File size: 7,197 Bytes
b26b7a0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 |
"""Models for the Folding Studio API."""
import logging
import os
from pathlib import Path
from typing import Any
import gradio as gr
import numpy as np
from folding_studio.client import Client
from folding_studio.query import Query
from folding_studio.query.boltz import BoltzQuery
from folding_studio.query.chai import ChaiQuery
from folding_studio.query.protenix import ProtenixQuery
from folding_studio_demo.model_fasta_validators import (
BaseFastaValidator,
BoltzFastaValidator,
ChaiFastaValidator,
ProtenixFastaValidator,
)
logger = logging.getLogger(__name__)
class AF3Model:
def __init__(
self, api_key: str, model_name: str, query: Query, validator: BaseFastaValidator
):
self.api_key = api_key
self.model_name = model_name
self.query = query
self.validator = validator
def call(
self, seq_file: Path | str, output_dir: Path, format_fasta: bool = False
) -> None:
"""Predict protein structure from amino acid sequence using AF3 model.
Args:
seq_file (Path | str): Path to FASTA file containing amino acid sequence
output_dir (Path): Path to output directory
format_description (bool): Whether to format the description of the sequence
"""
# Validate FASTA format before calling
is_valid, error_msg = self.check_file_description(seq_file)
if format_fasta and not is_valid:
logger.info("Invalid FASTA file format, forcing formatting...")
self.format_fasta(seq_file)
elif not is_valid:
logger.error(error_msg)
raise gr.Error(error_msg)
# Create a client using API key
logger.info("Authenticating client with API key")
client = Client.from_api_key(api_key=self.api_key)
# Define query
query: Query = self.query.from_file(path=seq_file, query_name="gradio")
query.save_parameters(output_dir)
logger.info("Payload: %s", query.payload)
# Send a request
logger.info(f"Sending {self.model_name} request to Folding Studio API")
response = client.send_request(
query, project_code=os.environ["FOLDING_PROJECT_CODE"]
)
# Access confidence data
logger.info("Confidence data: %s", response.confidence_data)
response.download_results(output_dir=output_dir, force=True, unzip=True)
logger.info("Results downloaded to %s", output_dir)
def format_fasta(self, seq_file: Path | str) -> None:
"""Format sequence to FASTA format.
Args:
seq_file (Path | str): Path to FASTA file
"""
formatted_fasta = self.validator.transform_fasta(seq_file)
with open(seq_file, "w") as f:
f.write(formatted_fasta)
def predictions(self, output_dir: Path) -> list[Path]:
"""Get the path to the prediction.
Args:
output_dir (Path): Path to output directory
Returns:
list[Path]: List of paths to predictions
"""
raise NotImplementedError()
def has_prediction(self, output_dir: Path) -> bool:
"""Check if prediction exists in output directory."""
return len(self.predictions(output_dir)) > 0
def check_file_description(self, seq_file: Path | str) -> tuple[bool, str | None]:
"""Check if the file description is correct.
Args:
seq_file (Path | str): Path to FASTA file
Returns:
tuple[bool, str | None]: Tuple containing a boolean indicating if the format is correct and an error message if not
"""
is_valid, error_msg = self.validator.is_valid_fasta(seq_file)
if not is_valid:
return False, error_msg
return True, None
class ChaiModel(AF3Model):
def __init__(self, api_key: str):
super().__init__(api_key, "Chai", ChaiQuery, ChaiFastaValidator())
def call(
self, seq_file: Path | str, output_dir: Path, format_fasta: bool = False
) -> None:
"""Predict protein structure from amino acid sequence using Chai model.
Args:
seq_file (Path | str): Path to FASTA file containing amino acid sequence
output_dir (Path): Path to output directory
format_fasta (bool): Whether to format the FASTA file
"""
super().call(seq_file, output_dir, format_fasta)
def predictions(self, output_dir: Path) -> dict[Path, dict[str, Any]]:
"""Get the path to the prediction."""
prediction = next(output_dir.rglob("pred.model_idx_[0-9].cif"), None)
if prediction is None:
return {}
cif_files = {
int(f.stem.split("model_idx_")[1]): f
for f in prediction.parent.glob("pred.model_idx_*.cif")
}
# Get all npz files and extract their indices
npz_files = {
int(f.stem.split("model_idx_")[1]): f
for f in prediction.parent.glob("scores.model_idx_*.npz")
}
# Find common indices and create pairs
common_indices = sorted(set(cif_files.keys()) & set(npz_files.keys()))
return {
idx: {"prediction_path": cif_files[idx], "metrics": np.load(npz_files[idx])}
for idx in common_indices
}
class ProtenixModel(AF3Model):
def __init__(self, api_key: str):
super().__init__(api_key, "Protenix", ProtenixQuery, ProtenixFastaValidator())
def call(
self, seq_file: Path | str, output_dir: Path, format_fasta: bool = False
) -> None:
"""Predict protein structure from amino acid sequence using Protenix model.
Args:
seq_file (Path | str): Path to FASTA file containing amino acid sequence
output_dir (Path): Path to output directory
format_fasta (bool): Whether to format the FASTA file
"""
super().call(seq_file, output_dir, format_fasta)
def predictions(self, output_dir: Path) -> list[Path]:
"""Get the path to the prediction."""
return list(output_dir.rglob("*_model_[0-9].cif"))
class BoltzModel(AF3Model):
def __init__(self, api_key: str):
super().__init__(api_key, "Boltz", BoltzQuery, BoltzFastaValidator())
def call(
self, seq_file: Path | str, output_dir: Path, format_fasta: bool = False
) -> None:
"""Predict protein structure from amino acid sequence using Boltz model.
Args:
seq_file (Path | str): Path to FASTA file containing amino acid sequence
output_dir (Path): Path to output directory
format_fasta (bool): Whether to format the FASTA file
"""
super().call(seq_file, output_dir, format_fasta)
def predictions(self, output_dir: Path) -> list[Path]:
"""Get the path to the prediction."""
prediction_paths = list(output_dir.rglob("*_model_[0-9].cif"))
return {
int(cif_path.stem[-1]): {
"prediction_path": cif_path,
"metrics": np.load(list(cif_path.parent.glob("plddt_*.npz"))[0]),
}
for cif_path in prediction_paths
}
|