dtk24.04.1

scripts/download_mgnify.sh

+#!/bin/bash
+#
+# Copyright 2021 DeepMind Technologies Limited
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+# Downloads and unzips the MGnify database for AlphaFold.
+#
+# Usage: bash download_mgnify.sh /path/to/download/directory
+set -e
+
+if [[ $# -eq 0 ]]; then
+    echo "Error: download directory must be provided as an input argument."
+    exit 1
+fi
+
+if ! command -v aria2c &> /dev/null ; then
+    echo "Error: aria2c could not be found. Please install aria2c (sudo apt install aria2)."
+    exit 1
+fi
+
+DOWNLOAD_DIR="$1"
+ROOT_DIR="${DOWNLOAD_DIR}/mgnify"
+# Mirror of:
+# https://ftp.ebi.ac.uk/pub/databases/metagenomics/peptide_database/2022_05/mgy_clusters.fa.gz
+SOURCE_URL="https://storage.googleapis.com/alphafold-databases/v2.3/mgy_clusters_2022_05.fa.gz"
+BASENAME=$(basename "${SOURCE_URL}")
+
+mkdir --parents "${ROOT_DIR}"
+aria2c "${SOURCE_URL}" --dir="${ROOT_DIR}"
+pushd "${ROOT_DIR}"
+gunzip "${ROOT_DIR}/${BASENAME}"
+popd

scripts/download_pdb70.sh

+#!/bin/bash
+#
+# Copyright 2021 DeepMind Technologies Limited
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+# Downloads and unzips the PDB70 database for AlphaFold.
+#
+# Usage: bash download_pdb70.sh /path/to/download/directory
+set -e
+
+if [[ $# -eq 0 ]]; then
+    echo "Error: download directory must be provided as an input argument."
+    exit 1
+fi
+
+if ! command -v aria2c &> /dev/null ; then
+    echo "Error: aria2c could not be found. Please install aria2c (sudo apt install aria2)."
+    exit 1
+fi
+
+DOWNLOAD_DIR="$1"
+ROOT_DIR="${DOWNLOAD_DIR}/pdb70"
+SOURCE_URL="http://wwwuser.gwdg.de/~compbiol/data/hhsuite/databases/hhsuite_dbs/old-releases/pdb70_from_mmcif_200401.tar.gz"
+BASENAME=$(basename "${SOURCE_URL}")
+
+mkdir --parents "${ROOT_DIR}"
+aria2c "${SOURCE_URL}" --dir="${ROOT_DIR}"
+tar --extract --verbose --file="${ROOT_DIR}/${BASENAME}" \
+  --directory="${ROOT_DIR}"
+rm "${ROOT_DIR}/${BASENAME}"

scripts/download_pdb_mmcif.sh

+#!/bin/bash
+#
+# Copyright 2021 DeepMind Technologies Limited
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+# Downloads, unzips and flattens the PDB database for AlphaFold.
+#
+# Usage: bash download_pdb_mmcif.sh /path/to/download/directory
+set -e
+
+if [[ $# -eq 0 ]]; then
+    echo "Error: download directory must be provided as an input argument."
+    exit 1
+fi
+
+if ! command -v aria2c &> /dev/null ; then
+    echo "Error: aria2c could not be found. Please install aria2c (sudo apt install aria2)."
+    exit 1
+fi
+
+if ! command -v rsync &> /dev/null ; then
+    echo "Error: rsync could not be found. Please install rsync."
+    exit 1
+fi
+
+DOWNLOAD_DIR="$1"
+ROOT_DIR="${DOWNLOAD_DIR}/pdb_mmcif"
+RAW_DIR="${ROOT_DIR}/raw"
+MMCIF_DIR="${ROOT_DIR}/mmcif_files"
+
+echo "Running rsync to fetch all mmCIF files (note that the rsync progress estimate might be inaccurate)..."
+echo "If the download speed is too slow, try changing the mirror to:"
+echo "  * rsync.ebi.ac.uk::pub/databases/pdb/data/structures/divided/mmCIF/ (Europe)"
+echo "  * ftp.pdbj.org::ftp_data/structures/divided/mmCIF/ (Asia)"
+echo "or see https://www.wwpdb.org/ftp/pdb-ftp-sites for more download options."
+mkdir --parents "${RAW_DIR}"
+rsync --recursive --links --perms --times --compress --info=progress2 --delete --port=33444 \
+  rsync.rcsb.org::ftp_data/structures/divided/mmCIF/ \
+  "${RAW_DIR}"
+
+echo "Unzipping all mmCIF files..."
+find "${RAW_DIR}/" -type f -iname "*.gz" -exec gunzip {} +
+
+echo "Flattening all mmCIF files..."
+mkdir --parents "${MMCIF_DIR}"
+find "${RAW_DIR}" -type d -empty -delete  # Delete empty directories.
+for subdir in "${RAW_DIR}"/*; do
+  mv "${subdir}/"*.cif "${MMCIF_DIR}"
+done
+
+# Delete empty download directory structure.
+find "${RAW_DIR}" -type d -empty -delete
+
+aria2c "https://files.wwpdb.org/pub/pdb/data/status/obsolete.dat" --dir="${ROOT_DIR}"

