Blurring contact maps of thousands of proteins: what we can learn by reconstructing 3D structure

Multiple serous cavity effusion screening based on smear images using vision transformer

Serous cavity effusion is a prevalent pathological condition encountered in clinical settings. Fluid samples obtained from these effusions are vital for diagnostic and therapeutic purposes. Traditionally, cytological examination of smears is a common method for diagnosing serous cavity effusion, renowned for its convenience. However, this technique presents limitations that can compromise its efficiency and diagnostic accuracy. This study aims to overcome these challenges and introduce an improved method for the precise detection of malignant cells in serous cavity effusions. We have developed a transformer-based classification framework, specifically employing the vision transformer (ViT) model, to fulfill this objective. Our research involved collecting smear images and corresponding cytological reports from 161 patients who underwent serous cavity drainage. We meticulously annotated 4836 patches from these images, identifying regions with and without malignant cells, thus creating a unique dataset for smear image classification. The findings of our study reveal that deep learning models, particularly the ViT model, exhibit remarkable accuracy in classifying patches as malignant or non-malignant. The ViT model achieved an impressive area under the receiver operating characteristic curve (AUROC) of 0.99, surpassing the performance of the convolutional neural network (CNN) model, which recorded an AUROC of 0.86. Additionally, we validated our models using an external cohort of 127 patients. The ViT model sustained its high-level screening performance, achieving an AUROC of 0.98 at the patient level, compared to the CNN model's AUROC of 0.84. The visualization of our ViT models confirmed their capability to precisely identify regions containing malignant cells in multiple serous cavity effusion smear images. In summary, our study demonstrates the potential of deep learning models, particularly the ViT model, in automating the screening process for serous cavity effusions. These models offer significant assistance to cytologists in enhancing diagnostic accuracy and efficiency. The ViT model stands out for its advanced self-attention mechanism, making it exceptionally suitable for tasks that necessitate detailed analysis of small, sparsely distributed targets like cellular clusters in serous cavity effusions.

Fuzzy binding model of molecular interactions between tropoelastin and integrin alphaVbeta3

Tropoelastin is the highly flexible monomer subunit of elastin, required for the resilience of the extracellular matrix in elastic tissues. To elicit biological signaling, multiple sites on tropoelastin bind to cell surface integrins in a poorly understood multifactorial process. We constructed a full atomistic molecular model of the interactions between tropoelastin and integrin α_vβ₃ using ensemble-based computational methodologies. Conformational changes of integrin α_vβ₃ associated with outside-in signaling were more frequently facilitated in an ensemble in which tropoelastin bound the integrin's α1 helix rather than the upstream canonical binding site. Our findings support a model of fuzzy binding, whereby many tropoelastin conformations and defined sites cooperatively interact with multiple α_vβ₃ regions. This model explains prior experimental binding to distinct tropoelastin regions, domains 17 and 36, and points to the cooperative participation of domain 20. Our study highlights the utility of ensemble-based approaches in helping to understand the interactive mechanisms of functionally significant flexible proteins.

Towards defining the Mechanisms of Alzheimer's disease based on a contextual analysis of molecular pathways

Alzheimer's disease (AD) is posing an increasingly profound problem to society. Our genuine understanding of the pathogenesis of AD is inadequate and as a consequence, diagnostic and therapeutic strategies are currently insufficient. The understandable focus of many studies is the identification of molecules with high diagnostic utility however the opportunity to obtain a further understanding of the mechanistic origins of the disease from such putative biomarkers is often overlooked. This study examines the involvement of biomarkers in AD to shed light on potential mechanisms and pathways through which they are implicated in the pathology of this devastating neurodegenerative disorder. The computational tools required to analyse ever-growing datasets in the context of AD are also discussed.

Probabilistic divergence of a template-based modelling methodology from the ideal protocol

Protein structural information is essential for the detailed mapping of a functional protein network. For a higher modelling accuracy and quicker implementation, template-based algorithms have been extensively deployed and redefined. The methods only assess the predicted structure against its native state/template and do not estimate the accuracy for each modelling step. A divergence measure is therefore postulated to estimate the modelling accuracy against its theoretical optimal benchmark. By freezing the domain boundaries, the divergence measures are predicted for the most crucial steps of a modelling algorithm. To precisely refine the score using weighting constants, big data analysis could further be deployed.

KGHC: a knowledge graph for hepatocellular carcinoma

BACKGROUND

Hepatocellular carcinoma is one of the most general malignant neoplasms in adults with high mortality. Mining relative medical knowledge from rapidly growing text data and integrating it with other existing biomedical resources will provide support to the research on the hepatocellular carcinoma. To this purpose, we constructed a knowledge graph for Hepatocellular Carcinoma (KGHC).

METHODS

We propose an approach to build a knowledge graph for hepatocellular carcinoma. Specifically, we first extracted knowledge from structured data and unstructured data. Since the extracted entities may contain some noise, we applied a biomedical information extraction system, named BioIE, to filter the data in KGHC. Then we introduced a fusion method which is used to fuse the extracted data. Finally, we stored the data into the Neo4j which can help researchers analyze the network of hepatocellular carcinoma.

RESULTS

KGHC contains 13,296 triples and provides the knowledge of hepatocellular carcinoma for healthcare professionals, making them free of digging into a large amount of biomedical literatures. This could hopefully improve the efficiency of researches on the hepatocellular carcinoma. KGHC is accessible free for academic research purpose at http://202.118.75.18:18895/browser/ .

CONCLUSIONS

In this paper, we present a knowledge graph associated with hepatocellular carcinoma, which is constructed with vast amounts of structured and unstructured data. The evaluation results show that the data in KGHC is of high quality.

Deep learning methods in protein structure prediction

Protein Structure Prediction is a central topic in Structural Bioinformatics. Since the '60s statistical methods, followed by increasingly complex Machine Learning and recently Deep Learning methods, have been employed to predict protein structural information at various levels of detail. In this review, we briefly introduce the problem of protein structure prediction and essential elements of Deep Learning (such as Convolutional Neural Networks, Recurrent Neural Networks and basic feed-forward Neural Networks they are founded on), after which we discuss the evolution of predictive methods for one-dimensional and two-dimensional Protein Structure Annotations, from the simple statistical methods of the early days, to the computationally intensive highly-sophisticated Deep Learning algorithms of the last decade. In the process, we review the growth of the databases these algorithms are based on, and how this has impacted our ability to leverage knowledge about evolution and co-evolution to achieve improved predictions. We conclude this review outlining the current role of Deep Learning techniques within the wider pipelines to predict protein structures and trying to anticipate what challenges and opportunities may arise next.

StructureDistiller: Structural relevance scoring identifies the most informative entries of a contact map

Protein folding and structure prediction are two sides of the same coin. Contact maps and the related techniques of constraint-based structure reconstruction can be considered as unifying aspects of both processes. We present the Structural Relevance (SR) score which quantifies the information content of individual contacts and residues in the context of the whole native structure. The physical process of protein folding is commonly characterized with spatial and temporal resolution: some residues are Early Folding while others are Highly Stable with respect to unfolding events. We employ the proposed SR score to demonstrate that folding initiation and structure stabilization are subprocesses realized by distinct sets of residues. The example of cytochrome c is used to demonstrate how StructureDistiller identifies the most important contacts needed for correct protein folding. This shows that entries of a contact map are not equally relevant for structural integrity. The proposed StructureDistiller algorithm identifies contacts with the highest information content; these entries convey unique constraints not captured by other contacts. Identification of the most informative contacts effectively doubles resilience toward contacts which are not observed in the native contact map. Furthermore, this knowledge increases reconstruction fidelity on sparse contact maps significantly by 0.4 Å.

Biclustering of Gene Expression Data Using Cuckoo Search and Genetic Algorithm

Biclustering analysis of gene expression data can reveal a large number of biologically significant local gene expression patterns. Therefore, a large number of biclustering algorithms apply meta-heuristic algorithms such as genetic algorithm (GA) and cuckoo search (CS) to analyze the biclusters. However, different meta-heuristic algorithms have different applicability and characteristics. For example, the CS algorithm can obtain high-quality bicluster and strong global search ability, but its local search ability is relatively poor. In contrast to the CS algorithm, the GA has strong local search ability, but its global search ability is poor. In order to not only improve the global search ability of a bicluster and its coverage, but also improve the local search ability of the bicluster and its quality, this paper proposed a meta-heuristic algorithm based on GA and CS algorithm (GA-CS Biclustering, Georgia Association of Community Service Boards (GACSB)) to solve the problem of gene expression data clustering. The algorithm uses the CS algorithm as the main framework, and uses the tournament strategy and the elite retention strategy based on the GA to generate the next generation of the population. Compared with the experimental results of common biclustering analysis algorithms such as correlated correspondence (CC), fast, local clustering (FLOC), interior search algorithm (ISA), Securities Exchange Board of India (SEBI), sum of squares between (SSB) and coordinated scheduling/beamforming (CSB), the GACSB algorithm can not only obtain biclusters of high quality, but also obtain biclusters of high-biologic significance. In addition, we also use different bicluster evaluation indicators, such as Average Correlation Value (ACV), Mean-Squared Residue (MSR) and Virtual Error (VE), and verify that the GACSB algorithm has a strong scalability.

