CryoREAD is a computational tool using deep learning to automatically build full DNA/RNA atomic structure from cryo-EM map.
(1) Structure Detection by Deep Learning: locations of phosphate, sugar, base, and four base types are detected by two-stage networks.
(2)Structure Node Clustering: representative nodes are identified through clustering from detected grid positions.
(3) Backbone Tracing: the backbone is traced by the graph constructed with representative sugar nodes.
(4) Sequence Assignment: Sequences are assigned to local fragments along the backbone path, which are then assembled in the subsequent step.
(5) Full Atom Model: full nucleotides are constructed according to triangles of phosphate, sugar, and base (S-P-B) node followed by atomic structure refinement.
python3 main.py --mode=0 -F=example/21051.mrc -M=best_model --contour=0.3 --gpu=0 --batch_size=4 --prediction_only
The predicted probability maps are saved in [Predict_Result/(map_name)/2nd_stage_detection] with mrc format. It will include 8 mrc files corresponding to 8 different classes. Here (map_name) is 21051.python3 main.py --mode=0 -F=example/21051.mrc -M=best_model --contour=0.3 --gpu=0 --batch_size=4 --resolution=3.7 --no_seqinfo --refine
The automatically build atomic structure is saved in [Predict_Result/(map-name)/Output/Refine_cycle[k].pdb] in pdb format, here default k is 3. However, it may fail if your dependencies are not properly installed, then you may only find Refine_cycle1.pdb or Refine_cycle2.pdb. Here (map_name) is 21051.python3 main.py --mode=0 -F=example/21051.mrc -M=best_model -P=example/21051.fasta --contour=0.3 --gpu=0 --batch_size=4 --rule_soft=0 --resolution=3.7 --refine
The automatically build atomic structure is saved in The automatically build atomic structure is saved in [Predict_Result/(map-name)/Output/Refine_cycle[k].pdb] in pdb format, here default k is 3. However, it may fail if your dependencies are not properly installed, then you may only find Refine_cycle1.pdb or Refine_cycle2.pdb. Modeled structures without considering sequence information are also saved as [Predict_Result/(map-name)/Output/CryoREAD_noseq.pdb] (without refinement). Meanwhile, structures only considering the sequence information without connecting gap regions are saved in [Predict_Result/(map-name)/Output/CryoREAD_seqonly.pdb] (without refinement) for reference. Here (map_name) is 21051. Compared to previous structures, only sequence assignments will be changed and overall structures are similar.
CryoREAD is a free software for academic and non-commercial users.
It is released under the terms of the GNU General Public License Ver.3 (https://www.gnu.org/licenses/gpl-3.0.en.html).
Commercial users please contact dkihara@purdue.edu for alternate licensing.
Citation of the following reference should be included in any publication that uses data or results generated by CryoREAD program.
Xiao Wang, Genki Terashi, & Daisuke Kihara. De novo structure modeling for nucleic acids in cryo-EM maps using deep learning. bioArxiv (2022)
The output structures and detection maps benchmarked in this paper is available here
© 2023 KIHARA Bioinformatics LABORATORY, PURDUE University | Design by TEMPLATED.