encode-toolkit 0.3.2__py3-none-any.whl → 0.3.4__py3-none-any.whl

encode_connector/__init__.py

@@ -1,4 +1,9 @@
 """ENCODE Project connector - MCP server and Python client."""
 
-__version__ = "0.2.1"
+from importlib.metadata import PackageNotFoundError, version
+
+try:
+    __version__ = version("encode-toolkit")
+except PackageNotFoundError:  # a source tree that is not installed
+    __version__ = "0+unknown"
 __author__ = "Dr. Alex M. Mawla, PhD"

encode_connector/client/constants.py

@@ -12,12 +12,21 @@ DOWNLOAD_CONCURRENCY = 3
 DEFAULT_TIMEOUT = 30.0
 DOWNLOAD_TIMEOUT = 300.0
 DEFAULT_LIMIT = 25
+# Frame for a single experiment. "page" is "embedded" plus the "audit" property; with
+# "embedded" ENCODE omits the audits and every experiment looks free of errors and warnings.
+EXPERIMENT_FRAME = "page"
+# experiments read per request while a file search walks the experiments of one organism
+EXPERIMENT_PAGE_SIZE = 200
+# ...and how many experiments it reads at most: each one costs a request to ENCODE
+MAX_EXPERIMENTS_SCANNED = 1000
+# files of one experiment read per request during that walk
+FILES_PAGE_SIZE = 200
 try:
     import importlib.metadata
 
     _version = importlib.metadata.version("encode-toolkit")
 except importlib.metadata.PackageNotFoundError:
-    _version = "0.3.2"
+    _version = "0.3.4"
 USER_AGENT = f"encode-toolkit/{_version} (MCP; +https://github.com/ammawla/encode-toolkit)"
 
 # Keyring service name for credential storage
@@ -239,8 +248,18 @@ FILE_FORMATS = [
     "vcf",
     "bigInteract",
     "idx",
-    "dat",
     "txt",
+    "h5ad",
+    "hdf5",
+    "sam",
+    "wig",
+    "starch",
+    "chain",
+    "PWM",
+    "btr",
+    "cndb",
+    "nucle3d",
+    "yaml",
 ]
 
 OUTPUT_TYPES = [
@@ -277,7 +296,6 @@ OUTPUT_TYPES = [
     "pseudoreplicated peaks",
     "pseudoreplicated IDR thresholded peaks",
     "replicated peaks",
-    "stable peaks",
     "hotspots",
     "footprints",
     "peaks and background as input for IDR",
@@ -289,6 +307,10 @@ OUTPUT_TYPES = [
     "filtered peaks",
     # Quantifications
     "gene quantifications",
+    "sparse gene count matrix of unique reads",
+    "sparse gene count matrix of all reads",
+    "unfiltered sparse gene count matrix of unique reads",
+    "unfiltered sparse gene count matrix of all reads",
     "transcript quantifications",
     "exon quantifications",
     "microRNA quantifications",
@@ -347,7 +369,6 @@ OUTPUT_CATEGORIES = [
     "annotation",
     "quantification",
     "reference",
-    "quality metric",
 ]
 
 FILE_STATUSES = [
@@ -381,6 +402,14 @@ ASSEMBLIES = [
     "dm3",
     "ce11",
     "ce10",
+    "GRCh38-minimal",
+    "mm10-minimal",
+    "T2T-CHM13",
+    "J02459.1",
+    "ENC001.1",
+    "ENC002.1",
+    "ENC003.1",
+    "ENC004.1",
 ]
 
 LIFE_STAGES = [
@@ -416,6 +445,28 @@ METADATA_MAP = {
 }
 
 # ENCODE API parameter name mapping (user-friendly -> API param)
+# Fields requested from /search/?type=Experiment. They are what ExperimentSummary.from_api
+# reads; naming them makes the API embed labels instead of returning object paths.
+EXPERIMENT_SEARCH_FIELDS = (
+    "accession",
+    "assay_title",
+    "target.label",
+    "biosample_summary",
+    "biosample_ontology.classification",
+    "biosample_ontology.organ_slims",
+    "replicates.library.biosample.organism.scientific_name",
+    "status",
+    "date_released",
+    "description",
+    "lab.title",
+    "files.@id",
+    "replication_type",
+    "life_stage_age",
+    "assembly",
+    "audit",
+    "dbxrefs",
+)
+
 EXPERIMENT_FILTER_MAP = {
     "assay_title": "assay_title",
     "organism": "replicates.library.biosample.donor.organism.scientific_name",

encode_connector/client/encode_client.py

@@ -19,7 +19,12 @@ from encode_connector.client.constants import (
     DEFAULT_LIMIT,
     DEFAULT_TIMEOUT,
     EXPERIMENT_FILTER_MAP,
+    EXPERIMENT_FRAME,
+    EXPERIMENT_PAGE_SIZE,
+    EXPERIMENT_SEARCH_FIELDS,
     FILE_FILTER_MAP,
+    FILES_PAGE_SIZE,
+    MAX_EXPERIMENTS_SCANNED,
     MAX_REQUESTS_PER_SECOND,
     METADATA_MAP,
     USER_AGENT,
@@ -236,10 +241,14 @@ class EncodeClient:
         Returns dict with 'results' (list of ExperimentSummary) and 'total' count.
         """
         limit = clamp_limit(limit)
+        offset = max(0, offset)
+        # frame=object replaces linked objects with paths ("/targets/H3K4me1-human/"), which
+        # loses the labels the filters use, the organ, the organism and the assemblies. Naming
+        # the fields makes the API embed exactly those.
         params: dict[str, Any] = {
             "type": "Experiment",
             "format": "json",
-            "frame": "object",
+            "field": list(EXPERIMENT_SEARCH_FIELDS),
             "limit": limit,
         }
         if offset > 0:
@@ -297,11 +306,11 @@ class EncodeClient:
         }
 
     async def get_experiment_raw(self, accession: str) -> dict:
-        """Get raw experiment data with embedded frame."""
+        """Get raw experiment data: linked objects embedded, audits included."""
         validate_accession(accession)
         return await self._request(
             f"/experiments/{accession}/",
-            {"format": "json", "frame": "embedded"},
+            {"format": "json", "frame": EXPERIMENT_FRAME},
         )
 
     async def get_experiment(self, accession: str) -> ExperimentDetail:
@@ -310,7 +319,7 @@ class EncodeClient:
         # Get experiment data
         exp_data = await self._request(
             f"/experiments/{accession}/",
-            {"format": "json", "frame": "embedded"},
+            {"format": "json", "frame": EXPERIMENT_FRAME},
         )
 
         # Get files for this experiment
@@ -343,6 +352,7 @@ class EncodeClient:
         status: str | None = None,
         preferred_default: bool | None = None,
         limit: int = 200,
+        offset: int = 0,
     ) -> list[FileSummary]:
         """List files for a specific experiment with optional filters."""
         validate_accession(experiment_accession)
@@ -354,6 +364,8 @@ class EncodeClient:
             "frame": "object",
             "limit": limit,
         }
+        if offset > 0:
+            params["from"] = offset
 