scripts/download_pdb_seqres.sh

+#!/bin/bash
+#
+# Copyright 2021 DeepMind Technologies Limited
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+# Downloads and unzips the PDB SeqRes database for AlphaFold.
+#
+# Usage: bash download_pdb_seqres.sh /path/to/download/directory
+set -e
+
+if [[ $# -eq 0 ]]; then
+    echo "Error: download directory must be provided as an input argument."
+    exit 1
+fi
+
+if ! command -v aria2c &> /dev/null ; then
+    echo "Error: aria2c could not be found. Please install aria2c (sudo apt install aria2)."
+    exit 1
+fi
+
+DOWNLOAD_DIR="$1"
+ROOT_DIR="${DOWNLOAD_DIR}/pdb_seqres"
+SOURCE_URL="https://files.wwpdb.org/pub/pdb/derived_data/pdb_seqres.txt"
+BASENAME=$(basename "${SOURCE_URL}")
+
+mkdir --parents "${ROOT_DIR}"
+aria2c "${SOURCE_URL}" --dir="${ROOT_DIR}"
+
+# Keep only protein sequences.
+grep --after-context=1 --no-group-separator '>.* mol:protein' "${ROOT_DIR}/pdb_seqres.txt" > "${ROOT_DIR}/pdb_seqres_filtered.txt"
+mv "${ROOT_DIR}/pdb_seqres_filtered.txt" "${ROOT_DIR}/pdb_seqres.txt"

scripts/download_small_bfd.sh

+#!/bin/bash
+#
+# Copyright 2021 DeepMind Technologies Limited
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+# Downloads and unzips the Small BFD database for AlphaFold.
+#
+# Usage: bash download_small_bfd.sh /path/to/download/directory
+set -e
+
+if [[ $# -eq 0 ]]; then
+    echo "Error: download directory must be provided as an input argument."
+    exit 1
+fi
+
+if ! command -v aria2c &> /dev/null ; then
+    echo "Error: aria2c could not be found. Please install aria2c (sudo apt install aria2)."
+    exit 1
+fi
+
+DOWNLOAD_DIR="$1"
+ROOT_DIR="${DOWNLOAD_DIR}/small_bfd"
+SOURCE_URL="https://storage.googleapis.com/alphafold-databases/reduced_dbs/bfd-first_non_consensus_sequences.fasta.gz"
+BASENAME=$(basename "${SOURCE_URL}")
+
+mkdir --parents "${ROOT_DIR}"
+aria2c "${SOURCE_URL}" --dir="${ROOT_DIR}"
+pushd "${ROOT_DIR}"
+gunzip "${ROOT_DIR}/${BASENAME}"
+popd

scripts/download_uniprot.sh

+#!/bin/bash
+#
+# Copyright 2021 DeepMind Technologies Limited
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+# Downloads, unzips and merges the SwissProt and TrEMBL databases for
+# AlphaFold-Multimer.
+#
+# Usage: bash download_uniprot.sh /path/to/download/directory
+set -e
+
+if [[ $# -eq 0 ]]; then
+    echo "Error: download directory must be provided as an input argument."
+    exit 1
+fi
+
+if ! command -v aria2c &> /dev/null ; then
+    echo "Error: aria2c could not be found. Please install aria2c (sudo apt install aria2)."
+    exit 1
+fi
+
+DOWNLOAD_DIR="$1"
+ROOT_DIR="${DOWNLOAD_DIR}/uniprot"
+
+TREMBL_SOURCE_URL="https://ftp.ebi.ac.uk/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_trembl.fasta.gz"
+TREMBL_BASENAME=$(basename "${TREMBL_SOURCE_URL}")
+TREMBL_UNZIPPED_BASENAME="${TREMBL_BASENAME%.gz}"
+
+SPROT_SOURCE_URL="https://ftp.ebi.ac.uk/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot.fasta.gz"
+SPROT_BASENAME=$(basename "${SPROT_SOURCE_URL}")
+SPROT_UNZIPPED_BASENAME="${SPROT_BASENAME%.gz}"
+
+mkdir --parents "${ROOT_DIR}"
+aria2c "${TREMBL_SOURCE_URL}" --dir="${ROOT_DIR}"
+aria2c "${SPROT_SOURCE_URL}" --dir="${ROOT_DIR}"
+pushd "${ROOT_DIR}"
+gunzip "${ROOT_DIR}/${TREMBL_BASENAME}"
+gunzip "${ROOT_DIR}/${SPROT_BASENAME}"
+
+# Concatenate TrEMBL and SwissProt, rename to uniprot and clean up.
+cat "${ROOT_DIR}/${SPROT_UNZIPPED_BASENAME}" >> "${ROOT_DIR}/${TREMBL_UNZIPPED_BASENAME}"
+mv "${ROOT_DIR}/${TREMBL_UNZIPPED_BASENAME}" "${ROOT_DIR}/uniprot.fasta"
+rm "${ROOT_DIR}/${SPROT_UNZIPPED_BASENAME}"
+popd

scripts/download_uniref30.sh

+#!/bin/bash
+#
+# Copyright 2021 DeepMind Technologies Limited
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+# Downloads and unzips the Uniclust30 database for AlphaFold.
+#
+# Usage: bash download_uniclust30.sh /path/to/download/directory
+set -e
+
+if [[ $# -eq 0 ]]; then
+    echo "Error: download directory must be provided as an input argument."
+    exit 1
+fi
+
+if ! command -v aria2c &> /dev/null ; then
+    echo "Error: aria2c could not be found. Please install aria2c (sudo apt install aria2)."
+    exit 1
+fi
+
+DOWNLOAD_DIR="$1"
+ROOT_DIR="${DOWNLOAD_DIR}/uniref30"
+# Mirror of:
+# https://wwwuser.gwdg.de/~compbiol/uniclust/2021_03/UniRef30_2021_03.tar.gz
+SOURCE_URL="https://storage.googleapis.com/alphafold-databases/v2.3/UniRef30_2021_03.tar.gz"
+BASENAME=$(basename "${SOURCE_URL}")
+
+mkdir --parents "${ROOT_DIR}"
+aria2c "${SOURCE_URL}" --dir="${ROOT_DIR}"
+tar --extract --verbose --file="${ROOT_DIR}/${BASENAME}" \
+  --directory="${ROOT_DIR}"
+rm "${ROOT_DIR}/${BASENAME}"

scripts/download_uniref90.sh

+#!/bin/bash
+#
+# Copyright 2021 DeepMind Technologies Limited
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+# Downloads and unzips the UniRef90 database for AlphaFold.
+#
+# Usage: bash download_uniref90.sh /path/to/download/directory
+set -e
+
+if [[ $# -eq 0 ]]; then
+    echo "Error: download directory must be provided as an input argument."
+    exit 1
+fi
+
+if ! command -v aria2c &> /dev/null ; then
+    echo "Error: aria2c could not be found. Please install aria2c (sudo apt install aria2)."
+    exit 1
+fi
+
+DOWNLOAD_DIR="$1"
+ROOT_DIR="${DOWNLOAD_DIR}/uniref90"
+SOURCE_URL="https://ftp.ebi.ac.uk/pub/databases/uniprot/uniref/uniref90/uniref90.fasta.gz"
+BASENAME=$(basename "${SOURCE_URL}")
+
+mkdir --parents "${ROOT_DIR}"
+aria2c "${SOURCE_URL}" --dir="${ROOT_DIR}"
+pushd "${ROOT_DIR}"
+gunzip "${ROOT_DIR}/${BASENAME}"
+popd

