCC and SCLC) and non-neoplastic lesions. The training set consisted of 593 WSIs for which the diagnosis had been determined by pathologists based on the visual inspection of Hematoxylin-Eosin (HE) slides and of 45 WSIs of indeterminate cases (64 ADCs and 19 SCCs). We then evaluated the models using five independent test sets. For each test set, we computed the receiver operator curve (ROC) area under the curve (AUC). Results: We applied the model to an indeterminate test set of WSIs obtained from TBLB specimens that pathologists had not been able to conclusively diagnose by examining the HE-stained specimens alone. Overall, the model achieved ROC AUCs of 0.993 (confidence interval [CI] 0.971-1.0) and 0.996 (0.981-1.0) for ADC and SCC, respectively. We further evaluated the model using five independent test sets consisting of both TBLB and surgically resected lung specimens (combined total of 2490 WSIs) and obtained highly promising results with ROC AUCs ranging from 0.94 to 0.99. Conclusions: In this study, we demonstrated that a deep learning model could be trained to predict lung cancer subtypes in indeterminate TBLB specimens. The extremely promising results obtained show that if deployed in clinical practice, a deep learning model that is capable of aiding pathologists in diagnosing indeterminate cases would be extremely beneficial as it would allow a diagnosis to be obtained sooner and reduce costs that would result from further investigations.

scholarly journals FANCY: fast estimation of privacy risk in functional genomics data

2020 ◽  
Author(s):  
Gamze Gürsoy ◽  
Charlotte M Brannon ◽  
Fabio C P Navarro ◽  
Mark Gerstein
Keyword(s):  
Functional Genomics ◽  
Supplementary Information ◽  
Cumulative Number ◽  
Rna Seq ◽  
Privacy Risk ◽  
Privacy Concerns ◽  
Privacy Leakage ◽  
Independent Test ◽  
Matlab Implementation ◽  
Test Sets

Abstract Motivation Functional genomics data are becoming clinically actionable, raising privacy concerns. However, quantifying privacy leakage via genotyping is difficult due to the heterogeneous nature of sequencing techniques. Thus, we present FANCY, a tool that rapidly estimates the number of leaking variants from raw RNA-Seq, ATAC-Seq and ChIP-Seq reads, without explicit genotyping. FANCY employs supervised regression using overall sequencing statistics as features and provides an estimate of the overall privacy risk before data release. Results FANCY can predict the cumulative number of leaking SNVs with an average 0.95 R2 for all independent test sets. We realize the importance of accurate prediction when the number of leaked variants is low. Thus, we develop a special version of the model, which can make predictions with higher accuracy when the number of leaking variants is low. Availability and implementation A python and MATLAB implementation of FANCY, as well as custom scripts to generate the features can be found at https://github.com/gersteinlab/FANCY. We also provide jupyter notebooks so that users can optimize the parameters in the regression model based on their own data. An easy-to-use webserver that takes inputs and displays results can be found at fancy.gersteinlab.org. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals lncRNA_Mdeep: An Alignment-Free Predictor for Distinguishing Long Non-Coding RNAs from Protein-Coding Transcripts by Multimodal Deep Learning

2020 ◽  
Vol 21 (15) ◽  
pp. 5222 ◽  
Author(s):  
Xiao-Nan Fan ◽  
Shao-Wu Zhang ◽  
Song-Yao Zhang ◽  
Jin-Jie Ni
Keyword(s):  
Deep Learning ◽  
Prediction Accuracy ◽  
Protein Coding ◽  
Learning Framework ◽  
Alignment Free ◽  
Independent Test ◽  
Non Coding Rnas ◽  
High Level ◽  
Fold Cross Validation ◽  
Human Complex

