Home

The field of protein structure prediction has recently been revolutionized through the introduction of deep learning. The current state-of-the-art tool AlphaFold2 can predict highly accurate structures; however, it has a prohibitively long inference time for applications that require the folding of hundreds of sequences. The prediction of protein structure annotations, such as amino acid distances, can be achieved at a higher speed with existing tools, such as the ProSPr network. Here, we report on important updates to the ProSPr network, its performance in the recent Critical Assessment of Techniques for Protein Structure Prediction (CASP14) competition, and an evaluation of its accuracy dependency on sequence length and multiple sequence alignment depth. We also provide a detailed description of the architecture and the training process, accompanied by reusable code. This work is anticipated to provide a solid foundation for the further development of protein distance prediction tools.

The pharmaceutical industry needs to reverse current cost and revenue trends in the research and development process. Digital transformation is the process of turning a classical industry into a data-driven industry that leverages new technologies and opportunities arising from data science, such as artificial intelligence and machine learning. For pharma to successfully maneuver this digital transformation, changes to strategy, platforms, and cultures are necessary. Within this paper, we review the current challenges for the digital transformation of the pharma enterprise and offer a solution in form of a data centric architecture powered by a digital hub and Self-reporting data assets (SRDAs). SRDAs represents an efficient subset of the more generic FAIR – Findable, Accessible, Interoperable, Reusable – principles in pharma, as they were developed explicitly to solve important data sharing and reuse cases in this domain. Along with multiple use cases, we show how SRDAs harmonize information and make it accessible in a reusable fashion to data scientists. We present a variety of dashboards that can be created on a solid foundation of SRDAs and outline future business benefits that can follow from this transformative technology.

CASP (Critical Assessment of Structure Prediction) is an organization aimed at advancing the state of the art in computing protein structure from sequence. In the spring of 2020, CASP launched a community project to compute the structures of the most structurally challenging proteins coded for in the SARS-CoV2 genome. Forty-seven research groups submitted over 3000 three-dimensional models and 700 sets of accuracy estimates on ten proteins. The resulting models were released to the public. CASP community members also worked together to provide estimates of local and global accuracy and identify structure-based domain boundaries for some proteins. Subsequently, two of these structures (ORF3a and ORF8) have been solved experimentally, allowing assessment of both model quality and the accuracy estimates. Models from the AlphaFold2 group were found to have good agreement with the experimental structures, with main chain GDT_TS accuracy scores ranging from 63 (a correct topology) to 87 (competitive with experiment).