scholarly journals Personalized deep learning of individual immunopeptidomes to identify neoantigens for cancer vaccines

2019 ◽  
Author(s):  
Ngoc Hieu Tran ◽  
Rui Qiao ◽  
Lei Xin ◽  
Xin Chen ◽  
Baozhen Shan ◽  
...  
Keyword(s):  
Mass Spectrometry ◽  
Deep Learning ◽  
De Novo ◽  
Mass Spectrometry Data ◽  
Main Role ◽  
Accurate Identification ◽  
Identification Rate ◽  
Cell Responses ◽  
First Time ◽  
Deep Learning Model

AbstractTumor-specific neoantigens play the main role for developing personal vaccines in cancer immunotherapy. We propose, for the first time, a personalized de novo sequencing workflow to identify HLA-I and HLA-II neoantigens directly and solely from mass spectrometry data. Our workflow trains a personal deep learning model on the immunopeptidome of an individual patient and then uses it to predict mutated neoantigens of that patient. This personalized learning and mass spectrometry-based approach enables comprehensive and accurate identification of neoantigens. We applied the workflow to datasets of five melanoma patients and substantially improved the accuracy and identification rate of de novo HLA peptides by 14.3% and 38.9%, respectively. This subsequently led to the identification of 10,440 HLA-I and 1,585 HLA-II new peptides that were not presented in existing databases. Most importantly, our workflow successfully discovered 17 neoantigens of both HLA-I and HLA-II, including those with validated T cell responses and those novel neoantigens that had not been reported in previous studies.

massNet: integrated processing and classification of spatially resolved mass spectrometry data using deep learning for rapid tumor delineation

2021 ◽  
Author(s):  
Walid M. Abdelmoula ◽  
Sylwia Stopka ◽  
Elizabeth C. Randall ◽  
Michael Regan ◽  
Jeffrey N. Agar ◽  
...  
Keyword(s):  
Mass Spectrometry ◽  
Deep Learning ◽  
Disease Diagnosis ◽  
Learning Model ◽  
Mass Spectrometry Data ◽  
Support Vector ◽  
Complex Nature ◽  
Peak Picking ◽  
Tumor Delineation ◽  
Deep Learning Model

Motivation: Mass spectrometry imaging (MSI) provides rich biochemical information in a label-free manner and therefore holds promise to substantially impact current practice in disease diagnosis. However, the complex nature of MSI data poses computational challenges in its analysis. The complexity of the data arises from its large size, high dimensionality, and spectral non-linearity. Preprocessing, including peak picking, has been used to reduce raw data complexity, however peak picking is sensitive to parameter selection that, perhaps prematurely, shapes the downstream analysis for tissue classification and ensuing biological interpretation. Results: We propose a deep learning model, massNet, that provides the desired qualities of scalability, non-linearity, and speed in MSI data analysis. This deep learning model was used, without prior preprocessing and peak picking, to classify MSI data from a mouse brain harboring a patient-derived tumor. The massNet architecture established automatically learning of predictive features, and automated methods were incorporated to identify peaks with potential for tumor delineation. The model's performance was assessed using cross-validation, and the results demonstrate higher accuracy and a 174-fold gain in speed compared to the established classical machine learning method, support vector machine. Availability and Implementation: The code is publicly available on GitHub.

scholarly journals Empirical Study and Improvement on Deep Transfer Learning for Human Activity Recognition

Sensors ◽  
2018 ◽  
Vol 19 (1) ◽  
pp. 57 ◽  
Author(s):  
Renjie Ding ◽  
Xue Li ◽  
Lanshun Nie ◽  
Jiazhen Li ◽  
Xiandong Si ◽  
...  
Keyword(s):  
Deep Learning ◽  
Empirical Study ◽  
Transfer Learning ◽  
Activity Recognition ◽  
Human Activity ◽  
Human Activity Recognition ◽  
Sensor Data ◽  
Accurate Identification ◽  
First Time ◽  
Deep Learning Model

