dayhoff-tools 1.1.19__py3-none-any.whl → 1.1.21__py3-none-any.whl

dayhoff_tools/__init__.py

@@ -0,0 +1,10 @@
+import importlib.metadata
+
+try:
+    # The package name here should match the 'name' field in your pyproject.toml
+    __version__ = importlib.metadata.version("dayhoff-tools")
+except importlib.metadata.PackageNotFoundError:
+    # This is a fallback for when the package might not be installed (e.g., running from source
+    # without installation, or during development). You can set it to None, "unknown",
+    # or handle it as you see fit.
+    __version__ = "unknown"

dayhoff_tools/cli/utility_commands.py

@@ -437,14 +437,13 @@ def install_dependencies(
         False,
         "--install-project",
         "-p",
-        help="Install the local project package itself into the environment.",
+        help="Install the local project package itself (with 'full' extras) into the environment.",
     ),
 ):
     """Install dependencies based on pyproject.toml.
 
     Ensures uv.lock matches pyproject.toml and syncs the environment.
-    This is the command to run after changing pyproject.toml manually
-    or cloning/pulling a repository.
+    When -p is used, installs the local project with its [full] optional dependencies.
     """
     # ANSI color codes
     BLUE = "\033[94m"
@@ -457,15 +456,26 @@ def install_dependencies(
         print(f"Running command: {BLUE}{' '.join(lock_cmd)}{RESET}")
         subprocess.run(lock_cmd, check=True, capture_output=True)
 
-        # Step 2: Sync environment
-        print("Syncing environment with lock file...")
-        sync_cmd = ["uv", "sync", "--all-groups"]
-        if not install_project:
-            sync_cmd.append("--no-install-project")
-        print(f"Running command: {BLUE}{' '.join(sync_cmd)}{RESET}")
-        subprocess.run(sync_cmd, check=True)
+        if install_project:
+            # Step 2a: Install the project with 'full' extras
+            print("Installing the local project with 'full' extras...")
+            # The .[full] syntax tells pip to install the current project ('.')
+            # with its 'full' optional dependencies.
+            pip_install_cmd = ["uv", "pip", "install", "-e", ".[full]"]
+            print(f"Running command: {BLUE}{' '.join(pip_install_cmd)}{RESET}")
+            subprocess.run(pip_install_cmd, check=True)
 
-        print("Dependencies installed/synced successfully.")
+            print("Project installed with 'full' extras successfully.")
+        else:
+            # Original behavior: Sync environment without installing the project
+            print(
+                "Syncing environment with lock file (project itself will not be installed)..."
+            )
+            # --all-groups ensures all non-project dependencies (like dev) are installed
+            sync_cmd = ["uv", "sync", "--all-groups", "--no-install-project"]
+            print(f"Running command: {BLUE}{' '.join(sync_cmd)}{RESET}")
+            subprocess.run(sync_cmd, check=True)
+            print("Dependencies synced successfully (project not installed).")
 
     except subprocess.CalledProcessError as e:
         stderr_output = e.stderr.decode() if e.stderr else "No stderr output."

dayhoff_tools/deployment/processors.py

@@ -1,3 +1,4 @@
+import csv
 import logging
 import os
 import shlex
@@ -6,6 +7,8 @@ import subprocess
 from abc import ABC, abstractmethod
 from pathlib import Path
 
+from dayhoff_tools.fasta import subset_fasta
+
 logger = logging.getLogger(__name__)
 
 
@@ -267,10 +270,12 @@ class MMSeqsProfileProcessor(Processor):
         # Define INTERMEDIATE output file paths within mmseqs_temp_dir
         intermediate_results_m8_file = mmseqs_temp_dir / "results.m8"
         intermediate_hits_fasta_file = mmseqs_temp_dir / "results.fasta"
+        intermediate_results_as_csv_file = mmseqs_temp_dir / "results_as.csv"
 
         # Define FINAL output file paths within run_base_dir, using target stem
-        final_results_m8_file = run_base_dir / f"{target_fasta_stem}_results.m8"
-        final_hits_fasta_file = run_base_dir / f"{target_fasta_stem}_hits.fasta"
+        final_results_csv_file = run_base_dir / f"{target_fasta_stem}.csv"
+        final_hits_fasta_file = run_base_dir / f"{target_fasta_stem}.fasta"
+        final_hits_txt_file = run_base_dir / f"{target_fasta_stem}.txt"
 
