Replace .txt bmDCA parameter files with .npy files

ulupo · ulupo · commit 25d049b884b3 · 2022-07-04T10:53:06.000+02:00
diff --git a/.gitattributes b/.gitattributes
@@ -2,3 +2,4 @@ data/*.txt filter=lfs diff=lfs merge=lfs -text
 data/*.fasta filter=lfs diff=lfs merge=lfs -text
 data/**/*.txt filter=lfs diff=lfs merge=lfs -text
 data/**/*.fasta filter=lfs diff=lfs merge=lfs -text
+data/**/*.npy filter=lfs diff=lfs merge=lfs -text
diff --git a/Contact_prediction_phylogeny.ipynb b/Contact_prediction_phylogeny.ipynb
@@ -222,9 +222,9 @@
     "bmDCA_scores = {}\n",
     "for pfam_family in msa_data:\n",
     "    bmDCA_scores[pfam_family] = {}\n",
-    "    _, J2 = read_bmDCA_parameters(bmDCA_PARAMETERS_DIR / f\"{pfam_family}.txt\")\n",
+    "    J = np.load(bmDCA_PARAMETERS_DIR / f\"{pfam_family}_J.npy\")\n",
     "    idx_subset = np.asarray(idxs_pfam_seqs[pfam_family])  # Restrict to sites matching with the PDB\n",
-    "    bmDCA_scores[pfam_family] = zero_sum_gauge_frob_scores(J2)[idx_subset, :][:, idx_subset]  # Use APC (default)"
+    "    bmDCA_scores[pfam_family] = zero_sum_gauge_frob_scores(J)[idx_subset, :][:, idx_subset]  # Use APC (default)"
    ]
   },
   {
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00004.txt b/data/Synthetic_data/bmDCA_parameters/PF00004.txt
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00004_J.npy b/data/Synthetic_data/bmDCA_parameters/PF00004_J.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c8cb0616ccb19505808c486c1215bf8b470bee46fba540c024d1cfde16510d5
+size 61472000
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00004_h.npy b/data/Synthetic_data/bmDCA_parameters/PF00004_h.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce02f0e808c4ceb7d64bf75c95bb84841f5fc094e8ec658936ddb9860e5b78d
+size 22304
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00005.txt b/data/Synthetic_data/bmDCA_parameters/PF00005.txt
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00005_J.npy b/data/Synthetic_data/bmDCA_parameters/PF00005_J.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e18ff86c91c588dcfe8c1a0b552217c02b6b47ad894d006ddbb5031686744753
+size 66217160
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00005_h.npy b/data/Synthetic_data/bmDCA_parameters/PF00005_h.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e2c281b43bc76dfe792e21dd5a9c765056f72d8697e1064ceb073aae567c18
+size 23144
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00041.txt b/data/Synthetic_data/bmDCA_parameters/PF00041.txt
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00041_J.npy b/data/Synthetic_data/bmDCA_parameters/PF00041_J.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e75a02b6d8f787d84dc99f03c5c196ab4912d97c64ac25d020c6d2393899ff27
+size 25489928
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00041_h.npy b/data/Synthetic_data/bmDCA_parameters/PF00041_h.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c0788b37c3707853d59b2354891883e167a8e4bc0cb9ad262abeadab69336ef
+size 14408
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00072.txt b/data/Synthetic_data/bmDCA_parameters/PF00072.txt
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00072_J.npy b/data/Synthetic_data/bmDCA_parameters/PF00072_J.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fc133fb9e6efe95432ea8d928a7800d9f933a5290d156fa78a000033d93458b
+size 44255360
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00072_h.npy b/data/Synthetic_data/bmDCA_parameters/PF00072_h.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21123825aa5be3ab2a38f3afa95f8d50811174c357985ad10d59352e4dc128e6
+size 18944
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00076.txt b/data/Synthetic_data/bmDCA_parameters/PF00076.txt
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00076_J.npy b/data/Synthetic_data/bmDCA_parameters/PF00076_J.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:641958ba30f87b126042f30f7e2b09590bc781f6bdf6823e5951f4d45da7e0e2
+size 16796936
