Protein design via deep learning Ding, Wenze; Nakai, Kenta; Gong, Haipeng
Briefings in bioinformatics,
05/2022, Volume:
23, Issue:
3
Journal Article
Peer reviewed
Open access
Abstract
Proteins with desired functions and properties are important in fields like nanotechnology and biomedicine. De novo protein design enables the production of previously unseen proteins from ...the ground up and is believed as a key point for handling real social challenges. Recent introduction of deep learning into design methods exhibits a transformative influence and is expected to represent a promising and exciting future direction. In this review, we retrospect the major aspects of current advances in deep-learning-based design procedures and illustrate their novelty in comparison with conventional knowledge-based approaches through noticeable cases. We not only describe deep learning developments in structure-based protein design and direct sequence design, but also highlight recent applications of deep reinforcement learning in protein design. The future perspectives on design goals, challenges and opportunities are also comprehensively discussed.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
In cancer research, the association between a gene and clinical outcome suggests the underlying etiology of the disease and consequently can motivate further studies. The recent availability of ...published cancer microarray datasets with clinical annotation provides the opportunity for linking gene expression to prognosis. However, the data are not easy to access and analyze without an effective analysis platform.
To take advantage of public resources in full, a database named "PrognoScan" has been developed. This is 1) a large collection of publicly available cancer microarray datasets with clinical annotation, as well as 2) a tool for assessing the biological relationship between gene expression and prognosis. PrognoScan employs the minimum P-value approach for grouping patients for survival analysis that finds the optimal cutpoint in continuous gene expression measurement without prior biological knowledge or assumption and, as a result, enables systematic meta-analysis of multiple datasets.
PrognoScan provides a powerful platform for evaluating potential tumor markers and therapeutic targets and would accelerate cancer research. The database is publicly accessible at http://gibk21.bse.kyutech.ac.jp/PrognoScan/index.html.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
Abstract
Summary
Identifying the protein–peptide binding residues is fundamentally important to understand the mechanisms of protein functions and explore drug discovery. Although several ...computational methods have been developed, most of them highly rely on third-party tools or complex data preprocessing for feature design, easily resulting in low computational efficacy and suffering from low predictive performance. To address the limitations, we propose PepBCL, a novel BERT (Bidirectional Encoder Representation from Transformers) -based contrastive learning framework to predict the protein–peptide binding residues based on protein sequences only. PepBCL is an end-to-end predictive model that is independent of feature engineering. Specifically, we introduce a well pre-trained protein language model that can automatically extract and learn high-latent representations of protein sequences relevant for protein structures and functions. Further, we design a novel contrastive learning module to optimize the feature representations of binding residues underlying the imbalanced dataset. We demonstrate that our proposed method significantly outperforms the state-of-the-art methods under benchmarking comparison, and achieves more robust performance. Moreover, we found that we further improve the performance via the integration of traditional features and our learnt features. Interestingly, the interpretable analysis of our model highlights the flexibility and adaptability of deep learning-based protein language model to capture both conserved and non-conserved sequential characteristics of peptide-binding residues. Finally, to facilitate the use of our method, we establish an online predictive platform as the implementation of the proposed PepBCL, which is now available at http://server.wei-group.net/PepBCL/.
Availability and implementation
https://github.com/Ruheng-W/PepBCL.
Supplementary information
Supplementary data are available at Bioinformatics online.
In this commentary, I explain my perspective on the relationship between artificial intelligence (AI)/data science and biomedicine from a long-range retrospective view. The development of modern ...biomedicine has always been accelerated by the repeated emergence of new technologies. Since all life systems are basically governed by the information in their own DNA, information science has special importance for the study of biomedicine. Unlike in physics, no (or very few) leading laws have been found in biology. Thus, in biology, the “data-to-knowledge” approach is important. AI has historically been applied to biomedicine, and the recent news that an AI-based approach achieved the best performance in an international competition of protein structure prediction may be regarded as another landmark in the field. Similar approaches could contribute to solving problems in genome sequence interpretation, such as identifying cancer-driving mutations in the genome of patients. Recently, the explosive development of next-generation sequencing (NGS) has been producing massive data, and this trend will accelerate. NGS is not only used for “reading” DNA sequences, but also for obtaining various types of information at the single-cell level. These data can be regarded as grid data points in climate simulation. Both data science and AI will become essential for the integrative interpretation/simulation of these data, and will take a leading role in future precision medicine.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
It has been suggested that DNA methylation can work in concert with other epigenetic factors, leading to changes in cellular phenotypes. For example, DNA demethylation modifications producing ...5-hydroxymethylcytosine (5hmC) are thought to interact with histone modifications to influence the acquisition of embryonic stem cell (ESC) potency. However, the mechanism by which this occurs is still unknown. Thus, we systematically analysed the co-occurrence of DNA and histone modifications at genic regions as well as their relationship with ESC-specific expression using a number of heterogeneous public datasets. From a set of 19 epigenetic factors, we found remarkable co-occurrence of 5hmC and H4K8ac, accompanied by H3K4me1. This enrichment was more prominent at gene body regions. The results were confirmed using data obtained from different detection methods and species. Our analysis shows that these marks work cooperatively to influence ESC-specific gene expression. We also found that this trivalent mark is relatively enriched in genes related with immunity, which is a bit specific in ESCs. We propose that a trivalent epigenetic mark, composed of 5hmC, H4K8ac and H3K4me1, regulates gene expression and modulates the nature of human ESCs as a novel epigenetic code.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
At the time of translation, nascent proteins are thought to be sorted into their final subcellular localization sites, based on the part of their amino acid sequences (i.e., sorting or targeting ...signals). Thus, it is interesting to computationally recognize these signals from the amino acid sequences of any given proteins and to predict their final subcellular localization with such information, supplemented with additional information (e.g.,
-mer frequency). This field has a long history and many prediction tools have been released. Even in this era of proteomic atlas at the single-cell level, researchers continue to develop new algorithms, aiming at accessing the impact of disease-causing mutations/cell type-specific alternative splicing, for example. In this article, we overview the entire field and discuss its future direction.
