A-Prot: Protein structure modeling using MSA transformer

In this study, we propose a new protein 3D structure modeling method, A-Prot, using MSA Transformer, one of the state-of-the-art protein lan-guage models. For a given MSA, an MSA feature tensor and row attention maps are extracted and converted into 2D residue-residue distance and dihedral angle predictions. We demonstrated that A-Prot predicts long-range contacts better than the existing methods. Additionally, we modeled the 3D structures of the free modeling and hard template-based modeling targets of CASP14. The assessment shows that the A-Prot models are more accurate than most top server groups of CASP14. These results imply that A-Prot captures evolutionary and structural infor-mation of proteins accurately with relatively low computational cost. Thus, A-Prot can provide a clue for the development of other protein prop-erty prediction methods.

Study of Real-Valued Distance Prediction For Protein Structure Prediction with Deep Learning

Inter-residue distance prediction by deep ResNet (convolutional residual neural network) has greatly advanced protein structure prediction. Currently the most successful structure prediction methods predict distance by discretizing it into dozens of bins. Here we study how well real-valued distance can be predicted and how useful it is for 3D structure modeling by comparing it with discrete-valued prediction based upon the same deep ResNet. Different from the recent methods that predict only a single real value for the distance of an atom pair, we predict both the mean and standard deviation of a distance and then employ a novel method to fold a protein by the predicted mean and deviation. Our findings include: 1) tested on the CASP13 FM (free-modeling) targets, our real-valued distance prediction obtains 81% precision on top L/5 long-range contact prediction, much better than the best CASP13 results (70%); 2) our real-valued prediction can predict correct folds for the same number of CASP13 FM targets as the best CASP13 group, despite generating only 20 decoys for each target; 3) our method greatly outperforms a very new real-valued prediction method DeepDist in both contact prediction and 3D structure modeling; and 4) when the same deep ResNet is used, our real-valued distance prediction has 1-6% higher contact and distance accuracy than our own discrete-valued prediction, but less accurate 3D structure models.

Analysis of distance-based protein structure prediction by deep learning in CASP13

This paper reports the CASP13 results of distance-based contact prediction, threading and folding methods implemented in three RaptorX servers, which are built upon the powerful deep convolutional residual neural network (ResNet) method initiated by us for contact prediction in CASP12. On the 32 CASP13 FM (free-modeling) targets with a median MSA (multiple sequence alignment) depth of 36, RaptorX yielded the best contact prediction among 46 groups and almost the best 3D structure modeling among all server groups without time-consuming conformation sampling. In particular, RaptorX achieved top L/5, L/2 and L long-range contact precision of 70%, 58% and 45%, respectively, and predicted correct folds (TMscore>0.5) for 18 of 32 targets. Although on average underperforming AlphaFold in 3D modeling, RaptorX predicted correct folds for all FM targets with >300 residues (T0950-D1, T0969-D1 and T1000-D2) and generated the best 3D models for T0950-D1 and T0969-D1 among all groups. This CASP13 test confirms our previous findings: (1) predicted distance is more useful than contacts for both template-based and free modeling; and (2) structure modeling may be improved by integrating alignment and co-evolutionary information via deep learning. This paper will discuss progress we have made since CASP12, the strength and weakness of our methods, and why deep learning performed much better in CASP13.

Study the precision of creating 3D structure modeling form terrestrial laser scanner observations

Laser scanner has become widely used nowadays for several applications in civil engineering. An advantage of laser scanner as compared to other geodetic instruments is its capability of collecting hundreds or even thousands of point per second. Terrestrial laser scanner allows acquiring easy and fast complex geometric data from building, machines, objects, etc. Several experimental and field tests are required to investigate the quality and accuracy of scanner points cloud and the 3D geometric models derived from laser scanner. So this paper investigates the precision of creation three dimensional structural model resulted from terrestrial laser scanner observations. The paper also presented the ability to create 3D model by structural faces depending on the plane equation for each face resulted from coordinates of several observed points cover this face using reflector less total station observations. Precision comparison for the quality of 3D models created from laser scanner observations and structure faces is also presented.The results of the practical measurements, calculations and analysis of results are presented.