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00076_h.npy b/data/Synthetic_data/bmDCA_parameters/PF00076_h.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:163f028cd35dd4e2ea45994197b52fd5c0cc1d1251a6c1070e56cac8969d1c23
+size 11720
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00096.txt b/data/Synthetic_data/bmDCA_parameters/PF00096.txt
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00096_J.npy b/data/Synthetic_data/bmDCA_parameters/PF00096_J.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd3ef439e12714968aa5ce1e061804b8c72f74c3fd8c354f158973bbdfca00c8
+size 1866440
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00096_h.npy b/data/Synthetic_data/bmDCA_parameters/PF00096_h.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90a4f60c1d74256f6027428287d6510fb742401b36d4a367164dfd76a98afaba
+size 3992
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00153.txt b/data/Synthetic_data/bmDCA_parameters/PF00153.txt
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00153_J.npy b/data/Synthetic_data/bmDCA_parameters/PF00153_J.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35271209d4df91fb61153a5378bb8866b3f99d60661f92cea71675e00b3e2620
+size 31173536
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00153_h.npy b/data/Synthetic_data/bmDCA_parameters/PF00153_h.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:496802abb06f773bbe2970d079e945e8bb87d5ca588602946720bc885f0cae2c
+size 15920
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00271.txt b/data/Synthetic_data/bmDCA_parameters/PF00271.txt
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00271_J.npy b/data/Synthetic_data/bmDCA_parameters/PF00271_J.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f2596cac58cb29e3e16a2d2fa01402b43b4fdb8b1b430bbdb061e03c7bb99d0
+size 43468616
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00271_h.npy b/data/Synthetic_data/bmDCA_parameters/PF00271_h.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6df4dbd971071790fdb3b01f9c6f9e9a3296dd993cf909b0bca9572aa1d6c9dd
+size 18776
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00397.txt b/data/Synthetic_data/bmDCA_parameters/PF00397.txt
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00397_J.npy b/data/Synthetic_data/bmDCA_parameters/PF00397_J.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1771a53089f84f60fdc12a3c2a85399346f17401d44ec1ed80e91a397533cc2
+size 3390536
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00397_h.npy b/data/Synthetic_data/bmDCA_parameters/PF00397_h.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4bfcec8ea20192e949b047c281cbc5daf0f9e31b806ef92f343b8c989cf2d2e
+size 5336
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00512.txt b/data/Synthetic_data/bmDCA_parameters/PF00512.txt
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00512_J.npy b/data/Synthetic_data/bmDCA_parameters/PF00512_J.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a0fe2f7054fa2bbf513ae4cbbc29833fbc4b8e8a7a17e6ca3afbec790a15aab
+size 15368096
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00512_h.npy b/data/Synthetic_data/bmDCA_parameters/PF00512_h.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f96d78948effcb8797c4ebd1a947635cc4baaa5e5845d9f0746bf2d3250b17a0
+size 11216
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00595.txt b/data/Synthetic_data/bmDCA_parameters/PF00595.txt
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00595_J.npy b/data/Synthetic_data/bmDCA_parameters/PF00595_J.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86c21f3138402fff1c993768cc3e2055933e0ca7dd3f54f4d58c79790f9a8805
+size 23722400
diff --git a/data/Synthetic_data/bmDCA_parameters/PF00595_h.npy b/data/Synthetic_data/bmDCA_parameters/PF00595_h.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0fdd78b3d890e2e900ceb3d657d795e97a8904be86ae772a4804df953f2af28
+size 13904
diff --git a/data/Synthetic_data/bmDCA_parameters/PF01535.txt b/data/Synthetic_data/bmDCA_parameters/PF01535.txt
diff --git a/data/Synthetic_data/bmDCA_parameters/PF01535_J.npy b/data/Synthetic_data/bmDCA_parameters/PF01535_J.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e5586ec6cbc3f011853a5a4e11bc9060881740f7f9cdb9c01538755bf84e215