Abstract
Here, we present DeepBIO, the first-of-its-kind automated and interpretable deep-learning platform for high-throughput biological sequence functional analysis. DeepBIO is a one-stop-shop web ...service that enables researchers to develop new deep-learning architectures to answer any biological question. Specifically, given any biological sequence data, DeepBIO supports a total of 42 state-of-the-art deep-learning algorithms for model training, comparison, optimization and evaluation in a fully automated pipeline. DeepBIO provides a comprehensive result visualization analysis for predictive models covering several aspects, such as model interpretability, feature analysis and functional sequential region discovery. Additionally, DeepBIO supports nine base-level functional annotation tasks using deep-learning architectures, with comprehensive interpretations and graphical visualizations to validate the reliability of annotated sites. Empowered by high-performance computers, DeepBIO allows ultra-fast prediction with up to million-scale sequence data in a few hours, demonstrating its usability in real application scenarios. Case study results show that DeepBIO provides an accurate, robust and interpretable prediction, demonstrating the power of deep learning in biological sequence functional analysis. Overall, we expect DeepBIO to ensure the reproducibility of deep-learning biological sequence analysis, lessen the programming and hardware burden for biologists and provide meaningful functional insights at both the sequence level and base level from biological sequences alone. DeepBIO is publicly available at https://inner.wei-group.net/DeepBIO.
Lay Summary
The development of next-generation sequencing techniques has led to an exponential increase in the amount of biological sequence data accessible. It naturally poses a fundamental challenge—how to build the relationships from such large-scale sequences to their functions. In this work, we present DeepBIO, the first-of-its-kind automated and interpretable deep-learning platform for high-throughput biological sequence functional analysis. It enables researchers to develop new deep-learning architectures to answer any biological question in a fully automated pipeline. We expect DeepBIO to ensure the reproducibility of deep-learning-based biological sequence analysis, lessen the programming and hardware burden for biologists and provide meaningful functional insights at both the sequence level and base level from biological sequences alone.
Graphical Abstract
Graphical Abstract
DeepBIO is an automated and interpretable deep-learning platform for high-throughput biological sequence level prediction, functional site annotation, and comprehensive visualization analysis.
Abstract
In this study, we propose iDNA-ABF, a multi-scale deep biological language learning model that enables the interpretable prediction of DNA methylations based on genomic sequences only. ...Benchmarking comparisons show that our iDNA-ABF outperforms state-of-the-art methods for different methylation predictions. Importantly, we show the power of deep language learning in capturing both sequential and functional semantics information from background genomes. Moreover, by integrating the interpretable analysis mechanism, we well explain what the model learns, helping us build the mapping from the discovery of important sequential determinants to the in-depth analysis of their biological functions.
Since the proposal of the signal hypothesis on protein subcellular sorting, a number of computational analyses have been performed in this field. A typical example is the development of prediction ...algorithms for the subcellular localization sites of input protein sequences. In this review, we mainly focus on the biological grounds of the prediction methods rather than the algorithmic issues because we believe the former will be more fruitful for future development. Recent advances on the study of protein sorting signals will hopefully be incorporated into future prediction methods. Unfortunately, many of the state‐of‐the‐art methods are published without sufficient objective tests. In fact, a simple test employed in this article shows that the performance of specifically developed predictors is not significantly better than that of a homology search. We suspect that this is a general problem associated with the interpretation of genome sequences, which have evolved through gene duplication and speciation.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SAZU, SBCE, SBMB, UL, UM, UPUK
Currently, the population dynamics of preclonal cancer cells before clonal expansion of tumors has not been sufficiently addressed thus far. By focusing on preclonal cancer cell population as a ...Darwinian evolutionary system, we formulated and analyzed the observed mutation frequency among tumors (MFaT) as a proxy for the hypothesized sequence read frequency and beneficial fitness effect of a cancer driver mutation. Analogous to intestinal crypts, we assumed that sample donor patients are separate culture tanks where proliferating cells follow certain population dynamics described by extreme value theory (EVT). To validate this, we analyzed three large-scale cancer genome datasets, each harboring > 10000 tumor samples and in total involving > 177898 observed mutation sites. We clarified the necessary premises for the application of EVT in the strong selection and weak mutation (SSWM) regime in relation to cancer genome sequences at scale. We also confirmed that the stochastic distribution of MFaT is likely of the Fréchet type, which challenges the well-known Gumbel hypothesis of beneficial fitness effects. Based on statistical data analysis, we demonstrated the potential of EVT as a population genetics framework to understand and explain the stochastic behavior of driver-mutation frequency in cancer genomes as well as its applicability in real cancer genome sequence data.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK