Louis BECQUEY / RNANet

Go to a project
Toggle navigation Toggle navigation pinning
Louis BECQUEY
0621fb8c 1 parent 3ba3c7d7

Alignment options used in alignment updates

Inline Side-by-side
Showing 5 changed files with 8 additions and 107 deletions
...@@ -2692,7 +2692,10 @@ def use_infernal(rfam_acc, alignopts): ...@@ -2692,7 +2692,10 @@ def use_infernal(rfam_acc, alignopts):
2692 2692
2693 # Align the new sequences 2693 # Align the new sequences
2694 with open(path_to_seq_data + f"realigned/{rfam_acc}_new.log", 'w') as o: 2694 with open(path_to_seq_data + f"realigned/{rfam_acc}_new.log", 'w') as o:
2695 - p1 = subprocess.run(["cmalign", "--ifile", path_to_seq_data + f"realigned/{rfam_acc}.ins", 2695 + cmd = ["cmalign"]
2696 + if alignopts is not None:
2697 + cmd += alignopts
2698 + p1 = subprocess.run(cmd + ["--ifile", path_to_seq_data + f"realigned/{rfam_acc}.ins",
2696 "--sfile", path_to_seq_data + f"realigned/{rfam_acc}.tsv", 2699 "--sfile", path_to_seq_data + f"realigned/{rfam_acc}.tsv",
2697 "-o", new_ali_path, 2700 "-o", new_ali_path,
2698 path_to_seq_data + f"realigned/{rfam_acc}.cm", 2701 path_to_seq_data + f"realigned/{rfam_acc}.cm",
...@@ -2705,6 +2708,7 @@ def use_infernal(rfam_acc, alignopts): ...@@ -2705,6 +2708,7 @@ def use_infernal(rfam_acc, alignopts):
2705 warn(f"Not enough RAM to allocate cmalign DP matrix for family {rfam_acc}. Use --sina or --cmalign-opts.", error=True) 2708 warn(f"Not enough RAM to allocate cmalign DP matrix for family {rfam_acc}. Use --sina or --cmalign-opts.", error=True)
2706 else: 2709 else:
2707 warn(align_errors, error=True) 2710 warn(align_errors, error=True)
2711 + return
2708 notify("Aligned new sequences together") 2712 notify("Aligned new sequences together")
2709 2713
2710 # Detect doublons and remove them 2714 # Detect doublons and remove them
...@@ -2721,6 +2725,7 @@ def use_infernal(rfam_acc, alignopts): ...@@ -2721,6 +2725,7 @@ def use_infernal(rfam_acc, alignopts):
2721 except ValueError: 2725 except ValueError:
2722 # Not a stockholm file 2726 # Not a stockholm file
2723 warn(f"New alignment {new_ali_path} is not a Stockholm file !", error=True) 2727 warn(f"New alignment {new_ali_path} is not a Stockholm file !", error=True)
2728 + return
2724 new_ids = [r.id for r in new_stk] 2729 new_ids = [r.id for r in new_stk]
2725 del new_stk 2730 del new_stk
2726 doublons = [i for i in existing_ids if i in new_ids] 2731 doublons = [i for i in existing_ids if i in new_ids]
......
...@@ -16,7 +16,7 @@ ...@@ -16,7 +16,7 @@
16 16
17 # Method 1 : Installation using Docker 17 # Method 1 : Installation using Docker
18 18
19 -* Step 1 : Download the [Docker container](https://entrepot.ibisc.univ-evry.fr/d/1aff90a9ef214a19b848/files/?p=/rnanet_v1.5b_docker.tar&dl=1). Open a terminal and move to the appropriate directory. 19 +* Step 1 : Download the [Docker container](https://entrepot.ibisc.univ-evry.fr/d/1aff90a9ef214a19b848/files/?p=/rnanet_v1.6b_docker.tar&dl=1). Open a terminal and move to the appropriate directory.
20 * Step 2 : Extract the archive to a Docker image named *rnanet* in your local installation 20 * Step 2 : Extract the archive to a Docker image named *rnanet* in your local installation
21 ``` 21 ```
22 $ docker load -i rnanet_v1.5b_docker.tar 22 $ docker load -i rnanet_v1.5b_docker.tar
......
1 -6ydp_1_AA_1176-2737
2 -6ydw_1_AA_1176-2737
3 -7d1a_1_A_805-902
4 -7d0g_1_A_805-913
5 -7d0f_1_A_817-913
6 -1vy7_1_AY_1-73
7 -1vy7_1_CY_1-73
8 -4w2h_1_CY_1-73
9 -7o7z_1_AH_144-220
10 -4c9d_1_D_29-1
11 -4c9d_1_C_29-1
12 -7aih_1_1_2984-3610
13 -7aih_1_1_2400-2963
14 -7ane_1_2_2489-3115
15 -7ane_1_2_1904-2468
16 -5g2x_1_A_595-692
17 -7aor_1_2_2589-3210
18 -7aor_1_2_2020-2579
19 -7a5p_1_2_259-449
20 -7aor_1_A_2589-3210
21 -7aor_1_A_2020-2579
22 -7am2_1_1_2491-3117
23 -7am2_1_1_1904-2470
24 -7ane_1_1_2489-3115
25 -7ane_1_1_1904-2468
26 -6uz7_1_8_2140-2825
1 -6ydp_1_AA_1176-2737
2 -Could not find nucleotides of chain AA in annotation 6ydp.json. Either there is a problem with 6ydp mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
3 -
4 -6ydw_1_AA_1176-2737
5 -Could not find nucleotides of chain AA in annotation 6ydw.json. Either there is a problem with 6ydw mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
6 -
7 -7d1a_1_A_805-902
8 -Could not find nucleotides of chain A in annotation 7d1a.json. Either there is a problem with 7d1a mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
9 -
10 -7d0g_1_A_805-913
