Some remarks on protein attribute prediction and pseudo amino acid composition.

Illuminating G-Protein-Coupling Selectivity of GPCRs.

To understand the genetic drivers of immune recognition and evasion in colorectal cancer (CRC), we analyzed 1,211 CRC primary tumor samples, including 179 classified as microsatellite instability-high (MSI-high). This set includes The Cancer Genome Atlas CRC cohort of 592 samples, completed and analyzed here. MSI-high, a hypermutated, immunogenic subtype of CRC, had a high rate of significantly mutated genes in important immune modulating pathways and in the antigen presentation machinery, including biallelic losses of B2M and HLA genes due to copy number alterations and copy-neutral loss of heterozygosity (CN-LOH). WNT/β-catenin signaling genes were significantly mutated in all CRC subtypes, and activated WNT/β-catenin signaling was correlated with the absence of T-cell infiltration. This large-scale genomic analysis of CRC demonstrates that MSI-high cases frequently undergo an immunoediting process that provides them with genetic events allowing immune escape despite high mutational load and frequent lymphocytic infiltration, and furthermore, that CRC tumors have genetic and methylation events associated with activated WNT signaling and T-cell exclusion.

/pdf/genetic-mechanisms-of-immune-evasion-in-colorectal-cancer-278jmlyd7c.pdf

Genetic Mechanisms of Immune Evasion in Colorectal Cancer

Predicting protein subcellular localization is an important and difficult problem, particularly when query proteins may have the multiplex character, i.e., simultaneously exist at, or move between, two or more different subcellular location sites. Most of the existing protein subcellular location predictor can only be used to deal with the single-location or “singleplex” proteins. Actually, multiple-location or “multiplex” proteins should not be ignored because they usually posses some unique biological functions worthy of our special notice. By introducing the “multi-labeled learning” and “accumulation-layer scale”, a new predictor, called iLoc-Euk, has been developed that can be used to deal with the systems containing both singleplex and multiplex proteins. As a demonstration, the jackknife cross-validation was performed with iLoc-Euk on a benchmark dataset of eukaryotic proteins classified into the following 22 location sites: (1) acrosome, (2) cell membrane, (3) cell wall, (4) centriole, (5) chloroplast, (6) cyanelle, (7) cytoplasm, (8) cytoskeleton, (9) endoplasmic reticulum, (10) endosome, (11) extracellular, (12) Golgi apparatus, (13) hydrogenosome, (14) lysosome, (15) melanosome, (16) microsome (17) mitochondrion, (18) nucleus, (19) peroxisome, (20) spindle pole body, (21) synapse, and (22) vacuole, where none of proteins included has pairwise sequence identity to any other in a same subset. The overall success rate thus obtained by iLoc-Euk was 79%, which is significantly higher than that by any of the existing predictors that also have the capacity to deal with such a complicated and stringent system. As a user-friendly web-server, iLoc-Euk is freely accessible to the public at the web-site http://icpr.jci.edu.cn/bioinfo/iLoc-Euk. It is anticipated that iLoc-Euk may become a useful bioinformatics tool for Molecular Cell Biology, Proteomics, System Biology, and Drug Development Also, its novel approach will further stimulate the development of predicting other protein attributes.

/pdf/iloc-euk-a-multi-label-classifier-for-predicting-the-48a98epqnr.pdf

iLoc-Euk: a multi-label classifier for predicting the subcellular localization of singleplex and multiplex eukaryotic proteins.

The identification of interactions between drugs/compounds and their targets is crucial for the development of new drugs. In vitro screening experiments (i.e. bioassays) are frequently used for this purpose; however, experimental approaches are insufficient to explore novel drug-target interactions, mainly because of feasibility problems, as they are labour intensive, costly and time consuming. A computational field known as 'virtual screening' (VS) has emerged in the past decades to aid experimental drug discovery studies by statistically estimating unknown bio-interactions between compounds and biological targets. These methods use the physico-chemical and structural properties of compounds and/or target proteins along with the experimentally verified bio-interaction information to generate predictive models. Lately, sophisticated machine learning techniques are applied in VS to elevate the predictive performance. The objective of this study is to examine and discuss the recent applications of machine learning techniques in VS, including deep learning, which became highly popular after giving rise to epochal developments in the fields of computer vision and natural language processing. The past 3 years have witnessed an unprecedented amount of research studies considering the application of deep learning in biomedicine, including computational drug discovery. In this review, we first describe the main instruments of VS methods, including compound and protein features (i.e. representations and descriptors), frequently used libraries and toolkits for VS, bioactivity databases and gold-standard data sets for system training and benchmarking. We subsequently review recent VS studies with a strong emphasis on deep learning applications. Finally, we discuss the present state of the field, including the current challenges and suggest future directions. We believe that this survey will provide insight to the researchers working in the field of computational drug discovery in terms of comprehending and developing novel bio-prediction methods.

/pdf/recent-applications-of-deep-learning-and-machine-2jhuk5h77l.pdf

Recent applications of deep learning and machine intelligence on in silico drug discovery: methods, tools and databases.