         # --- MMseqs2 Workflow Paths (intermediate files in mmseqs_temp_dir) ---
         query_db = mmseqs_temp_dir / "queryDB"
@@ -405,40 +410,147 @@ class MMSeqsProfileProcessor(Processor):
                 run_base_dir,
             )
 
-            # 9. Extract hit sequences directly to FASTA using createseqfiledb
-            self._run_mmseqs_command(
-                [
-                    "mmseqs",
-                    "createseqfiledb",
-                    str(target_db),  # <i:sequenceDB> - The DB to pull sequences from
-                    str(
-                        result_db
-                    ),  # <i:resultDB> - Contains IDs of target sequences to pull
-                    str(
-                        intermediate_hits_fasta_file
-                    ),  # <o:fastaDB> - Output FASTA file
-                    "--threads",  # createseqfiledb supports --threads
-                    self.num_threads,
-                ],
-                "Extract hit sequences to FASTA via createseqfiledb",
-                run_base_dir,
+            # 8.5 Convert M8 to CSV with headers
+            logger.info(
+                f"Converting M8 results {intermediate_results_m8_file} to CSV {intermediate_results_as_csv_file}"
+            )
+            csv_headers = [
+                "query_id",
+                "target_id",
+                "percent_identity",
+                "alignment_length",
+                "mismatches",
+                "gap_openings",
+                "query_start",
+                "query_end",
+                "target_start",
+                "target_end",
+                "e_value",
+                "bit_score",
+            ]
+            try:
+                if intermediate_results_m8_file.exists():
+                    with open(intermediate_results_m8_file, "r") as m8_in, open(
+                        intermediate_results_as_csv_file, "w", newline=""
+                    ) as csv_out:
+                        writer = csv.writer(csv_out)
+                        writer.writerow(csv_headers)
+                        for line in m8_in:
+                            if line.strip():  # Ensure line is not empty
+                                columns = line.strip().split("\t")
+                                writer.writerow(columns)
+                    logger.info(
+                        f"Successfully converted M8 to CSV: {intermediate_results_as_csv_file}"
+                    )
+                else:
+                    logger.warning(
+                        f"Intermediate M8 file {intermediate_results_m8_file} not found for CSV conversion. CSV will be empty or not created."
+                    )
+                    # Ensure the CSV file is touched if M8 was missing, so downstream move doesn't fail
+                    intermediate_results_as_csv_file.touch()
+            except Exception as e:
+                logger.error(f"Failed to convert M8 to CSV: {e}")
+                # Touch the CSV file in case of error to prevent downstream errors if it's expected
+                if not intermediate_results_as_csv_file.exists():
+                    intermediate_results_as_csv_file.touch()
+                # We might still want to raise e here, depending on desired error handling for CSV conversion failure
+
+            # 9. Extract hit sequences from M8 results using subset_fasta
+            logger.info(f"Parsing M8 results from: {intermediate_results_m8_file}")
+            hit_sequence_ids = set()
+            try:
+                if not intermediate_results_m8_file.exists():
+                    logger.warning(
+                        f"M8 results file {intermediate_results_m8_file} not found. Hits FASTA will be empty."
+                    )
+                    intermediate_hits_fasta_file.touch()  # Create empty hits file
+                else:
+                    with open(intermediate_results_m8_file, "r") as m8_file:
+                        for line in m8_file:
+                            if line.strip():  # Ensure line is not empty
+                                columns = line.strip().split("\t")
+                                if len(columns) >= 2:
+                                    hit_sequence_ids.add(
+                                        columns[1]
+                                    )  # Target ID is the second column
+                    logger.info(
+                        f"Found {len(hit_sequence_ids)} unique target IDs in M8 results."
+                    )
+
+                    if not hit_sequence_ids:
+                        logger.warning(
+                            f"No target IDs found in {intermediate_results_m8_file} after parsing. Output hits FASTA will be empty."
+                        )
+                        intermediate_hits_fasta_file.touch()  # Create empty file
+                    else:
+                        logger.info(
+                            f"Extracting {len(hit_sequence_ids)} hit sequences from {local_target_file} to {intermediate_hits_fasta_file} using subset_fasta."
+                        )
+                        try:
+                            subset_fasta(
+                                fasta_file=str(local_target_file),
+                                output_path=str(intermediate_hits_fasta_file),
+                                target_ids=hit_sequence_ids,
+                                exclude=False,
+                                return_written_ids=False,
+                            )
+                            logger.info(
+                                f"Successfully created hits FASTA: {intermediate_hits_fasta_file} using subset_fasta."
+                            )
+                        except FileNotFoundError as e:
+                            logger.error(
+                                f"subset_fasta FileNotFoundError: {e}. Ensuring {intermediate_hits_fasta_file} exists as empty."
+                            )
+                            if not intermediate_hits_fasta_file.exists():
+                                intermediate_hits_fasta_file.touch()
+                            raise
+                        except Exception as e:
+                            logger.error(
+                                f"subset_fasta failed to create {intermediate_hits_fasta_file}: {e}"
+                            )
+                            if not intermediate_hits_fasta_file.exists():
+                                intermediate_hits_fasta_file.touch()
+                            raise
+            except Exception as e:
+                logger.error(
+                    f"Error processing M8 file {intermediate_results_m8_file} or its hits extraction: {e}"
+                )
+                if not intermediate_hits_fasta_file.exists():
+                    intermediate_hits_fasta_file.touch()
+                raise
+
+            # 10. Write the set of hit sequence IDs to a .txt file
+            logger.info(
+                f"Writing {len(hit_sequence_ids)} hit sequence IDs to {final_hits_txt_file}"
             )
+            try:
+                with open(final_hits_txt_file, "w") as txt_out:
+                    for seq_id in sorted(
+                        list(hit_sequence_ids)
+                    ):  # Sort for consistent output
+                        txt_out.write(f"{seq_id}\n")
+                logger.info(f"Successfully wrote hit IDs to {final_hits_txt_file}")
+            except Exception as e:
+                logger.error(f"Failed to write hit IDs to {final_hits_txt_file}: {e}")
+                # The main workflow should still proceed even if this supplementary file fails
 
             logger.info(
                 f"MMseqs2 workflow completed successfully. Intermediate outputs in {mmseqs_temp_dir}"
             )
 
             # Move and rename final output files from mmseqs_temp_dir to run_base_dir
-            if intermediate_results_m8_file.exists():
+            if intermediate_results_as_csv_file.exists():
                 shutil.move(
-                    str(intermediate_results_m8_file), str(final_results_m8_file)
+                    str(intermediate_results_as_csv_file), str(final_results_csv_file)
+                )
+                logger.info(
+                    f"Moved and renamed M8 results to CSV: {final_results_csv_file}"
                 )
-                logger.info(f"Moved and renamed M8 results to {final_results_m8_file}")
             else:
                 logger.warning(
-                    f"Intermediate M8 file {intermediate_results_m8_file} not found. Creating empty target file."
+                    f"Intermediate CSV file {intermediate_results_as_csv_file} not found. Creating empty target CSV file."
                 )
-                final_results_m8_file.touch()  # Create empty file in run_base_dir if not found
+                final_results_csv_file.touch()  # Create empty file in run_base_dir if not found
 
             if intermediate_hits_fasta_file.exists():
                 shutil.move(

{dayhoff_tools-1.1.19.dist-info → dayhoff_tools-1.1.21.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: dayhoff-tools
-Version: 1.1.19
+Version: 1.1.21
 Summary: Common tools for all the repos at Dayhoff Labs
 Author: Daniel Martin-Alarcon
 Author-email: dma@dayhofflabs.com

