Proteins are essential to life, and understanding their structure can facilitate a mechanistic understanding of their function. Through an enormous experimental effort1–4, the structures of around 100,000 unique proteins have been determined5, but this represents a small fraction of the billions of known protein sequences6,7. Structural coverage is bottlenecked by the months to years of painstaking effort required to determine a single protein structure. Accurate computational approaches are needed to address this gap and to enable large-scale structural bioinformatics. Predicting the three-dimensional structure that a protein will adopt based solely on its amino acid sequence—the structure prediction component of the ‘protein folding problem’8—has been an important open research problem for more than 50 years9. Despite recent progress10–14, existing methods fall far short of atomic accuracy, especially when no homologous structure is available. Here we provide the first computational method that can regularly predict protein structures with atomic accuracy even in cases in which no similar structure is known. We validated an entirely redesigned version of our neural network-based model, AlphaFold, in the challenging 14th Critical Assessment of protein Structure Prediction (CASP14)15, demonstrating accuracy competitive with experimental structures in a majority of cases and greatly outperforming other methods. Underpinning the latest version of AlphaFold is a novel machine learning approach that incorporates physical and biological knowledge about protein structure, leveraging multi-sequence alignments, into the design of the deep learning algorithm. AlphaFold predicts protein structures with an accuracy competitive with experimental structures in the majority of cases using a novel deep learning architecture.

/pdf/highly-accurate-protein-structure-prediction-with-alphafold-2xjbzfwu3n.pdf

Highly accurate protein structure prediction with AlphaFold

Microstructures and properties of high-entropy alloys

SWISS-MODEL pioneered the field of automated modeling as the first protein modeling service on the Internet. In combination with the visualization tool Swiss-PdbViewer, the Internet-based Workspace and the SWISS-MODEL Repository, it provides a fully integrated sequence to structure analysis and modeling platform. This computational environment is made freely available to the scientific community with the aim to hide the computational complexity of structural bioinformatics and encourage bench scientists to make use of the ever-increasing structural information available. Indeed, over the last decade, the availability of structural information has significantly increased for many organisms as a direct consequence of the complementary nature of comparative protein modeling and experimental structure determination. This has a very positive and enabling impact on many different applications in biomedical research as described in this paper.

Automated comparative protein structure modeling with SWISS-MODEL and Swiss-PdbViewer: a historical perspective.

Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results across a variety of domains. Biology and medicine are data-rich disciplines, but the data are complex and often ill-understood. Hence, deep learning techniques may be particularly well suited to solve problems of these fields. We examine applications of deep learning to a variety of biomedical problems-patient classification, fundamental biological processes and treatment of patients-and discuss whether deep learning will be able to transform these tasks or if the biomedical sphere poses unique challenges. Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress indicates that deep learning methods will provide valuable means for speeding up or aiding human investigation. Though progress has been made linking a specific neural network's prediction to input features, understanding how users should interpret these models to make testable hypotheses about the system under study remains an open challenge. Furthermore, the limited amount of labelled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning enabling changes at both bench and bedside with the potential to transform several areas of biology and medicine.

https://royalsocietypublishing.org/doi/pdf/10.1098/rsif.2017.0387

Opportunities and obstacles for deep learning in biology and medicine.

The similarity in the three-dimensional structures of homologous proteins imposes strong constraints on their sequence variability. It has long been suggested that the resulting correlations among amino acid compositions at different sequence positions can be exploited to infer spatial contacts within the tertiary protein structure. Crucial to this inference is the ability to disentangle direct and indirect correlations, as accomplished by the recently introduced direct-coupling analysis (DCA). Here we develop a computationally efficient implementation of DCA, which allows us to evaluate the accuracy of contact prediction by DCA for a large number of protein domains, based purely on sequence information. DCA is shown to yield a large number of correctly predicted contacts, recapitulating the global structure of the contact map for the majority of the protein domains examined. Furthermore, our analysis captures clear signals beyond intradomain residue contacts, arising, e.g., from alternative protein conformations, ligand-mediated residue couplings, and interdomain interactions in protein oligomers. Our findings suggest that contacts predicted by DCA can be used as a reliable guide to facilitate computational predictions of alternative protein conformations, protein complex formation, and even the de novo prediction of protein domain structures, contingent on the existence of a large number of homologous sequences which are being rapidly made available due to advances in genome sequencing.

