Secondary structure specific simpler prediction models for protein backbone angles.

MOTIVATION: Protein backbone angle prediction has achieved significant accuracy improvement with the development of deep learning methods. Usually the same deep learning model is used in making prediction for all residues regardless of the categories of secondary structures they belong to. In this paper, we propose to train separate deep learning models for each category of secondary structures. Machine learning methods strive to achieve generality over the training examples and consequently loose accuracy. In this work, we explicitly exploit classification knowledge to restrict generalisation within the specific class of training examples. This is to compensate the loss of generalisation by exploiting specialisation knowledge in an informed way. RESULTS: The new method named SAP4SS obtains mean absolute error (MAE) values of 15.59, 18.87, 6.03, and 21.71 respectively for four types of backbone angles [Formula: see text], [Formula: see text], [Formula: see text], and [Formula: see text]. Consequently, SAP4SS significantly outperforms existing state-of-the-art methods SAP, OPUS-TASS, and SPOT-1D: the differences in MAE for all four types of angles are from 1.5 to 4.1% compared to the best known results. AVAILABILITY: SAP4SS along with its data is available from https://gitlab.com/mahnewton/sap4ss .

Distance plus attention for binding affinity prediction.

Protein-ligand binding affinity plays a pivotal role in drug development, particularly in identifying potential ligands for target disease-related proteins. Accurate affinity predictions can significantly reduce both the time and cost involved in drug development. However, highly precise affinity prediction remains a research challenge. A key to improve affinity prediction is to capture interactions between proteins and ligands effectively. Existing deep-learning-based computational approaches use 3D grids, 4D tensors, molecular graphs, or proximity-based adjacency matrices, which are either resource-intensive or do not directly represent potential interactions. In this paper, we propose atomic-level distance features and attention mechanisms to capture better specific protein-ligand interactions based on donor-acceptor relations, hydrophobicity, and π -stacking atoms. We argue that distances encompass both short-range direct and long-range indirect interaction effects while attention mechanisms capture levels of interaction effects. On the very well-known CASF-2016 dataset, our proposed method, named Distance plus Attention for Affinity Prediction (DAAP), significantly outperforms existing methods by achieving Correlation Coefficient (R) 0.909, Root Mean Squared Error (RMSE) 0.987, Mean Absolute Error (MAE) 0.745, Standard Deviation (SD) 0.988, and Concordance Index (CI) 0.876. The proposed method also shows substantial improvement, around 2% to 37%, on five other benchmark datasets. The program and data are publicly available on the website https://gitlab.com/mahnewton/daap. Scientific Contribution StatementThis study innovatively introduces distance-based features to predict protein-ligand binding affinity, capitalizing on unique molecular interactions. Furthermore, the incorporation of protein sequence features of specific residues enhances the model's proficiency in capturing intricate binding patterns. The predictive capabilities are further strengthened through the use of a deep learning architecture with attention mechanisms, and an ensemble approach, averaging the outputs of five models, is implemented to ensure robust and reliable predictions.

Spiral search: a hydrophobic-core directed local search for simplified PSP on 3D FCC lattice.

BACKGROUND: Protein structure prediction is an important but unsolved problem in biological science. Predicted structures vary much with energy functions and structure-mapping spaces. In our simplified ab initio protein structure prediction methods, we use hydrophobic-polar (HP) energy model for structure evaluation, and 3-dimensional face-centred-cubic lattice for structure mapping. For HP energy model, developing a compact hydrophobic-core (H-core) is essential for the progress of the search. The H-core helps find a stable structure with the lowest possible free energy. RESULTS: In order to build H-cores, we present a new Spiral Search algorithm based on tabu-guided local search. Our algorithm uses a novel H-core directed guidance heuristic that squeezes the structure around a dynamic hydrophobic-core centre. We applied random walks to break premature H-cores and thus to avoid early convergence. We also used a novel relay-restart technique to handle stagnation. CONCLUSIONS: We have tested our algorithms on a set of benchmark protein sequences. The experimental results show that our spiral search algorithm outperforms the state-of-the-art local search algorithms for simplified protein structure prediction. We also experimentally show the effectiveness of the relay-restart.