{dayhoff_tools-1.1.19.dist-info → dayhoff_tools-1.1.21.dist-info}/RECORD

@@ -1,17 +1,17 @@
-dayhoff_tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+dayhoff_tools/__init__.py,sha256=M5zThPyEBRYa5CfwlzKhcqTevWn3OKu62cjV6Zqie2A,469
 dayhoff_tools/chemistry/standardizer.py,sha256=uMn7VwHnx02nc404eO6fRuS4rsl4dvSPf2ElfZDXEpY,11188
 dayhoff_tools/chemistry/utils.py,sha256=jt-7JgF-GeeVC421acX-bobKbLU_X94KNOW24p_P-_M,2257
 dayhoff_tools/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 dayhoff_tools/cli/cloud_commands.py,sha256=NGux28-cjDyCADF-L1tjdEMzkCMYX8V4xNvpK6EWcZA,40802
 dayhoff_tools/cli/main.py,sha256=47EGb28ALaYFc7oAUGlY1D66AIDmc4RZiXxN-gPVrpQ,4519
 dayhoff_tools/cli/swarm_commands.py,sha256=5EyKj8yietvT5lfoz8Zx0iQvVaNgc3SJX1z2zQR6o6M,5614
-dayhoff_tools/cli/utility_commands.py,sha256=PRShdh4O35JfjVxTOsduZ8-grGF5-SfXihcptcFT-hk,23584
+dayhoff_tools/cli/utility_commands.py,sha256=08MMLlQZEjJ_r7Cd6b92aYYPjH7gMvMQvCOcpoNnFVo,24352
 dayhoff_tools/deployment/base.py,sha256=8tXwsPYvRo-zV-aNhHw1c7Rji-KWg8S5xoCCznFnVVI,17412
 dayhoff_tools/deployment/deploy_aws.py,sha256=O0gQxHioSU_sNU8T8MD4wSOPvWc--V8eRRZzlRu035I,16446
 dayhoff_tools/deployment/deploy_gcp.py,sha256=DxBM4sUzwPK9RWLP9bSfr38n1HHl-TVrp4TsbdN8pUA,5795
 dayhoff_tools/deployment/deploy_utils.py,sha256=StFwbqnr2_FWiKVg3xnJF4kagTHzndqqDkpaIOaAn_4,26027
 dayhoff_tools/deployment/job_runner.py,sha256=4tmdplpvqSE9bVxRWHo2U5kwkYrYod0Uwzpg2Q7qG5o,4850
-dayhoff_tools/deployment/processors.py,sha256=4a8fYFilcbBGAVUeowjL5n-Pa7NIL3Jmhs69lCQIkpQ,19554
+dayhoff_tools/deployment/processors.py,sha256=0D2r2-NgVcFfxF0QSqLZy86cxEWSn78jLTKYf60fLBQ,25519
 dayhoff_tools/deployment/swarm.py,sha256=MGcS2_x4RNFtnVjWlU_SwNfhICz8NlGYr9cYBK4ZKDA,21688
 dayhoff_tools/embedders.py,sha256=CRgcb2z7KeeFrRQawyUZuJ4Yi0-J5jSr0hwuRhjG_FI,36513
 dayhoff_tools/fasta.py,sha256=e7xw3pInoupqCGE0-fJTOzmW_earL1M7qPyoqIPfUT4,46269
@@ -26,7 +26,7 @@ dayhoff_tools/intake/uniprot.py,sha256=BZYJQF63OtPcBBnQ7_P9gulxzJtqyorgyuDiPeOJq
 dayhoff_tools/logs.py,sha256=DKdeP0k0kliRcilwvX0mUB2eipO5BdWUeHwh-VnsICs,838
 dayhoff_tools/sqlite.py,sha256=jV55ikF8VpTfeQqqlHSbY8OgfyfHj8zgHNpZjBLos_E,18672
 dayhoff_tools/warehouse.py,sha256=TqV8nex1AluNaL4JuXH5zuu9P7qmE89lSo6f_oViy6U,14965
-dayhoff_tools-1.1.19.dist-info/METADATA,sha256=40SO5LPPs3GIs_bHfr5jt-TpZUb05-5EHz6Uo09TdxI,2225
-dayhoff_tools-1.1.19.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-dayhoff_tools-1.1.19.dist-info/entry_points.txt,sha256=iAf4jteNqW3cJm6CO6czLxjW3vxYKsyGLZ8WGmxamSc,49
-dayhoff_tools-1.1.19.dist-info/RECORD,,
+dayhoff_tools-1.1.21.dist-info/METADATA,sha256=R6Q1CWHxPpXkuYs0OwJ-WSSb9pnPIS8V4xbZHKjugZE,2225
+dayhoff_tools-1.1.21.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+dayhoff_tools-1.1.21.dist-info/entry_points.txt,sha256=iAf4jteNqW3cJm6CO6czLxjW3vxYKsyGLZ8WGmxamSc,49
+dayhoff_tools-1.1.21.dist-info/RECORD,,