Human activity recognition (HAR) based on sensor data is a significant problem in pervasive computing. In recent years, deep learning has become the dominating approach in this field, due to its high accuracy. However, it is difficult to make accurate identification for the activities of one individual using a model trained on data from other users. The decline on the accuracy of recognition restricts activity recognition in practice. At present, there is little research on the transferring of deep learning model in this field. This is the first time as we known, an empirical study was carried out on deep transfer learning between users with unlabeled data of target. We compared several widely-used algorithms and found that Maximum Mean Discrepancy (MMD) method is most suitable for HAR. We studied the distribution of features generated from sensor data. We improved the existing method from the aspect of features distribution with center loss and get better results. The observations and insights in this study have deepened the understanding of transfer learning in the activity recognition field and provided guidance for further research.

scholarly journals Identification of Novel Conopeptides and Distinct Gene Superfamilies in the Marine Cone Snail Conus quercinus

2021 ◽  
Vol 8 ◽  
Author(s):  
Han Zhang ◽  
Lei Wang ◽  
Xiang Yang ◽  
Zhiwei Lian ◽  
Yinbin Qiu ◽  
...  
Keyword(s):  
Mass Spectrometry ◽  
Prokaryotic Expression ◽  
Disulfide Bonds ◽  
De Novo ◽  
Animal Experiments ◽  
Cone Snail ◽  
Active Peptides ◽  
Neuroscience Research ◽  
First Time ◽  
Mass Spectrometry Mass Spectrometry

Conopeptides from the marine cone snails are a mixture of cysteine-rich active peptides, representing a unique and fertile resource for neuroscience research and drug discovery. The ConoServer database includes 8,134 conopeptides from 122 Conus species, yet many more natural conopeptides remain to be discovered. Here, we identified 517 distinct conopeptide precursors in Conus quercinus using de novo deep transcriptome sequencing. Ten of these precursors were verified at the protein level using liquid chromatography-mass spectrometry/mass spectrometry (LC-MS/MS). The combined gene and protein analyses revealed two novel gene superfamilies (Que-MNCLQ and Que-MAMNV), and three other gene superfamilies (N, P, and I1) were reported for the first time in C. quercinus. From the Que-MAMNV superfamily, a novel conotoxin, Que-0.1, was obtained via cloning and prokaryotic expression. We also documented a new purification process that can be used to induce the expression of conopeptides containing multiple pairs of disulfide bonds. The animal experiments showed that Que-0.1 strongly inhibited neuroconduction; the effects of Que-1.0 were 6.25 times stronger than those of pethidine hydrochloride. In addition, a new cysteine framework (CC-C-C-C-C-C-CC-C-C-C-C-C) was found in C. quercinus. These discoveries accelerate our understanding of conopeptide diversity in the genus, Conus and supply promising materials for medical research.

scholarly journals Combined Mass Spectrometry and Histopathology Imaging for Perioperative Tissue Assessment in Cancer Surgery

2021 ◽  
Vol 7 (10) ◽  
pp. 203
Author(s):  
Laura Connolly ◽  
Amoon Jamzad ◽  
Martin Kaufmann ◽  
Catriona E. Farquharson ◽  
Kevin Ren ◽  
...  
Keyword(s):  
Mass Spectrometry ◽  
Deep Learning ◽  
Image Registration ◽  
Assessment Tool ◽  
Desorption Electrospray Ionization ◽  
Mass Spectrometry Data ◽  
Ionization Mass ◽  
Prostate Needle Biopsy ◽  
Imaging Tool ◽  
Spatial Registration

Mass spectrometry is an effective imaging tool for evaluating biological tissue to detect cancer. With the assistance of deep learning, this technology can be used as a perioperative tissue assessment tool that will facilitate informed surgical decisions. To achieve such a system requires the development of a database of mass spectrometry signals and their corresponding pathology labels. Assigning correct labels, in turn, necessitates precise spatial registration of histopathology and mass spectrometry data. This is a challenging task due to the domain differences and noisy nature of images. In this study, we create a registration framework for mass spectrometry and pathology images as a contribution to the development of perioperative tissue assessment. In doing so, we explore two opportunities in deep learning for medical image registration, namely, unsupervised, multi-modal deformable image registration and evaluation of the registration. We test this system on prostate needle biopsy cores that were imaged with desorption electrospray ionization mass spectrometry (DESI) and show that we can successfully register DESI and histology images to achieve accurate alignment and, consequently, labelling for future training. This automation is expected to improve the efficiency and development of a deep learning architecture that will benefit the use of mass spectrometry imaging for cancer diagnosis.