+size 3390536
diff --git a/data/Synthetic_data/bmDCA_parameters/PF01535_h.npy b/data/Synthetic_data/bmDCA_parameters/PF01535_h.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b22fd5afd2ce6d1cc52e89d88f89b554b1d145afc2cc707a719b4efd853c9f00
+size 5336
diff --git a/data/Synthetic_data/bmDCA_parameters/PF02518.txt b/data/Synthetic_data/bmDCA_parameters/PF02518.txt
diff --git a/data/Synthetic_data/bmDCA_parameters/PF02518_J.npy b/data/Synthetic_data/bmDCA_parameters/PF02518_J.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27fd1ad066c5b997b1b36ca9fba54b1e5290ba44af986e9100670be0f288a4e5
+size 43468616
diff --git a/data/Synthetic_data/bmDCA_parameters/PF02518_h.npy b/data/Synthetic_data/bmDCA_parameters/PF02518_h.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ffc097b527bd0576514d3049537f1245a49ae178753417216fd6f192bd8d65
+size 18776
diff --git a/data/Synthetic_data/bmDCA_parameters/PF07679.txt b/data/Synthetic_data/bmDCA_parameters/PF07679.txt
diff --git a/data/Synthetic_data/bmDCA_parameters/PF07679_J.npy b/data/Synthetic_data/bmDCA_parameters/PF07679_J.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c2e661f13332e47ef59ea196f02dcba7b22d5cb562c594dd8502021adacfaf5
+size 28576928
diff --git a/data/Synthetic_data/bmDCA_parameters/PF07679_h.npy b/data/Synthetic_data/bmDCA_parameters/PF07679_h.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ae740d706dba27beef8ddda05ebf68a732df5e21a5eb30566c588982440329
+size 15248
diff --git a/data/Synthetic_data/bmDCA_parameters/PF13354.txt b/data/Synthetic_data/bmDCA_parameters/PF13354.txt
diff --git a/data/Synthetic_data/bmDCA_parameters/PF13354_J.npy b/data/Synthetic_data/bmDCA_parameters/PF13354_J.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ac684255f60dcd0a3e76df7e5b99409bef46758f49480bfc97b6074012374e2
+size 138311840
diff --git a/data/Synthetic_data/bmDCA_parameters/PF13354_h.npy b/data/Synthetic_data/bmDCA_parameters/PF13354_h.npy
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6373c1586cdb778490c49cc5b745dd3f09edc5cabda10386069279917877f8ae
+size 33392

Original file line number	Diff line number	Diff line change
`@@ -222,9 +222,9 @@`
`222`	`222`	`"bmDCA_scores = {}\n",`
`223`	`223`	`"for pfam_family in msa_data:\n",`
`224`	`224`	`" bmDCA_scores[pfam_family] = {}\n",`
`225`		`- " _, J2 = read_bmDCA_parameters(bmDCA_PARAMETERS_DIR / f\"{pfam_family}.txt\")\n",`
	`225`	`+ " J = np.load(bmDCA_PARAMETERS_DIR / f\"{pfam_family}_J.npy\")\n",`
`226`	`226`	`" idx_subset = np.asarray(idxs_pfam_seqs[pfam_family]) # Restrict to sites matching with the PDB\n",`
`227`		`- " bmDCA_scores[pfam_family] = zero_sum_gauge_frob_scores(J2)[idx_subset, :][:, idx_subset] # Use APC (default)"`
	`227`	`+ " bmDCA_scores[pfam_family] = zero_sum_gauge_frob_scores(J)[idx_subset, :][:, idx_subset] # Use APC (default)"`
`228`	`228`	`]`
`229`	`229`	`},`
`230`	`230`	`{`
Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,3 @@`
	`1`	`+version https://git-lfs.github.com/spec/v1`
	`2`	`+oid sha256:8c8cb0616ccb19505808c486c1215bf8b470bee46fba540c024d1cfde16510d5`
	`3`	`+size 61472000`
Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,3 @@`
	`1`	`+version https://git-lfs.github.com/spec/v1`
	`2`	`+oid sha256:5ce02f0e808c4ceb7d64bf75c95bb84841f5fc094e8ec658936ddb9860e5b78d`
	`3`	`+size 22304`
Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,3 @@`
	`1`	`+version https://git-lfs.github.com/spec/v1`
	`2`	`+oid sha256:e18ff86c91c588dcfe8c1a0b552217c02b6b47ad894d006ddbb5031686744753`
	`3`	`+size 66217160`
Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,3 @@`
	`1`	`+version https://git-lfs.github.com/spec/v1`
	`2`	`+oid sha256:15e2c281b43bc76dfe792e21dd5a9c765056f72d8697e1064ceb073aae567c18`
	`3`	`+size 23144`
Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,3 @@`
	`1`	`+version https://git-lfs.github.com/spec/v1`
	`2`	`+oid sha256:e75a02b6d8f787d84dc99f03c5c196ab4912d97c64ac25d020c6d2393899ff27`
	`3`	`+size 25489928`