/pdf/direct-coupling-analysis-of-residue-coevolution-captures-i6jxi7zeut.pdf

Direct-coupling analysis of residue coevolution captures native contacts across many protein families

Understanding the molecular determinants of specificity in protein–protein interaction is an outstanding challenge of postgenome biology. The availability of large protein databases generated from sequences of hundreds of bacterial genomes enables various statistical approaches to this problem. In this context covariance-based methods have been used to identify correlation between amino acid positions in interacting proteins. However, these methods have an important shortcoming, in that they cannot distinguish between directly and indirectly correlated residues. We developed a method that combines covariance analysis with global inference analysis, adopted from use in statistical physics. Applied to a set of >2,500 representatives of the bacterial two-component signal transduction system, the combination of covariance with global inference successfully and robustly identified residue pairs that are proximal in space without resorting to ad hoc tuning parameters, both for heterointeractions between sensor kinase (SK) and response regulator (RR) proteins and for homointeractions between RR proteins. The spectacular success of this approach illustrates the effectiveness of the global inference approach in identifying direct interaction based on sequence information alone. We expect this method to be applicable soon to interaction surfaces between proteins present in only 1 copy per genome as the number of sequenced genomes continues to expand. Use of this method could significantly increase the potential targets for therapeutic intervention, shed light on the mechanism of protein–protein interaction, and establish the foundation for the accurate prediction of interacting protein partners.

/pdf/identification-of-direct-residue-contacts-in-protein-protein-bzvqgl4eo0.pdf

Identification of direct residue contacts in protein-protein interaction by message passing.

Sensor complexes regulating two-component signal transduction

Effects of injection angles on combustion processes using multiple injection strategies in an HSDI diesel engine

Many systems respond to slowly changing external conditions with crackling noise, created by avalanches or pulses with a broad range of sizes. Examples range from Barkhausen noise (BN) in magnets to earthquakes. In this Letter, we discuss the effects of increasing driving rate $\ensuremath{\Omega}$ on the scaling behavior of the avalanche size and duration distributions as well as qualitative effects of $\ensuremath{\Omega}$ on the power spectra. We derive an exponent inequality as a criteria for the relevance of $\ensuremath{\Omega}$. To illustrate these general results, we use recent experiments on BN as a successful example.

Driving rate effects on crackling noise.

Lower proof ethanol is shown to be a viable alternate fuel for diesel engines. This type of ethanol can be manufactured economically in small distillation plants from renewable grain supplies. The effect of fumigation of ethanol proofs with a multipoint injection system on a turbocharged direct injection diesel engine at 2,400 rpm and three loads was studied. The addition of the water in the lower proofs reduced the maximum rate of pressure rise and peak pressure from pure ethanol levels. Both of these values were significantly higher than those for diesel operation. HC and CO emissions increased several times over diesel levels at all loads and also with increased ethanol fumigation. NO emissions were reduced below diesel levels for lower proof ethanol at all loads. The tests at this rpm and load with a a multipoint ethanol injection system indicate that lower (100 or 125) proof provides optimum performance.

Robert A. White

Papers

Identification of direct residue contacts in protein-protein interaction by message passing.

Sensor complexes regulating two-component signal transduction

Effects of injection angles on combustion processes using multiple injection strategies in an HSDI diesel engine

Driving rate effects on crackling noise.

The Effect of Fumigation of Different Ethanol Proofs on a Turbocharged Diesel Engine