Delving into the Latest Updates on Pending AI with Synapse

Overview

Electron cryo-microscopy (cryo-EM) is rapidly becoming a major competitor to X-ray crystallography, especially for large structures that are difficult or impossible to crystallize. While recent spectacular technological improvements have led to significantly higher resolution three-dimensional reconstructions, the average quality of cryo-EM maps is still at the low-resolution end of the range compared with crystallography. A long-standing challenge for atomic model refinement has been the production of stereochemically meaningful models for this resolution regime. Here, it is demonstrated that including accurate model geometry restraints derived from ab initio quantum-chemical calculations (HF-D3/6-31G) can improve the refinement of an example structure (chain A of PDB entry 3j63). The robustness of the procedure is tested for additional structures with up to 7000 atoms (PDB entry 3a5x and chain C of PDB entry 5fn5) using the less expensive semi-empirical (GFN1-xTB) model. The necessary algorithms enabling real-space quantum refinement have been implemented in the latest version of qr.refine and are described here.

01 Jan 2020·Acta Crystallographica Section D Structural BiologyQ3 · BIOLOGY

Including crystallographic symmetry in quantum-based refinement: Q|R#2

Q3 · BIOLOGY

Article

Author: Afonine, Pavel V ; Biczysko, Malgorzata ; Kruse, Holger ; Xu, Yanting ; Zheng, Min ; Moriarty, Nigel W ; Urzhumtsev, Alexandre ; Waller, Mark P

Three-dimensional structure models refined using low-resolution data from crystallographic or electron cryo-microscopy experiments can benefit from high-quality restraints derived from quantum-chemical methods. However, nonperiodic atom-centered quantum-chemistry codes do not inherently account for nearest-neighbor interactions of crystallographic symmetry-related copies in a satisfactory way. Here, these nearest-neighbor effects have been included in the model by expanding to a super-cell and then truncating the super-cell to only include residues from neighboring cells that are interacting with the asymmetric unit. In this way, the fragmentation approach can adequately and efficiently include nearest-neighbor effects. It has previously been shown that a moderately sized X-ray structure can be treated using quantum methods if a fragmentation approach is applied. In this study, a target protein (PDB entry 4gif) was partitioned into a number of large fragments. The use of large fragments (typically hundreds of atoms) is tractable when a GPU-based package such as TeraChem is employed or cheaper (semi-empirical) methods are used. The QM calculations were run at the HF-D3/6-31G level. The models refined using a recently developed semi-empirical method (GFN2-xTB) were compared and contrasted. To validate the refinement procedure for a non-P1 structure, a standard set of crystallographic metrics were used. The robustness of the implementation is shown by refining 13 additional protein models across multiple space groups and a summary of the refinement metrics is presented.

Towards AI-based synthesis at scale

Author: Waller, Mark

The significant investment in high-throughput automation in Biol. has resulted in many breakthroughs.This suggests that an increased reliance on automation in Chem. is inevitable.Advanced artificial intelligence (AI) coupled to bespoke robotics are the two key components required to build autonomous systems for running chem. experiments at scale.We have developed a range of novel solutions that adapt state-of-the-art AI solutions for the domain of Chem.We have developed a method to generate novel mol. targets using recurrent neural networks (RNN).[1] This enables us to quickly discover new areas of chem. space that might contain highly valuable compoundsHowever, the number of mols. that are produced by the RNN is immense, and the bottleneck becomes assessing their synthesizability.We also developed an AI-based tool that can determine optimal routes to synthesize the novel generated mols.[2,3,4] This retrosynthetic tool was trained on the breadth of chem. knowledge extracted from the Reaxys database.[5] On the hardware side we have been developing cheap modular robotic platform.The key to the project was restricting ourselves to an ultra low cost solutionThere are of course very high-end robotic systems, but the costs are often too high to effectively scale.As the field matures, the costs of robotic platforms will decrease, and the rate of innovation will accelerate, and adoption will then increase rapidly.Apart from novel and pragmatic algorithms in AI, a significant amount of engineering is further required to make hardware, firmware, software and wetware all work together in order to make a scalable robotic chem. platform.

100 Deals associated with Pending AI

Login to view more data

100 Translational Medicine associated with Pending AI

Login to view more data