The road not taken: retreat and diverge in local search for simplified protein structure prediction.

BACKGROUND: Given a protein's amino acid sequence, the protein structure prediction problem is to find a three dimensional structure that has the native energy level. For many decades, it has been one of the most challenging problems in computational biology. A simplified version of the problem is to find an on-lattice self-avoiding walk that minimizes the interaction energy among the amino acids. Local search methods have been preferably used in solving the protein structure prediction problem for their efficiency in finding very good solutions quickly. However, they suffer mainly from two problems: re-visitation and stagnancy. RESULTS: In this paper, we present an efficient local search algorithm that deals with these two problems. During search, we select the best candidate at each iteration, but store the unexplored second best candidates in a set of elite conformations, and explore them whenever the search faces stagnation. Moreover, we propose a new non-isomorphic encoding for the protein conformations to store the conformations and to check similarity when applied with a memory based search. This new encoding helps eliminate conformations that are equivalent under rotation and translation, and thus results in better prevention of re-visitation. CONCLUSION: On standard benchmark proteins, our algorithm significantly outperforms the state-of-the art approaches for Hydrophobic-Polar energy models and Face Centered Cubic Lattice.

Real-to-bin conversion for protein residue distances.

Protein Structure Prediction (PSP) has achieved significant progress lately. Prediction of inter-residue distances by machine learning and their exploitation during the conformational search is largely among the critical factors behind the progress. Real values than bin probabilities could more naturally represent inter-residue distances, while the latter, via spline curves more naturally helps obtain differentiable objective functions than the former. Consequently, PSP methods that exploit predicted binned distances perform better than those that exploit predicted real-valued distances. To leverage the advantage of bin probabilities in getting differentiable objective functions, in this work, we propose techniques to convert real-valued distances into distance bin probabilities. Using standard benchmark proteins, we then show that our real-to-bin converted distances help PSP methods obtain three-dimensional structures with 4%-16% better root mean squared deviation (RMSD), template modeling score (TM-Score), and global distance test (GDT) values than existing similar PSP methods. Our proposed PSP method is named real to bin (R2B) inter-residue distance predictor, and its code is available from https://gitlab.com/mahnewton/r2b.

A structural and surface approach to size and shape control of sulfur-modified undoped and Fe-doped TiO2 anatase nano-materials.

In situ synchrotron X-ray diffraction and diffuse reflectance infrared spectroscopy (DRIFTS) are combined to study the influence of sulfur on the crystallization of pure and Fe-doped titania nano-materials. Using these two tools we have investigated the effect of sulfur on the nucleation and growth processes of the anatase polymorph from amorphous powders and show how the addition of sulfur controls the primary particle size and shape of the materials. As well known, sulfur leads to the stabilization of the oxide particle size against sintering during thermal treatments and here we interpret the physico-chemical basis of such behaviour as an exclusive effect on grain growth kinetics, in turn linked to the dehydration of the surface layers of the materials. In addition this work shows that the presence of sulfur also affects the shape of the anatase particles, favouring the existence of (101)-type surfaces and elongated (along the c crystallographic axis) particles. This combined analysis of how sulfur influences morphological aspects of the anatase phase as it grows provides a basis for understanding of surface and chemical properties of anatase nano-powders that are highly dependent upon particle morphology.

Enhancing protein contact map prediction accuracy via ensembles of inter-residue distance predictors.

Protein contact maps capture coevolutionary interactions between amino acid residue pairs that are spatially within certain proximity threshold. Predicted contact maps are used in many protein related problems that include drug design, protein design, protein function prediction, and protein structure prediction. Contact map prediction has achieved significant progress lately but still further challenges remain with prediction of contacts between residues that are separated in the amino acid residue sequence by large numbers of other residues. In this paper, with experimental results on 5 standard benchmark datasets that include membrane proteins, we show that contact map prediction could be significantly enhanced by using ensembles of various state-of-the-art short distance predictors and then by converting predicted distances into contact probabilities. Our program along with its data is available from https://gitlab.com/mahnewton/ecp.