Long non-coding RNAs (lncRNAs) play crucial roles in diverse biological processes and human complex diseases. Distinguishing lncRNAs from protein-coding transcripts is a fundamental step for analyzing the lncRNA functional mechanism. However, the experimental identification of lncRNAs is expensive and time-consuming. In this study, we presented an alignment-free multimodal deep learning framework (namely lncRNA_Mdeep) to distinguish lncRNAs from protein-coding transcripts. LncRNA_Mdeep incorporated three different input modalities, then a multimodal deep learning framework was built for learning the high-level abstract representations and predicting the probability whether a transcript was lncRNA or not. LncRNA_Mdeep achieved 98.73% prediction accuracy in a 10-fold cross-validation test on humans. Compared with other eight state-of-the-art methods, lncRNA_Mdeep showed 93.12% prediction accuracy independent test on humans, which was 0.94%~15.41% higher than that of other eight methods. In addition, the results on 11 cross-species datasets showed that lncRNA_Mdeep was a powerful predictor for predicting lncRNAs.

scholarly journals lncRNA_Mdeep: an alignment-free predictor for long non-coding RNAs identification by multimodal deep learning

2020 ◽  
Author(s):  
Xiao-Nan Fan ◽  
Shao-Wu Zhang ◽  
Song-Yao Zhang ◽  
Jin-Jie Ni
Keyword(s):  
Deep Learning ◽  
Prediction Accuracy ◽  
Protein Coding ◽  
Learning Framework ◽  
Alignment Free ◽  
Independent Test ◽  
Non Coding Rnas ◽  
High Level ◽  
Fold Cross Validation ◽  
Human Complex

Abstract Background: Long non-coding RNAs (lncRNAs) play crucial roles in diverse biological processes and human complex diseases. Distinguishing lncRNAs from protein-coding transcripts is a fundamental step for analyzing lncRNA functional mechanism. However, the experimental identification of lncRNAs is expensive and time-consuming. Results: In this study, we present an alignment-free multimodal deep learning framework (namely lncRNA_Mdeep) to distinguish lncRNAs from protein-coding transcripts. LncRNA_Mdeep incorporates three different input modalities (i.e. OFH modality, k-mer modality, and sequence modality), then a multimodal deep learning framework is built for learning the high-level abstract representations and predicting the probability whether a transcript is lncRNA or not. Conclusions: LncRNA_Mdeep achieves 98.73% prediction accuracy in 10-fold cross-validation test on human. Compared with other eight state-of-the-art methods, lncRNA_Mdeep shows 93.12% prediction accuracy independent test on human, which is 0.94%~15.41% higher than that of other eight methods. In addition, the results on 11 cross-species datasets show that lncRNA_Mdeep is a powerful predictor for identifying lncRNAs. The source code can be downloaded from https://github.com/NWPU-903PR/lncRNA_Mdeep.

DeepFunc: A Deep Learning Framework for Accurate Prediction of Protein Functions from Protein Sequences and Interactions

PROTEOMICS ◽  
2019 ◽  
Vol 19 (12) ◽  
pp. 1900019 ◽  
Author(s):  
Fuhao Zhang ◽  
Hong Song ◽  
Min Zeng ◽  
Yaohang Li ◽  
Lukasz Kurgan ◽  
...  
Keyword(s):  
Deep Learning ◽  
Protein Sequences ◽  
Accurate Prediction ◽  
Learning Framework ◽  
Protein Functions

Designing a general method for predicting the regulatory relationships between long noncoding RNAs and protein-coding genes based on multi-omics characteristics

2019 ◽  
Vol 36 (7) ◽  
pp. 2025-2032
Author(s):  
Yuwei Zhang ◽  
Tianfei Yi ◽  
Huihui Ji ◽  
Guofang Zhao ◽  
Yang Xi ◽  
...  
Keyword(s):  
Noncoding Rna ◽  
Cross Validation ◽  
Machine Learning Algorithms ◽  
Supplementary Information ◽  
Protein Coding ◽  
Protein Coding Genes ◽  
Negative Results ◽  
Independent Test ◽  
Multiple Characteristics ◽  
Test Sets