11 -Could not find nucleotides of chain A in annotation 7d0g.json. Either there is a problem with 7d0g mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
12 -
13 -7d0f_1_A_817-913
14 -Could not find nucleotides of chain A in annotation 7d0f.json. Either there is a problem with 7d0f mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
15 -
16 -1vy7_1_AY_1-73
17 -Sequence is too short. (< 5 resolved nts)
18 -
19 -1vy7_1_CY_1-73
20 -Sequence is too short. (< 5 resolved nts)
21 -
22 -4w2h_1_CY_1-73
23 -Sequence is too short. (< 5 resolved nts)
24 -
25 -7o7z_1_AH_144-220
26 -Could not find nucleotides of chain AH in annotation 7o7z.json. Either there is a problem with 7o7z mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
27 -
28 -4c9d_1_D_29-1
29 -Mapping is reversed, this case is not supported (yet).
30 -
31 -4c9d_1_C_29-1
32 -Mapping is reversed, this case is not supported (yet).
33 -
34 -7aih_1_1_2984-3610
35 -Could not find nucleotides of chain 1 in annotation 7aih.json. Either there is a problem with 7aih mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
36 -
37 -7aih_1_1_2400-2963
38 -Could not find nucleotides of chain 1 in annotation 7aih.json. Either there is a problem with 7aih mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
39 -
40 -7ane_1_2_2489-3115
41 -Could not find nucleotides of chain 2 in annotation 7ane.json. Either there is a problem with 7ane mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
42 -
43 -7ane_1_2_1904-2468
44 -Could not find nucleotides of chain 2 in annotation 7ane.json. Either there is a problem with 7ane mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
45 -
46 -5g2x_1_A_595-692
47 -Sequence is too short. (< 5 resolved nts)
48 -
49 -7aor_1_2_2589-3210
50 -Could not find nucleotides of chain 2 in annotation 7aor.json. Either there is a problem with 7aor mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
51 -
52 -7aor_1_2_2020-2579
53 -Could not find nucleotides of chain 2 in annotation 7aor.json. Either there is a problem with 7aor mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
54 -
55 -7a5p_1_2_259-449
56 -Could not find nucleotides of chain 2 in annotation 7a5p.json. Either there is a problem with 7a5p mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
57 -
58 -7aor_1_A_2589-3210
59 -Could not find nucleotides of chain A in annotation 7aor.json. Either there is a problem with 7aor mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
60 -
61 -7aor_1_A_2020-2579
62 -Could not find nucleotides of chain A in annotation 7aor.json. Either there is a problem with 7aor mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
63 -
64 -7am2_1_1_2491-3117
65 -Could not find nucleotides of chain 1 in annotation 7am2.json. Either there is a problem with 7am2 mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
66 -
67 -7am2_1_1_1904-2470
68 -Could not find nucleotides of chain 1 in annotation 7am2.json. Either there is a problem with 7am2 mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
69 -
70 -7ane_1_1_2489-3115
71 -Could not find nucleotides of chain 1 in annotation 7ane.json. Either there is a problem with 7ane mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
72 -
73 -7ane_1_1_1904-2468
74 -Could not find nucleotides of chain 1 in annotation 7ane.json. Either there is a problem with 7ane mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
75 -
76 -6uz7_1_8_2140-2825
77 -Could not find nucleotides of chain 8 in annotation 6uz7.json. Either there is a problem with 6uz7 mmCIF download, or the bases are not resolved in the structure. Delete it and retry.
78 -
...@@ -3,7 +3,7 @@ ...@@ -3,7 +3,7 @@
3 # run it one or twice a year, otherwise, the faster update runs should be enough. 3 # run it one or twice a year, otherwise, the faster update runs should be enough.
4 4
5 cd /home/lbecquey/Projects/RNANet 5 cd /home/lbecquey/Projects/RNANet
6 -rm -rf latest_run.log errors.txt 6 +rm -rf latest_run.log errors.txt known_issues.txt known_issues_reasons.txt
7 7
8 # Run RNANet 8 # Run RNANet
9 bash -c 'time python3.8 ./RNAnet.py --3d-folder /home/lbecquey/Data/RNA/3D/ --seq-folder /home/lbecquey/Data/RNA/sequences/ --from-scratch --ignore-issues -r 20.0 --no-homology --redundant --extract' > latest_run.log 2>&1 9 bash -c 'time python3.8 ./RNAnet.py --3d-folder /home/lbecquey/Data/RNA/3D/ --seq-folder /home/lbecquey/Data/RNA/sequences/ --from-scratch --ignore-issues -r 20.0 --no-homology --redundant --extract' > latest_run.log 2>&1
......