Enhancing protein inter-residue real distance prediction by scrutinising deep learning models.

Protein structure prediction (PSP) has achieved significant progress lately via prediction of inter-residue distances using deep learning models and exploitation of the predictions during conformational search. In this context, prediction of large inter-residue distances and also prediction of distances between residues separated largely in the protein sequence remain challenging. To deal with these challenges, state-of-the-art inter-residue distance prediction algorithms have used large sets of coevolutionary and non-coevolutionary features. In this paper, we argue that the more the types of features used, the more the kinds of noises introduced and then the deep learning model has to overcome the noises to improve the accuracy of the predictions. Also, multiple features capturing similar underlying characteristics might not necessarily have significantly better cumulative effect. So we scrutinise the feature space to reduce the types of features to be used, but at the same time, we strive to improve the prediction accuracy. Consequently, for inter-residue real distance prediction, in this paper, we propose a deep learning model named scrutinised distance predictor (SDP), which uses only 2 coevolutionary and 3 non-coevolutionary features. On several sets of benchmark proteins, our proposed SDP method improves mean Local Distance Different Test (LDDT) scores at least by 10% over existing state-of-the-art methods. The SDP program along with its data is available from the website https://gitlab.com/mahnewton/sdp .

Constraint Guided Beta-Sheet Refinement for Protein Structure Prediction.

Protein structure prediction (PSP) is a crucial issue in Bioinformatics. PSP has its important use in many vital research areas that include drug discovery. One of the important intermediate steps in PSP is predicting a protein's beta-sheet structures. Because of non-local interactions among numerous irregular areas in beta-sheets, their highly accurate prediction is challenging. The challenge is compounded when a given protein's structure has a large number of beta-sheets. In this paper, we specifically refine the beta-sheets of a protein structure by using a local search method. Then, we use another local search method to refine the full structure. Our search methods analyse residue-residue distance-based scores and apply geometric restrictions gained from deep learning models. Moreover, our search methods recognise the regions of the current conformations prompting the nether scores and generate neighbouring conformations focusing on that identified regions and making alterations there. On a set of standard 88 proteins of various sizes between 46 and 450 residues, our method successfully outperforms state-of-the-art PSP search algorithms. The improvements are more than 12% in average root mean squared distance (RMSD), template modelling score (TM-score), and global distance test (GDT) values.

A stacked meta-ensemble for protein inter-residue distance prediction.

Predicted inter-residue distances are a key behind recent success in high quality protein structure prediction (PSP). However, prediction of both short and long distance values together is challenging. Consequently, predicted short distances are mostly used by existing PSP methods. In this paper, we use a stacked meta-ensemble method to combine deep learning models trained for different ranges of real-valued distances. On five benchmark sets of proteins, our proposed inter-residue distance prediction method improves mean Local Distance Different Test (LDDT) scores at least by 5% over existing such methods. Moreover, using a real-valued distance based conformational search algorithm, we also show that predicted long distances help obtain significantly better protein conformations than when only predicted short distances are used. Our method is named meta-ensemble for distance prediction (MDP) and its program is available from https://gitlab.com/mahnewton/mdp.

Quantitative Toxicity Prediction via Meta Ensembling of Multitask Deep Learning Models.

Toxicity prediction using quantitative structure-activity relationship has achieved significant progress in recent years. However, most existing machine learning methods in toxicity prediction utilize only one type of feature representation and one type of neural network, which essentially restricts their performance. Moreover, methods that use more than one type of feature representation struggle with the aggregation of information captured within the features since they use predetermined aggregation formulas. In this paper, we propose a deep learning framework for quantitative toxicity prediction using five individual base deep learning models and their own base feature representations. We then propose to adopt a meta ensemble approach using another separate deep learning model to perform aggregation of the outputs of the individual base deep learning models. We train our deep learning models in a weighted multitask fashion combining four quantitative toxicity data sets of LD50, IGC50, LC50, and LC50-DM and minimizing the root-mean-square errors. Compared to the current state-of-the-art toxicity prediction method TopTox on LD50, IGC50, and LC50-DM, that is, three out of four data sets, our method, respectively, obtains 5.46, 16.67, and 6.34% better root-mean-square errors, 6.41, 11.80, and 12.16% better mean absolute errors, and 5.21, 7.36, and 2.54% better coefficients of determination. We named our method QuantitativeTox, and our implementation is available from the GitHub repository https://github.com/Abdulk084/QuantitativeTox.