Abstract Motivation Long noncoding RNA (lncRNA) has been verified to interact with other biomolecules especially protein-coding genes (PCGs), thus playing essential regulatory roles in life activities and disease development. However, the inner mechanisms of most lncRNA–PCG relationships are still unclear. Our study investigated the characteristics of true lncRNA–PCG relationships and constructed a novel predictor with machine learning algorithms. Results We obtained the 307 true lncRNA-PCG pairs from database and found that there are significant differences in multiple characteristics between true and random lncRNA–PCG sets. Besides, 3-fold cross-validation and prediction results on independent test sets show the great AUC values of LR, SVM and RF, among which RF has the best performance with average AUC 0.818 for cross-validation, 0.823 and 0.853 for two independent test sets, respectively. In case study, some candidate lncRNA–PCG relationships in colorectal cancer were found and HOTAIR–COMP interaction was specially exemplified. The proportion of the reported pairs in the predicted positive results was significantly higher than that in negative results (P < 0.05). Supplementary information Supplementary data are available at Bioinformatics online.

CATHER: a novel threading algorithm with predicted contacts

2019 ◽  
Vol 36 (7) ◽  
pp. 2119-2125 ◽  
Author(s):  
Zongyang Du ◽  
Shuo Pan ◽  
Qi Wu ◽  
Zhenling Peng ◽  
Jianyi Yang
Keyword(s):  
Deep Learning ◽  
Protein Structure ◽  
Structure Prediction ◽  
Supplementary Information ◽  
Supplementary Data ◽  
Contact Map ◽  
Test Set ◽  
Benchmark Tests ◽  
Independent Test ◽  
Push Forward

Abstract Motivation Threading is one of the most effective methods for protein structure prediction. In recent years, the increasing accuracy in protein contact map prediction opens a new avenue to improve the performance of threading algorithms. Several preliminary studies suggest that with predicted contacts, the performance of threading algorithms can be improved greatly. There is still much room to explore to make better use of predicted contacts. Results We have developed a new contact-assisted threading algorithm named CATHER using both conventional sequential profiles and contact map predicted by a deep learning-based algorithm. Benchmark tests on an independent test set and the CASP12 targets demonstrated that CATHER made significant improvement over other methods which only use either sequential profile or predicted contact map. Our method was ranked at the Top 10 among all 39 participated server groups on the 32 free modeling targets in the blind tests of the CASP13 experiment. These data suggest that it is promising to push forward the threading algorithms by using predicted contacts. Availability and implementation http://yanglab.nankai.edu.cn/CATHER/. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals CLPred: a sequence-based protein crystallization predictor using BLSTM neural network

2020 ◽  
Vol 36 (Supplement_2) ◽  
pp. i709-i717
Author(s):  
Wenjing Xuan ◽  
Ning Liu ◽  
Neng Huang ◽  
Yaohang Li ◽  
Jianxin Wang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Long Range ◽  
Short Term Memory ◽  
Protein Crystallization ◽  
Predictive Performance ◽  
Attrition Rate ◽  
Multiple Time ◽  
Interaction Patterns ◽  
Range Interaction

Abstract Motivation Determining the structures of proteins is a critical step to understand their biological functions. Crystallography-based X-ray diffraction technique is the main method for experimental protein structure determination. However, the underlying crystallization process, which needs multiple time-consuming and costly experimental steps, has a high attrition rate. To overcome this issue, a series of in silico methods have been developed with the primary aim of selecting the protein sequences that are promising to be crystallized. However, the predictive performance of the current methods is modest. Results We propose a deep learning model, so-called CLPred, which uses a bidirectional recurrent neural network with long short-term memory (BLSTM) to capture the long-range interaction patterns between k-mers amino acids to predict protein crystallizability. Using sequence only information, CLPred outperforms the existing deep-learning predictors and a vast majority of sequence-based diffraction-quality crystals predictors on three independent test sets. The results highlight the effectiveness of BLSTM in capturing non-local, long-range inter-peptide interaction patterns to distinguish proteins that can result in diffraction-quality crystals from those that cannot. CLPred has been steadily improved over the previous window-based neural networks, which is able to predict crystallization propensity with high accuracy. CLPred can also be improved significantly if it incorporates additional features from pre-extracted evolutional, structural and physicochemical characteristics. The correctness of CLPred predictions is further validated by the case studies of Sox transcription factor family member proteins and Zika virus non-structural proteins. Availability and implementation https://github.com/xuanwenjing/CLPred.

