Database Setup

cd alphafold3
./fetch_databases.sh [<DB_DIR>]

sudo apt install wget zstd

# Start screen session
screen -S alphafold_dl

# Run download
cd alphafold3
./fetch_databases.sh /data/alphafold_databases

# Detach: Ctrl+A, then D
# Reattach later: screen -r alphafold_dl

/path/to/databases/
├── mmcif_files/
│   ├── 00/
│   ├── 01/
│   ├── 02/
│   ├── ...
│   └── zz/
├── bfd-first_non_consensus_sequences.fasta
├── mgy_clusters_2022_05.fa
├── nt_rna_2023_02_23_clust_seq_id_90_cov_80_rep_seq.fasta
├── pdb_seqres_2022_09_28.fasta
├── rfam_14_9_clust_seq_id_90_cov_80_rep_seq.fasta
├── rnacentral_active_seq_id_90_cov_80_linclust.fasta
├── uniprot_all_2021_04.fa
└── uniref90_2022_05.fa

# GCP: Mount and format SSD
sudo mkdir /mnt/disks/ssd
sudo mkfs.ext4 -F /dev/nvme0n1
sudo mount /dev/nvme0n1 /mnt/disks/ssd

# Copy databases
sudo rsync -avh --progress /path/to/databases/ /mnt/disks/ssd/databases/

# Create 300GB RAM disk
sudo mkdir /mnt/ramdisk
sudo mount -t tmpfs -o size=300G tmpfs /mnt/ramdisk

# Copy most-used databases
cp -r /path/to/databases/* /mnt/ramdisk/

# Copy frequently used databases to SSD
cp /hdd/databases/uniref90_2022_05.fa /ssd/databases/
cp /hdd/databases/mgy_clusters_2022_05.fa /ssd/databases/
cp /hdd/databases/bfd-first_non_consensus_sequences.fasta /ssd/databases/

# Run with multiple db_dir flags
python run_alphafold.py \
    --db_dir=/ssd/databases \
    --db_dir=/hdd/databases \
    ...

python run_alphafold.py \
    --uniref90_database_path="uniref90.fasta@128" \
    --uniref90_z_value=153742194 \
    --jackhmmer_n_cpu=2 \
    --jackhmmer_max_parallel_shards=16 \
    ...

# Set directory permissions
sudo chmod 755 --recursive /path/to/databases

# If running Docker, ensure container can read
sudo chown -R $(id -u):$(id -g) /path/to/databases

docker run -it \
    --volume /path/to/databases:/root/public_databases:ro \
    ...

singularity exec \
    --bind /path/to/databases:/root/public_databases \
    ...

ls -lh /path/to/databases/*.fa*
ls -lh /path/to/databases/mmcif_files/ | head

python run_alphafold.py \
    --json_path=test_input.json \
    --db_dir=/path/to/databases \
    --model_dir=/path/to/models \
    --output_dir=/path/to/output

# Resume wget download
wget -c <url>

# Resume rsync
rsync -avh --progress --partial /source /destination

# Check file integrity
md5sum uniref90_2022_05.fa.gz
# Compare with published checksum

# Re-download if needed
rm corrupted_file.gz
wget <url>

# Check available space
df -h /path/to/databases

# Clean up compressed files after extraction
rm *.gz

# Fix ownership
sudo chown -R $USER:$USER /path/to/databases

# Fix permissions
chmod -R 755 /path/to/databases

# Check paths are absolute
python run_alphafold.py \
    --db_dir=/absolute/path/to/databases \
    ...

# Verify files are readable
cat /path/to/databases/uniref90_2022_05.fa | head