Enhancing protein backbone angle prediction by using simpler models of deep neural networks.

Protein structure prediction is a grand challenge. Prediction of protein structures via the representations using backbone dihedral angles has recently achieved significant progress along with the on-going surge of deep neural network (DNN) research in general. However, we observe that in the protein backbone angle prediction research, there is an overall trend to employ more and more complex neural networks and then to throw more and more features to the neural networks. While more features might add more predictive power to the neural network, we argue that redundant features could rather clutter the scenario and more complex neural networks then just could counterbalance the noise. From artificial intelligence and machine learning perspectives, problem representations and solution approaches do mutually interact and thus affect performance. We also argue that comparatively simpler predictors can more easily be reconstructed than the more complex ones. With these arguments in mind, we present a deep learning method named Simpler Angle Predictor (SAP) to train simpler DNN models that enhance protein backbone angle prediction. We then empirically show that SAP can significantly outperform existing state-of-the-art methods on well-known benchmark datasets: for some types of angles, the differences are 6-8 in terms of mean absolute error (MAE). The SAP program along with its data is available from the website https://gitlab.com/mahnewton/sap .

Tumourigenic canine osteosarcoma cell lines associated with frizzled-6 up-regulation and enhanced side population cell frequency.

An increased serum alkaline phosphatase concentration is known to be associated with a negative prognosis in canine and human osteosarcoma. To expand upon previous studies regarding the biological relevance of increased serum alkaline phosphatase as a negative prognostic factor, xenogeneic heterotopic transplants were performed using six canine primary osteosarcoma cell lines generated from patients with differing serum alkaline phosphatase concentrations (three normal and three increased). Three of the six cell lines were capable of generating tumours and tumour formation was independent of the serum alkaline phosphatase status of the cell line. Microarray analysis identified 379 genes as being differentially expressed between the tumourigenic and non-tumourigenic cell lines. Frizzled-6 was upregulated to the greatest extent (7.78-fold) in tumourigenic cell lines compared with non-tumourigenic cell lines. Frizzled-6, a co-receptor for Wnt ligands has been associated with enhanced tumour-initiating cells and poor prognosis for other tumours. The increased expression of frizzled-6 was confirmed by quantitative reverse transcription polymerase chain reaction (QPCR) and Western blot analysis. Additionally, the tumourigenic cell lines also had an increase in the percentage of side population cells compared with non-tumourigenic cell lines (5.89% versus 1.58%, respectively). There were no differences in tumourigenicity, frizzled-6 or percentage of side population cells noted between osteosarcoma cell lines generated from patients of differing serum alkaline phosphatase concentration. However, to our knowledge this is the first study to identified frizzled-6 as a possible marker of osteosarcoma cell populations with enhanced tumourigenicity and side population cells. Future work will focus on defining the role of frizzled-6 in osteosarcoma tumourigenesis and tumour-initiating cells.

Intestinal neoplasia in the ApcMin mouse: independence from the microbial and natural killer (beige locus) status.

We have tested the hypothesis that enteric bacteria are necessary for formation of intestinal adenomas in C57BL/6-ApcMin/+ mouse. Germ-free mice developed 2-fold fewer adenomas than conventional controls in the medial small intestine (7.3 versus 14.9; P < 0.003), but there were no significant differences in the rest of the intestinal tract. We conclude that microbial status does not strongly alter the adenoma phenotype in this mouse model of familial adenomatous polyposis. In parallel, we have found that C57BL/6-ApcMin/+ mice mutated at the beige locus, which controls natural killer activity, are also unaltered in adenoma multiplicity.