server/README.md

+# JSON file format for AlphaFold Server jobs
+
+You can
+[download an example JSON file here](https://github.com/google-deepmind/alphafold/blob/main/server/example.json);
+here we describe the contents of this example JSON file.
+
+This JSON file consists of a list of dictionaries (even in the case of a single
+dictionary, a single-element list must be used), with each dictionary containing
+a job description. Therefore, you can specify multiple jobs in one JSON file.
+
+Each job description contains a job name, a list of PRNG seeds (which can be an
+empty list for automated random seed assignment), and a list of entities
+(molecules) to be modeled.
+
+AlphaFold Server JSON files are especially useful for automation of repetitive
+modeling jobs (e.g. to screen interactions of one protein with a small number of
+others). The easiest way to construct an initial JSON file is to run a modeling
+job via AlphaFold Server GUI and use it as a template. AlphaFold Server will
+produce a zip file containing modeling results. Inside the zip file you will
+find a JSON file named `<job_name>_job_request.json` containing the job inputs.
+These files offer a convenient starting point for generating new jobs as they
+are easily editable in standard text editors or in programming environments like
+Google Colab notebooks.
+
+Note that comments are not allowed in JSON files.
+
+## Job name, seeds and sequences
+
+*   `name` is a string with the job name. This is how the job will appear as in
+    the job history table.
+*   `modelSeeds` is a list of strings of uint32 seed values (e.g.
+    `["1593933729", "4273"]`). Seeds are used to run the modeling. We recommend
+    providing an empty list, in which case a single random seed will be used.
+    This is the recommended option.
+*   `sequences` is a list of dictionaries that carry descriptions of the
+    entities (molecules) for modeling.
+
+```json
+{
+  "name": "Test Fold Job Number One",
+  "modelSeeds": [],
+  "sequences": [...]
+}
+```
+
+## Entity types
+
+Valid entity types mirror those available in the AlphaFold Server web interface:
+
+*   `proteinChain` – used for proteins
+*   `dnaSequence` – used for DNA (single strand)
+*   `rnaSequence` – used for RNA (single strand)
+*   `ligand` – used for allowed ligands
+*   `ion` – used for allowed ions
+
+### Protein chains
+
+`sequence` is a string containing protein sequence; the same limitations as in
+the UI are in place, e.g. only letters corresponding to amino acids are allowed,
+as defined by IUPAC. Only 20 standard amino acid type are supported.
+
+`count` is the number of copies of this protein chain (integer).
+
+`glycans` is an optional list of dictionaries that carries descriptions of the
+protein glycosylation.
+
+*   `residues` is a string defining glycan. Please refer to the
+    [FAQ](https://alphafoldserver.com/faq) for the format description and
+    allowed glycans.
+*   `position` is a position of the amino acid to which the glycan is attached
+    (integer, 1-based indexing).
+
+`modifications` is an optional list of dictionaries that carries descriptions of
+the post-translational modifications.
+
+*   `ptmType` is a string containing the
+    [CCD code](https://www.wwpdb.org/data/ccd) of the modification; the same
+    codes are allowed as in the UI.
+*   `position` is a position of the modified amino acid (integer).
+*   Allowed modifications: `CCD_SEP`, `CCD_TPO`, `CCD_PTR`, `CCD_NEP`,
+    `CCD_HIP`, `CCD_ALY`, `CCD_MLY`, `CCD_M3L`, `CCD_MLZ`, `CCD_2MR`, `CCD_AGM`,
+    `CCD_MCS`, `CCD_HYP`, `CCD_HY3`, `CCD_LYZ`, `CCD_AHB`, `CCD_P1L`, `CCD_SNN`,
+    `CCD_SNC`, `CCD_TRF`, `CCD_KCR`, `CCD_CIR`, `CCD_YHA`
+
+```json
+{
+  "proteinChain": {
+    "sequence": "PREACHINGS",
+
+    "glycans": [
+      {
+        "residues": "NAG(NAG)(BMA)",
+        "position": 8
+      },
+      {
+        "residues": "BMA",
+        "position": 10
+      }
+    ],
+
+    "modifications": [
+      {
+        "ptmType": "CCD_HY3",
+        "ptmPosition": 1
+      },
+      {
+        "ptmType": "CCD_P1L",
+        "ptmPosition": 5
+      }
+    ],
+
+    "count": 1
+  }
+},
+{
+  "proteinChain": {
+    "sequence": "REACHER",
+    "count": 1
+  }
+}
+```
+
+### DNA chains
+
+Please note that the `dnaSequence` type refers to single stranded DNA. If you
+wish to model double stranded DNA, please add a second `"dnaSequence`", carrying
+the sequence of the reverse complement strand.
+
+`sequence` is a string containing a DNA sequence; the same limitations as in the
+UI are in place, i.e. only letters A, T, G, C are allowed.
+
+`count` is a number of copies of this DNA chain (integer).
+
+`modifications` is an optional list of dictionaries that carries descriptions of
+the DNA chemical modifications.
+
+*   `modificationType` is a string containing
+    [CCD code](https://www.wwpdb.org/data/ccd) of modification; the same codes
+    are allowed as in the UI.
+*   `basePosition` is a position of the modified nucleotide (integer).
+*   Allowed modifications: `CCD_5CM`, `CCD_C34`, `CCD_5HC`, `CCD_6OG`,
+    `CCD_6MA`, `CCD_1CC`, `CCD_8OG`, `CCD_5FC`, `CCD_3DR`
+
+```json
+{
+  "dnaSequence": {
+    "sequence": "GATTACA",
+
+    "modifications": [
+      {
+        "modificationType": "CCD_6OG",
+        "basePosition": 1
+      },
+      {
+        "modificationType": "CCD_6MA",
+        "basePosition": 2
+      }
+    ],
+
+    "count": 1
+  }
+},
+{
+  "dnaSequence": {
+    "sequence": "TGTAATC",
+    "count": 1
+  }
+}
+```
+
+### RNA chains
+
+`sequence` is a string containing RNA sequence (single strand); the same
+limitations as in the UI are in place, e.g. only letters A, U, G, C are allowed.
+
+`count` is a number of copies of this RNA chain (integer).
+
+`modifications` is an optional list of dictionaries that carries descriptions of
+the RNA chemical modifications.
+
+*   `modificationType` is a string containing
+    [CCD code](https://www.wwpdb.org/data/ccd) of modification; the same codes
+    are allowed as in the UI.
+*   `basePosition` is a position of the modified nucleotide (integer).
+*   Allowed modifications: `CCD_PSU`, `CCD_5MC`, `CCD_OMC`, `CCD_4OC`,
+    `CCD_5MU`, `CCD_OMU`, `CCD_UR3`, `CCD_A2M`, `CCD_MA6`, `CCD_6MZ`, `CCD_2MG`,
+    `CCD_OMG`, `CCD_7MG`, `CCD_RSQ`
+
+```json
+{
+  "rnaSequence": {
+    "sequence": "GUAC",
+
+    "modifications": [
+      {
+        "modificationType": "CCD_2MG",
+        "basePosition": 1
+      },
+      {
+        "modificationType": "CCD_5MC",
+        "basePosition": 4
+      }
+    ],
+
+    "count": 1
+  }
+}
+```
+
+### Ligands
+
+`ligand` is a string containing the [CCD code](https://www.wwpdb.org/data/ccd)
+of the ligand; the same codes are allowed as in the UI.
+
+`count` is the number of copies of this ligand (integer).
+
+Allowed ligands: `CCD_ADP`, `CCD_ATP`, `CCD_AMP`, `CCD_GTP`, `CCD_GDP`,
+`CCD_FAD`, `CCD_NAD`, `CCD_NAP`, `CCD_NDP`, `CCD_HEM`, `CCD_HEC`, `CCD_PLM`,
+`CCD_OLA`, `CCD_MYR`, `CCD_CIT`, `CCD_CLA`, `CCD_CHL`, `CCD_BCL`, `CCD_BCB`
+
+```json
+{
+  "ligand": {
+    "ligand": "CCD_ATP",
+    "count": 1
+  }
+},
+{
+  "ligand": {
+    "ligand": "CCD_HEM",
+    "count": 2
+  }
+}
+```
+
+### Ions
+
+`ion` is a string containing [CCD code](https://www.wwpdb.org/data/ccd) of the
+ion; the same codes are allowed as in the UI. The ion charge is implicitly
+specified by the CCD code.
+
+`count` is a number of copies of this ion (integer).
+
+Allowed ions: `MG`, `ZN`, `CL`, `CA`, `NA`, `MN`, `K`, `FE`, `CU`, `CO`
+
+```json
+{
+  "ion": {
+    "ion": "MG",
+    "count": 2
+  }
+},
+{
+  "ion": {
+    "ion": "NA",
+    "count": 3
+  }
+}
+```
+
+# Additional modeling jobs
+
+You may specify multiple jobs in one JSON file. This is an example of a simple
+job request for one protein chain and two copies of the palindromic DNA
+sequence:
+
+```json
+{
+  "name": "Test Fold Job Number Two",
+  "modelSeeds": [],
+  "sequences": [
+    {
+      "proteinChain": {
+        "sequence": "TEACHINGS",
+        "count": 1
+      }
+    },
+    {
+      "dnaSequence": {
+        "sequence": "TAGCTA",
+        "count": 2
+      }
+    }
+  ]
+}
+```

server/example.json

+[
+  {
+    "name": "Test Fold Job Number One",
+    "modelSeeds": [],
+    "sequences": [
+      {
+        "proteinChain": {
+          "sequence": "PREACHINGS",
+          "glycans": [
+            {
+              "residues": "NAG(NAG)(BMA)",
+              "position": 8
+            },
+            {
+              "residues": "BMA",
+              "position": 10
+            }
+          ],
+          "modifications": [
+            {
+              "ptmType": "CCD_HY3",
+              "ptmPosition": 1
+            },
+            {
+              "ptmType": "CCD_P1L",
+              "ptmPosition": 5
+            }
+          ],
+          "count": 1
+        }
+      },
+      {
+        "proteinChain": {
+          "sequence": "REACHER",
+          "count": 1
+        }
+      },
+      {
+        "dnaSequence": {
+          "sequence": "GATTACA",
+          "modifications": [
+            {
+              "modificationType": "CCD_6OG",
+              "basePosition": 1
+            },
+            {
+              "modificationType": "CCD_6MA",
+              "basePosition": 2
+            }
+          ],
+          "count": 1
+        }
+      },
+      {
+        "dnaSequence": {
+          "sequence": "TGTAATC",
+          "count": 1
+        }
+      },
+      {
+        "rnaSequence": {
+          "sequence": "GUAC",
+          "modifications": [
+            {
+              "modificationType": "CCD_2MG",
+              "basePosition": 1
+            },
+            {
+              "modificationType": "CCD_5MC",
+              "basePosition": 4
+            }
+          ],
+          "count": 1
+        }
+      },
+      {
+        "ligand": {
+          "ligand": "CCD_ATP",
+          "count": 1
+        }
+      },
+      {
+        "ligand": {
+          "ligand": "CCD_HEM",
+          "count": 2
+        }
+      },
+      {
+        "ion": {
+          "ion": "MG",
+          "count": 2
+        }
+      },
+      {
+        "ion": {
+          "ion": "NA",
+          "count": 3
+        }
+      }
+    ]
+  },
+  {
+    "name": "Test Fold Job Number Two",
+    "modelSeeds": [],
+    "sequences": [
+      {
+        "proteinChain": {
+          "sequence": "TEACHINGS",
+          "count": 1
+        }
+      },
+      {
+        "dnaSequence": {
+          "sequence": "TAGGACA",
+          "count": 1
+        }
+      }
+    ]
+  }
+]

setup.py

+# Copyright 2021 DeepMind Technologies Limited
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Install script for setuptools."""
+
+from alphafold import version
+from setuptools import find_packages
+from setuptools import setup
+
+setup(
+    name='alphafold',
+    version=version.__version__,
+    description=(
+        'An implementation of the inference pipeline of AlphaFold v2.0. This is'
+        ' a completely new model that was entered as AlphaFold2 in CASP14 and'
+        ' published in Nature.'
+    ),
+    author='DeepMind',
+    author_email='alphafold@deepmind.com',
+    license='Apache License, Version 2.0',
+    url='https://github.com/deepmind/alphafold',
+    packages=find_packages(),
+    install_requires=[
+        # 'absl-py',
+        # 'biopython',
+        # 'chex',
+        # 'dm-haiku',
+        # 'dm-tree',
+        # 'docker',
+        # 'immutabledict',
+        # 'jax',
+        # 'ml-collections',
+        # 'numpy',
+        # 'pandas',
+        # 'scipy',
+        # 'tensorflow-cpu',
+    ],
+    tests_require=[
+        'matplotlib',  # For notebook_utils_test.
+        'mock',
+    ],
+    classifiers=[
+        'Development Status :: 5 - Production/Stable',
+        'Intended Audience :: Science/Research',
+        'License :: OSI Approved :: Apache Software License',
+        'Operating System :: POSIX :: Linux',
+        'Programming Language :: Python :: 3.6',
+        'Programming Language :: Python :: 3.7',
+        'Programming Language :: Python :: 3.8',
+        'Programming Language :: Python :: 3.9',
+        'Programming Language :: Python :: 3.10',
+        'Topic :: Scientific/Engineering :: Artificial Intelligence',
+    ],
+)