Ordering Protein Contact Matrices

Numerous biophysical approaches provide information about residues spatial proximity in proteins. However, correct assignment of the protein fold from this proximity information is not straightforward if the spatially close protein residues are not assigned to residues in the primary sequence. Here, we propose an algorithm to assign such residue numbers by ordering the columns and lines of the raw protein contact matrix directly obtained from proximity information between unassigned amino acids. The ordering problem is formatted as the search of a trail within a graph connecting protein residues through the nonzero contact values. The algorithm performs in two steps: (i) finding the longest trail of the graph using an original dynamic programming algorithm, (ii) clustering the individual ordered matrices using a self-organizing map (SOM) approach. The combination of the dynamic programming and self-organizing map approaches constitutes a quite innovative point of the present work. The algorithm was validated on a set of about 900 proteins, representative of the sizes and proportions of secondary structures observed in the Protein Data Bank. The algorithm was revealed to be efficient for noise levels up to 40%, obtaining average gaps of about 20% at maximum between ordered and initial matrices. The proposed approach paves the ways toward a method of fold prediction from noisy proximity information, as TM scores larger than 0.5 have been obtained for ten randomly chosen proteins, in the case of a noise level of 10%. The methods has been also validated on two experimental cases, on which it performed satisfactorily.

An automatic approach for constructing a knowledge base of symptoms in Chinese

Background

While a large number of well-known knowledge bases (KBs) in life science have been published as Linked Open Data, there are few KBs in Chinese. However, KBs in Chinese are necessary when we want to automatically process and analyze electronic medical records (EMRs) in Chinese. Of all, the symptom KB in Chinese is the most seriously in need, since symptoms are the starting point of clinical diagnosis.

Results

We publish a public KB of symptoms in Chinese, including symptoms, departments, diseases, medicines, and examinations as well as relations between symptoms and the above related entities. To the best of our knowledge, there is no such KB focusing on symptoms in Chinese, and the KB is an important supplement to existing medical resources. Our KB is constructed by fusing data automatically extracted from eight mainstream healthcare websites, three Chinese encyclopedia sites, and symptoms extracted from a larger number of EMRs as supplements.

Methods

Firstly, we design data schema manually by reference to the Unified Medical Language System (UMLS). Secondly, we extract entities from eight mainstream healthcare websites, which are fed as seeds to train a multi-class classifier and classify entities from encyclopedia sites and train a Conditional Random Field (CRF) model to extract symptoms from EMRs. Thirdly, we fuse data to solve the large-scale duplication between different data sources according to entity type alignment, entity mapping, and attribute mapping. Finally, we link our KB to UMLS to investigate similarities and differences between symptoms in Chinese and English.

Conclusions

As a result, the KB has more than 26,000 distinct symptoms in Chinese including 3968 symptoms in traditional Chinese medicine and 1029 synonym pairs for symptoms. The KB also includes concepts such as diseases and medicines as well as relations between symptoms and the above related entities. We also link our KB to the Unified Medical Language System and analyze the differences between symptoms in the two KBs. We released the KB as Linked Open Data and a demo at https://datahub.io/dataset/symptoms-in-chinese.

Improved protein structure reconstruction using secondary structures, contacts at higher distance thresholds, and non-contacts

Background

Residue-residue contacts are key features for accurate de novo protein structure prediction. For the optimal utilization of these predicted contacts in folding proteins accurately, it is important to study the challenges of reconstructing protein structures using true contacts. Because contact-guided protein modeling approach is valuable for predicting the folds of proteins that do not have structural templates, it is necessary for reconstruction studies to focus on hard-to-predict protein structures.

Results

Using a data set consisting of 496 structural domains released in recent CASP experiments and a dataset of 150 representative protein structures, in this work, we discuss three techniques to improve the reconstruction accuracy using true contacts – adding secondary structures, increasing contact distance thresholds, and adding non-contacts. We find that reconstruction using secondary structures and contacts can deliver accuracy higher than using full contact maps. Similarly, we demonstrate that non-contacts can improve reconstruction accuracy not only when the used non-contacts are true but also when they are predicted. On the dataset consisting of 150 proteins, we find that by simply using low ranked predicted contacts as non-contacts and adding them as additional restraints, can increase the reconstruction accuracy by 5% when the reconstructed models are evaluated using TM-score.

Conclusions

Our findings suggest that secondary structures are invaluable companions of contacts for accurate reconstruction. Confirming some earlier findings, we also find that larger distance thresholds are useful for folding many protein structures which cannot be folded using the standard definition of contacts. Our findings also suggest that for more accurate reconstruction using predicted contacts it is useful to predict contacts at higher distance thresholds (beyond 8 Å) and predict non-contacts.

Electronic supplementary material

The online version of this article (10.1186/s12859-017-1807-5) contains supplementary material, which is available to authorized users.