Chemopreventive efficacy of combined piroxicam and difluoromethylornithine treatment of Apc mutant Min mouse adenomas, and selective toxicity against Apc mutant embryos.

Genetic knockout or pharmacological inhibition of cyclooxygenase-2 decreases the number and size of adenomas in mouse models of familial adenomatous polyposis. Epidemiological and clinical studies in humans indicate that the entire class of nonsteroidal anti-inflammatory drugs (NSAIDs) that inhibit both COX-1 and COX-2 enzymes are promising colon cancer chemopreventive agents. We used the Apc mutant Min mouse model to test combinations of agents that might maximize preventive benefit with minimal toxicity because they act via different mechanisms. Min mice (n = 144) were exposed to low doses of the nonselective COX inhibitor piroxicam and the ornithine decarboxylase (ODC) inhibitor difluoromethylornithine (DFMO), beginning at the time they were weaned and continuing throughout the duration of the experiment. Piroxicam at 12, 25, and 50 ppm in the diet caused dose-dependent decreases in the number of tumors in the middle and distal portions of the small intestine. This decrease in tumor multiplicity was associated with a striking decrease in the size of those tumors that did grow out. In contrast, none of the doses of piroxicam alone decreased tumor multiplicity in the proximal portion of the intestine (duodenum). Exposure to DFMO (0.5 or 1.0% in water) caused a dose-dependent decrease in tumor multiplicity in the middle and distal portions of the small intestine. However, this decreased multiplicity was not associated with a striking decrease in the size of the tumors. Combined treatment of mice with piroxicam plus DFMO was much more effective than either agent alone and resulted in a significant number of mice totally free of any intestinal adenomas (P < 0.001), in contrast to the 100% incidence and high multiplicity in control Min mice. In addition to this profound effectiveness in reducing tumor number, the few residual tumors in mice treated with the combined drugs were markedly smaller in size than tumors that arose from control Min mice. These experiments suggest that selective COX-2 inhibition combined with ODC inhibition is a very promising approach for colon cancer prevention. These COX-2 and ODC inhibitor drugs were not overtly toxic at the doses used when administered to mice after weaning. However, when treatment was begun in utero, the Mendelian expected progeny ratio of 1:1 that we routinely obtained in untreated control litters was no longer observed. Apc(min)/+ progeny of pregnant dams treated with piroxicam and/or DFMO were reduced in number and their ratio to Apc+/+ progeny was decreased to approximately 0.28:1. Thus, these agents are effective against adenomas that have homozygous mutation of the APC gene and also select against fetuses bearing a heterozygous mutation in the APC gene.

p16/pRb pathway alterations are required for bypassing senescence in human prostate epithelial cells.

The cell cycle regulatory genes p16/CDKN2 and RB are frequently deleted in prostate cancers. In this study, we examined the role of alterations in p16 and pRb during growth, senescence, and immortalization in vitro of human prostate epithelial cells (HPECs). HPECs are established from normal prostate tissues and cultured on collagen-coated dishes. Our results show that p16 is reproducibly elevated at senescence in HPECs. HPECs are immortalized using human papilloma virus 16 E6 and/or E7 as molecular tools to inactivate p53 and/or pRb, respectively. Immortalization occurs infrequently in this system and only after a latent period during which additional genetic/epigenetic changes are thought to occur. Notably, all of the E6-immortalized HPEC lines but none of the E7 lines show inactivation of p16/CDKN2 (by deletion, methylation, or mutation) in association with immortalization. In contrast, E7 lines, in which pRb function is abrogated by E7 binding, retain the high levels of p16 observed at senescence. Thus, all lines show either a p16 or pRb inactivation. Analysis of six independent lines from metastatic prostate cancers reveals a similar loss of either p16 or pRb. Comparative genomic hybridization of HPECs shows that gains of chromosomes 5q, 8q, and 20 are nonrandomly associated with bypassing senescence (probability = 0.95). These results suggest that high levels of the cyclin-dependent kinase inhibitor p16 mediate senescence G1 arrest in HPECs and that bypassing this block by a p16/pRb pathway alteration is required for immortalization in vitro and possibly tumorigenesis in vivo. Our results further indicate that inactivation of the p16/pRb pathway alone is not sufficient to immortalize HPECs and that additional genetic alterations are required for this process.