The ability to predict the response of a cancer patient to a therapeutic agent is a major goal in modern oncology that should ultimately lead to personalized treatment. Existing approaches to predicting drug sensitivity rely primarily on profiling of cancer cell line panels that have been treated with different drugs and selecting genomic or functional genomic features to regress or classify the drug response. Here, we propose a dual-layer integrated cell line-drug network model, which uses both cell line similarity network (CSN) data and drug similarity network (DSN) data to predict the drug response of a given cell line using a weighted model. Using the Cancer Cell Line Encyclopedia (CCLE) and Cancer Genome Project (CGP) studies as benchmark datasets, our single-layer model with CSN or DSN and only a single parameter achieved a prediction performance comparable to the previously generated elastic net model. When using the dual-layer model integrating both CSN and DSN, our predicted response reached a 0.6 Pearson correlation coefficient with observed responses for most drugs, which is significantly better than the previous results using the elastic net model. We have also applied the dual-layer cell line-drug integrated network model to fill in the missing drug response values in the CGP dataset. Even though the dual-layer integrated cell line-drug network model does not specifically model mutation information, it correctly predicted that BRAF mutant cell lines would be more sensitive than BRAF wild-type cell lines to three MEK1/2 inhibitors tested.

/pdf/predicting-anticancer-drug-responses-using-a-dual-layer-12mbnah329.pdf

Predicting Anticancer Drug Responses Using a Dual-Layer Integrated Cell Line-Drug Network Model

Prediction of protein structural class for low-similarity sequences using support vector machine and PSI-BLAST profile.

An enduring challenge in personalized medicine is to select right drug for individual patients. Testing drugs on patients in large clinical trials is one way to assess their efficacy and toxicity, but it is impractical to test hundreds of drugs currently under development. Therefore the preclinical prediction model is highly expected as it enables prediction of drug response to hundreds of cell lines in parallel. Recently, two large-scale pharmacogenomic studies screened multiple anticancer drugs on over 1000 cell lines in an effort to elucidate the response mechanism of anticancer drugs. To this aim, we here used gene expression features and drug sensitivity data in Cancer Cell Line Encyclopedia (CCLE) to build a predictor based on Support Vector Machine (SVM) and a recursive feature selection tool. Robustness of our model was validated by cross-validation and an independent dataset, the Cancer Genome Project (CGP). Our model achieved good cross validation performance for most drugs in the Cancer Cell Line Encyclopedia (≥80 % accuracy for 10 drugs, ≥ 75 % accuracy for 19 drugs). Independent tests on eleven common drugs between CCLE and CGP achieved satisfactory performance for three of them, i.e., AZD6244, Erlotinib and PD-0325901, using expression levels of only twelve, six and seven genes, respectively. These results suggest that drug response could be effectively predicted from genomic features. Our model could be applied to predict drug response for some certain drugs and potentially play a complementary role in personalized medicine.

/pdf/anticancer-drug-sensitivity-prediction-in-cell-lines-from-4s5cmz3vs9.pdf

Anticancer drug sensitivity prediction in cell lines from baseline gene expression through recursive feature selection.

Computational prediction of protein structural class based solely on sequence data remains a challenging problem in protein science. Existing methods differ in the protein sequence representation models and prediction engines adopted. In this study, a powerful feature extraction method, which combines position-specific score matrix (PSSM) with auto covariance (AC) transformation, is introduced. Thus, a sample protein is represented by a series of discrete components, which could partially incorporate the long-range sequence order information and evolutionary information reflected from the PSI-BLAST profile. To verify the performance of our method, jackknife cross-validation tests are performed on four widely used benchmark datasets. Comparison of our results with existing methods shows that our method provides the state-of-the-art performance for structural class prediction. A Web server that implements the proposed method is freely available at http://202.194.133.5/xinxi/AAC_PSSM_AC/index.htm.

Accurate prediction of protein structural class using auto covariance transformation of PSI-BLAST profiles

Knowledge of apoptosis proteins plays an important role in understanding the mechanism of programmed cell death. Thus, annotating the function of apoptosis proteins is of significant value. Since the function of apoptosis proteins correlates with their subcellular location, the information about their subcellular location can be very useful in understanding their role in the process of programmed cell death. In the present study, we propose a novel sequence representation that incorporates the evolution information represented in the position-specific score matrices by the auto covariance transformation. Then the support vector machine classifier is adopted to predict subcellular location of apoptosis proteins. To verify the performance of this method, jackknife cross-validation tests are performed on three widely used benchmark datasets and results show that our approach achieves relatively high prediction accuracies over some classical methods.

Jun Wang

Papers

Predicting Anticancer Drug Responses Using a Dual-Layer Integrated Cell Line-Drug Network Model

Prediction of protein structural class for low-similarity sequences using support vector machine and PSI-BLAST profile.

Anticancer drug sensitivity prediction in cell lines from baseline gene expression through recursive feature selection.

Accurate prediction of protein structural class using auto covariance transformation of PSI-BLAST profiles

Prediction of Subcellular Location of Apoptosis Proteins Using Pseudo Amino Acid Composition: An Approach from Auto Covariance Transformation