GDFuzz3D: a method for protein 3D structure reconstruction from contact maps, based on a non-Euclidean distance function

MOTIVATION

To date, only a few distinct successful approaches have been introduced to reconstruct a protein 3D structure from a map of contacts between its amino acid residues (a 2D contact map). Current algorithms can infer structures from information-rich contact maps that contain a limited fraction of erroneous predictions. However, it is difficult to reconstruct 3D structures from predicted contact maps that usually contain a high fraction of false contacts.

RESULTS

We describe a new, multi-step protocol that predicts protein 3D structures from the predicted contact maps. The method is based on a novel distance function acting on a fuzzy residue proximity graph, which predicts a 2D distance map from a 2D predicted contact map. The application of a Multi-Dimensional Scaling algorithm transforms that predicted 2D distance map into a coarse 3D model, which is further refined by typical modeling programs into an all-atom representation. We tested our approach on contact maps predicted de novo by MULTICOM, the top contact map predictor according to CASP10. We show that our method outperforms FT-COMAR, the state-of-the-art method for 3D structure reconstruction from 2D maps. For all predicted 2D contact maps of relatively low sensitivity (60-84%), GDFuzz3D generates more accurate 3D models, with the average improvement of 4.87 Å in terms of RMSD.

AVAILABILITY AND IMPLEMENTATION

GDFuzz3D server and standalone version are freely available at http://iimcb.genesilico.pl/gdserver/GDFuzz3D/.

CONTACT

iamb@genesilico.pl

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

CNNcon: improved protein contact maps prediction using cascaded neural networks

BACKGROUNDS

Despite continuing progress in X-ray crystallography and high-field NMR spectroscopy for determination of three-dimensional protein structures, the number of unsolved and newly discovered sequences grows much faster than that of determined structures. Protein modeling methods can possibly bridge this huge sequence-structure gap with the development of computational science. A grand challenging problem is to predict three-dimensional protein structure from its primary structure (residues sequence) alone. However, predicting residue contact maps is a crucial and promising intermediate step towards final three-dimensional structure prediction. Better predictions of local and non-local contacts between residues can transform protein sequence alignment to structure alignment, which can finally improve template based three-dimensional protein structure predictors greatly.

METHODS

CNNcon, an improved multiple neural networks based contact map predictor using six sub-networks and one final cascade-network, was developed in this paper. Both the sub-networks and the final cascade-network were trained and tested with their corresponding data sets. While for testing, the target protein was first coded and then input to its corresponding sub-networks for prediction. After that, the intermediate results were input to the cascade-network to finish the final prediction.

RESULTS

The CNNcon can accurately predict 58.86% in average of contacts at a distance cutoff of 8 Å for proteins with lengths ranging from 51 to 450. The comparison results show that the present method performs better than the compared state-of-the-art predictors. Particularly, the prediction accuracy keeps steady with the increase of protein sequence length. It indicates that the CNNcon overcomes the thin density problem, with which other current predictors have trouble. This advantage makes the method valuable to the prediction of long length proteins. As a result, the effective prediction of long length proteins could be possible by the CNNcon.

Effective inter-residue contact definitions for accurate protein fold recognition

BACKGROUND

Effective encoding of residue contact information is crucial for protein structure prediction since it has a unique role to capture long-range residue interactions compared to other commonly used scoring terms. The residue contact information can be incorporated in structure prediction in several different ways: It can be incorporated as statistical potentials or it can be also used as constraints in ab initio structure prediction. To seek the most effective definition of residue contacts for template-based protein structure prediction, we evaluated 45 different contact definitions, varying bases of contacts and distance cutoffs, in terms of their ability to identify proteins of the same fold.

RESULTS

We found that overall the residue contact pattern can distinguish protein folds best when contacts are defined for residue pairs whose Cβ atoms are at 7.0 Å or closer to each other. Lower fold recognition accuracy was observed when inaccurate threading alignments were used to identify common residue contacts between protein pairs. In the case of threading, alignment accuracy strongly influences the fraction of common contacts identified among proteins of the same fold, which eventually affects the fold recognition accuracy. The largest deterioration of the fold recognition was observed for β-class proteins when the threading methods were used because the average alignment accuracy was worst for this fold class. When results of fold recognition were examined for individual proteins, we found that the effective contact definition depends on the fold of the proteins. A larger distance cutoff is often advantageous for capturing spatial arrangement of the secondary structures which are not physically in contact. For capturing contacts between neighboring β strands, considering the distance between Cα atoms is better than the Cβ-based distance because the side-chain of interacting residues on β strands sometimes point to opposite directions.

CONCLUSION

Residue contacts defined by Cβ-Cβ distance of 7.0 Å work best overall among tested to identify proteins of the same fold. We also found that effective contact definitions differ from fold to fold, suggesting that using different residue contact definition specific for each template will lead to improvement of the performance of threading.