Chemoprevention of spontaneous intestinal adenomas in the Apc Min mouse model by the nonsteroidal anti-inflammatory drug piroxicam.

C57BL/6J-Min/+mice (n = 56), heterozygous for a nonsense mutation in the Apc gene, were randomized at weaning to seven groups, including groups treated with piroxicam at 0, 50, 100, and 200 ppm in the AIN93G diet. After only 6 weeks of treatment, intestinal adenomas and aberrant crypt foci were counted, and serum levels of piroxicam and thromboxane B2 were quantitated. Tumor multiplicity was decreased in a dose-dependent manner from 17.3 +/- 2.7 in the control to 2.1 +/- 1.1 (12%) in the high-dose piroxicam group (P < 0.001). Thromboxane B2 levels in plasma also decreased monotonically in parallel to the decrease in tumor multiplicity, consistent with the prostaglandin inhibitory effect of piroxicam. The Min mouse model demonstrates that the nonsteroidal anti-inflammatory drug piroxicam has strong biological and therapeutic effects, potentially useful for prevention of the early adenoma stage of tumor development.

Osteosarcoma tissues and cell lines from patients with differing serum alkaline phosphatase concentrations display minimal differences in gene expression patterns.

Serum alkaline phosphatase (ALP) concentration is a prognostic factor for osteosarcoma in multiple studies, although its biological significance remains incompletely understood. To determine whether gene expression patterns differed in osteosarcoma from patients with differing serum ALP concentrations, microarray analysis was performed on 18 primary osteosarcoma samples and six osteosarcoma cell lines from dogs with normal and increased serum ALP concentration. No differences in gene expression patterns were noted between tumours or cell lines with differing serum ALP concentration using a gene-specific two-sample t-test. Using a more sensitive empirical Bayes procedure, defective in cullin neddylation 1 domain containing 1 (DCUN1D1) was increased in both the tissue and cell lines of the normal ALP group. Using quantitative PCR (qPCR), differences in DCUN1D1 expression between the two groups failed to reach significance. The homogeneity of gene expression patterns of osteosarcoma associated differing serum ALP concentrations are consistent with previous studies suggesting serum ALP concentration is not associated with intrinsic differences of osteosarcoma cells.

20q gain associates with immortalization: 20q13.2 amplification correlates with genome instability in human papillomavirus 16 E7 transformed human uroepithelial cells.

Breast, bladder, colon, and ovarian carcinomas show frequent low level 20q gain and less frequently high level 20q13.2 amplification, but the significance of these 20q amplifications in transformation has not been defined. Using karyotypic and comparative genomic hybridization (CGH) analyses, chromosome losses and gains were analysed in six newly immortalized human uroepithelial cell (HUC) lines transformed by Human Papillomavirus 16 (HPV16) E7. Results showed clonal chromosomes with 20q11->qter gain in all six lines. CGH revealed a peak of 20q13.2 amplification in two cell lines. FISH with whole chromosome 20 paint showed expanded chromosome regions (ECRs) and double minute chromosomes (DMs) that contained chromosome 20 material in cell lines with 20q13.2 amplification. FISH with probes from the center of the 20q13.2 human breast cancer amplicon showed as many as 24 signals in cells with 20q13.2 amplification. The acquisition of genome instability in these E7-HUCs did not correlate with TP53 mutation, as all E7-HUCs contained only wildtype TP53. These results suggest that low level 20q gain is associated with overcoming cellular senescence in E7 transformed cells (P-value=2 x 10(-7)), but does not confer genome instability, while high level 20q13.2 amplification is associated with chromosome instability. Loss of 10p (P-value = 3 x 10(-5)) was also important in immortalization of E7-transformed HUCs. Thus, these results have profound implications for interpreting the significance of high versus low level 20q gains in human cancers.