scholarly journals DHS-Crystallize: Deep-Hybrid-Sequence based method for predicting protein Crystallization

2020 ◽  
Author(s):  
Azadeh Alavi ◽  
David B. Ascher
Keyword(s):  
Protein Crystallization ◽  
Attrition Rate ◽  
Gradient Boosting ◽  
Trial And Error ◽  
Crystallization Property ◽  
X Ray ◽  
X Ray Crystallography ◽  
Gradient Boosting Machine ◽  
Test Sets ◽  
High Attrition Rate

AbstractThe key method for determining the structure of a protein to date is X-ray crystallography, which is a very expensive technique that suffers from high attrition rate. On the contrary, a sequence-based predictor that is capable of accurately determining protein crystallization property, would not only overcome such limitations, but also would reduce the trial-and-error settings required to perform crystallization. In this work, to predict protein crystallizability, we have developed a novel sequence-based hybrid method that employs two separate, yet fully automated, concepts for extracting features from protein sequences. Specifically, we use a deep convolutional neural network on a publicly available dataset to extract descriptive features directly from the sequences, then fuse such feature with structural-and-physio-chemical driven features (such as amino-acid composition or AAIndex-based physicochemical properties). Dimentionality reduction is then performed on the resulting features and the output vectors are applied to train optimized gradient boosting machine (XGBoostt). We evaluate our method through three publicly available test sets, and show that our proposed DHS-Crystallize algorithm outperforms state-of-the-art methods, and achieves higher performance compared to using DCNN-deriven features, or structural-and-physio-chemical driven features alone.

scholarly journals BCrystal: an interpretable sequence-based protein crystallization predictor

2019 ◽  
Vol 36 (5) ◽  
pp. 1429-1438 ◽  
Author(s):  
Abdurrahman Elbasir ◽  
Raghvendra Mall ◽  
Khalid Kunji ◽  
Reda Rawi ◽  
Zeyaul Islam ◽  
...  
Keyword(s):  
Correlation Coefficient ◽  
Solvent Accessibility ◽  
Protein Crystallization ◽  
Protein Structures ◽  
Attrition Rate ◽  
Supplementary Information ◽  
Gradient Boosting ◽  
Relative Solvent Accessibility ◽  
X Ray Crystallography ◽  
Matthew’S Correlation Coefficient

Abstract Motivation X-ray crystallography has facilitated the majority of protein structures determined to date. Sequence-based predictors that can accurately estimate protein crystallization propensities would be highly beneficial to overcome the high expenditure, large attrition rate, and to reduce the trial-and-error settings required for crystallization. Results In this study, we present a novel model, BCrystal, which uses an optimized gradient boosting machine (XGBoost) on sequence, structural and physio-chemical features extracted from the proteins of interest. BCrystal also provides explanations, highlighting the most important features for the predicted crystallization propensity of an individual protein using the SHAP algorithm. On three independent test sets, BCrystal outperforms state-of-the-art sequence-based methods by more than 12.5% in accuracy, 18% in recall and 0.253 in Matthew’s correlation coefficient, with an average accuracy of 93.7%, recall of 96.63% and Matthew’s correlation coefficient of 0.868. For relative solvent accessibility of exposed residues, we observed higher values to associate positively with protein crystallizability and the number of disordered regions, fraction of coils and tripeptide stretches that contain multiple histidines associate negatively with crystallizability. The higher accuracy of BCrystal enables it to accurately screen for sequence variants with enhanced crystallizability. Availability and implementation Our BCrystal webserver is at https://machinelearning-protein.qcri.org/ and source code is available at https://github.com/raghvendra5688/BCrystal. Supplementary information Supplementary data are available at Bioinformatics online.

Sign in / Sign up

Export Citation Format

Share Document