scholarly journals PredMP: a web server for de novo prediction and visualization of membrane proteins

2018 ◽  
Vol 35 (4) ◽  
pp. 691-693 ◽  
Author(s):  
Sheng Wang ◽  
Shiyang Fei ◽  
Zongan Wang ◽  
Yu Li ◽  
Jinbo Xu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Lipid Bilayer ◽  
3D Model ◽  
De Novo ◽  
3D Structure ◽  
Supplementary Information ◽  
Model Generation ◽  
Transmembrane Topology ◽  
Distance Restraints ◽  
Deep Learning Model

Abstract Motivation PredMP is the first web service, to our knowledge, that aims at de novo prediction of the membrane protein (MP) 3D structure followed by the embedding of the MP into the lipid bilayer for visualization. Our approach is based on a high-throughput Deep Transfer Learning (DTL) method that first predicts MP contacts by learning from non-MPs and then predicts the 3D model of the MP using the predicted contacts as distance restraints. This algorithm is derived from our previous Deep Learning (DL) method originally developed for soluble protein contact prediction, which has been officially ranked No. 1 in CASP12. The DTL framework in our approach overcomes the challenge that there are only a limited number of solved MP structures for training the deep learning model. There are three modules in the PredMP server: (i) The DTL framework followed by the contact-assisted folding protocol has already been implemented in RaptorX-Contact, which serves as the key module for 3D model generation; (ii) The 1D annotation module, implemented in RaptorX-Property, is used to predict the secondary structure and disordered regions; and (iii) the visualization module to display the predicted MPs embedded in the lipid bilayer guided by the predicted transmembrane topology. Results Tested on 510 non-redundant MPs, our server predicts correct folds for ∼290 MPs, which significantly outperforms existing methods. Tested on a blind and live benchmark CAMEO from September 2016 to January 2018, PredMP can successfully model all 10 MPs belonging to the hard category. Availability and implementation PredMP is freely accessed on the web at http://www.predmp.com. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals DrugEx v2: De Novo Design of Drug Molecule by Pareto-based Multi-Objective Reinforcement Learning in Polypharmacology

2021 ◽  
Author(s):  
Xuhan Liu ◽  
Kai Ye ◽  
Herman Van Vlijmen ◽  
Michael T. M. Emmerich ◽  
Adriaan P. IJzerman ◽  
...  
Keyword(s):  
Deep Learning ◽  
Reinforcement Learning ◽  
Drug Target ◽  
De Novo ◽  
Multi Objective ◽  
Learning Framework ◽  
Drug Molecules ◽  
Pareto Ranking ◽  
Speed Up ◽  
Deep Learning Model

<p>In polypharmacology, ideal drugs are required to bind to multiple specific targets to enhance efficacy or to reduce resistance formation. Although deep learning has achieved breakthrough in drug discovery, most of its applications only focus on a single drug target to generate drug-like active molecules in spite of the reality that drug molecules often interact with more than one target which can have desired (polypharmacology) or undesired (toxicity) effects. In a previous study we proposed a new method named <i>DrugEx</i> that integrates an exploration strategy into RNN-based reinforcement learning to improve the diversity of the generated molecules. Here, we extended our <i>DrugEx</i> algorithm with multi-objective optimization to generate drug molecules towards more than one specific target (two adenosine receptors, A<sub>1</sub>AR and A<sub>2A</sub>AR, and the potassium ion channel hERG in this study). In our model, we applied an RNN as the <i>agent</i> and machine learning predictors as the <i>environment</i>, both of which were pre-trained in advance and then interplayed under the reinforcement learning framework. The concept of evolutionary algorithms was merged into our method such that <i>crossover</i> and <i>mutation</i> operations were implemented by the same deep learning model as the <i>agent</i>. During the training loop, the agent generates a batch of SMILES-based molecules. Subsequently scores for all objectives provided by the <i>environment</i> are used for constructing Pareto ranks of the generated molecules with non-dominated sorting and Tanimoto-based crowding distance algorithms. Here, we adopted GPU acceleration to speed up the process of Pareto optimization. The final reward of each molecule is calculated based on the Pareto ranking with the ranking selection algorithm. The agent is trained under the guidance of the reward to make sure it can generate more desired molecules after convergence of the training process. All in all we demonstrate generation of compounds with a diverse predicted selectivity profile toward multiple targets, offering the potential of high efficacy and lower toxicity.</p>

scholarly journals Elderly Fall Detection using Lightweight Convolution Deep Learning Model

2021 ◽  
Vol 12 (2) ◽  
pp. 2097-2103
Author(s):  
Neeraj Varshney
Keyword(s):  
Deep Learning ◽  
Daily Life ◽  
Fall Detection ◽  
Living Alone ◽  
Sensor Data ◽  
Routine Activity ◽  
Old People ◽  
Accurate Identification ◽  
Daily Life Activities ◽  
Deep Learning Model

Old people, who are living alone at home face serious problem of Falls while moving from one place to another and sometime life threading also. In order to prevent this situation, several fall monitoring systems based on sensor data were proposed. However, there was an issue of misclassification to identify the fall as daily life activities and also routine activity as fall. Towards this end, a deep learning based model is proposed in this paper by using the data of heart rate, BP and sugar level to identify fall along with other daily life activities like walking, running jogging etc. For accurate identification of fall accidents, a publicly accessible data collection and a lightly weighted CNN model are used. The model reports proposed and 98.21 % precision.

scholarly journals Recombinant expression and purification of adenocarcinoma GPR161 receptor

2019 ◽  
pp. 85-95
Author(s):  
Kasym Kasenovich Mukanov ◽  
Zhansaya Batyrbekkyzy Adish ◽  
Kanatbek Naizabekovich Mukantayev ◽  
Kanat Akhmetovich Tursunov ◽  
Zhuldyz Kydyrbekkyzy Kairova ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Mass Spectrometry ◽  
Monoclonal Antibodies ◽  
Intracellular Signaling ◽  
De Novo ◽  
Recombinant Expression ◽  
Protein A ◽  
Cellular Adhesion ◽  
Mass Spectrometry Data ◽  
Metal Affinity

Triple-negative breast cancer (TNBC) is an aggressive form of breast cancer and very few therapeutic options are currently available for its treatment. Interestingly, G-protein coupled receptor 161 (GPR161) is expressed in TNBC cells and can activate the mammalian target of the rapamycin complex 1 signaling pathway. GPR161 and Ras GTPase-activating-like protein, a protein involved in intracellular signaling, proliferation, and cellular adhesion, have been shown to genetically interact in human breast cancer cells. Targeting of GPR161 by monoclonal antibodies may therefore be a strategy to develop diagnostics and therapeutics for TNBC. Thus, to obtain such monoclonal antibodies, we synthesized the GPR161 gene de novo, cloned it into the pET32 expression plasmid, and used the recombinant plasmid to transform the competent BL21 (DE3) strain of Escherichia coli. The recombinant GPR161 gene was designed to contain an N-terminal thioredoxin tag, a thrombin site, the GPR161 sequence, and a C-terminalhexa-histidine tag to facilitate purification by metal-affinity chromatography. Following purification of the recombinant GPR161 (rGPR161) protein using a HisTrap column, we characterized the protein by Western blotting and mass spectrometry. The rGPR161 protein had a molecular mass of ~49 kDa and its identity as rGPR161 was confirmed by mass spectrometry data using the SwissProt database and the Mascot program. Future studies will involve the development of monoclonal antibodies using rGPR161 as the immunogen.

Sign in / Sign up

Export Citation Format

Share Document