         filter_values = {
             "file_format": file_format,
@@ -395,6 +407,7 @@ class EncodeClient:
     ) -> dict[str, Any]:
         """Search files across all experiments with combined filters."""
         limit = clamp_limit(limit)
+        offset = max(0, offset)
         params: dict[str, Any] = {
             "type": "File",
             "format": "json",
@@ -434,41 +447,60 @@ class EncodeClient:
         # For organism filtering on files, we need a two-step approach:
         # search experiments first, then get files from matching experiments
         if organism:
-            # For non-human organisms, do a two-step search
-            exp_result = await self.search_experiments(
-                assay_title=assay_title,
-                organism=organism,
-                organ=organ,
-                biosample_type=biosample_type,
-                target=target,
-                status=status or "released",
-                search_term=search_term,
-                limit=200,
-            )
-            if not exp_result["results"]:
-                return {"results": [], "total": 0, "limit": limit, "offset": offset}
-
-            # Get files from matching experiments
-            all_files = []
-            for exp in exp_result["results"]:
-                exp_files = await self.list_files(
-                    experiment_accession=exp.accession,
-                    file_format=file_format,
-                    file_type=file_type,
-                    output_type=output_type,
-                    output_category=output_category,
-                    assembly=assembly,
-                    status=status,
-                    preferred_default=preferred_default,
+            # Collect one file past the requested page so the caller can tell that more exist.
+            # Matching files may belong to experiments far down the list, so keep reading
+            # experiment pages until the page is full or the experiments run out.
+            wanted = offset + limit + 1
+            all_files: list[FileSummary] = []
+            experiment_offset = 0
+            experiment_total = 0
+            while len(all_files) < wanted and experiment_offset < MAX_EXPERIMENTS_SCANNED:
+                exp_result = await self.search_experiments(
+                    assay_title=assay_title,
+                    organism=organism,
+                    organ=organ,
+                    biosample_type=biosample_type,
+                    target=target,
+                    status=status or "released",
+                    search_term=search_term,
+                    limit=EXPERIMENT_PAGE_SIZE,
+                    offset=experiment_offset,
                 )
-                all_files.extend(exp_files)
-                if len(all_files) >= limit:
+                experiments = exp_result["results"]
+                experiment_total = exp_result.get("total", 0)
+                for exp in experiments:
+                    # one experiment can hold more files than a request returns
+                    file_offset = 0
+                    while len(all_files) < wanted:
+                        exp_files = await self.list_files(
+                            experiment_accession=exp.accession,
+                            file_format=file_format,
+                            file_type=file_type,
+                            output_type=output_type,
+                            output_category=output_category,
+                            assembly=assembly,
+                            status=status,
+                            preferred_default=preferred_default,
+                            limit=FILES_PAGE_SIZE,
+                            offset=file_offset,
+                        )
+                        all_files.extend(exp_files)
+                        file_offset += len(exp_files)
+                        if len(exp_files) < FILES_PAGE_SIZE:
+                            break
+                    if len(all_files) >= wanted:
+                        break
+                experiment_offset += len(experiments)
+                if not experiments or experiment_offset >= experiment_total:
                     break
 
+            total_note = "Lower bound: files collected so far from matching experiments, not the full count"
+            if len(all_files) < wanted and experiment_total > experiment_offset >= MAX_EXPERIMENTS_SCANNED:
+                total_note += f"; stopped after reading {experiment_offset} of {experiment_total} experiments"
             return {
-                "results": all_files[:limit],
+                "results": all_files[offset : offset + limit],
                 "total": len(all_files),
-                "total_note": "Approximate — based on files collected from matching experiments",
+                "total_note": total_note,
                 "limit": limit,
                 "offset": offset,
             }

encode_connector/client/models.py

@@ -12,6 +12,30 @@ def _extract_assemblies(file_list: list | None) -> list[str]:
     return sorted(set(f.get("assembly", "") for f in file_list if isinstance(f, dict) and f.get("assembly")))
 
 
+def _experiment_assemblies(data: dict, file_list: list) -> list[str]:
+    """Assemblies of an experiment: its own ``assembly`` list, else those of its embedded files."""
+    own = data.get("assembly")
+    if isinstance(own, list) and own:
+        return sorted({name for name in own if isinstance(name, str) and name})
+    return _extract_assemblies(file_list)
+
+
+def _experiment_organism(data: dict) -> str:
+    """Organism of an experiment. Search results carry it on the replicates' biosamples."""
+    organism = data.get("organism")
+    if isinstance(organism, dict) and organism.get("scientific_name"):
+        return organism["scientific_name"]
+    names: list[str] = []
+    for replicate in data.get("replicates") or []:
+        if not isinstance(replicate, dict):
+            continue
+        biosample = (replicate.get("library") or {}).get("biosample") or {}
+        name = (biosample.get("organism") or {}).get("scientific_name", "") if isinstance(biosample, dict) else ""
+        if name and name not in names:
+            names.append(name)
+    return ", ".join(names)
+
+
 def _extract_audit_counts(data: dict) -> dict[str, int]:
     """Extract all 4 ENCODE audit level counts from an experiment dict.
 
@@ -57,7 +81,7 @@ class ExperimentSummary(BaseModel):
 
     @classmethod
     def from_api(cls, data: dict) -> ExperimentSummary:
-        """Parse from ENCODE API experiment object (frame=object)."""
+        """Parse a search hit (the fields EXPERIMENT_SEARCH_FIELDS asks for) or an embedded object."""
         # Extract target label
         target = ""
         if data.get("target"):
@@ -90,7 +114,7 @@ class ExperimentSummary(BaseModel):
                 biosample_type = ont
 
         file_list = data.get("files") or []
-        assemblies = _extract_assemblies(file_list)
+        assemblies = _experiment_assemblies(data, file_list)
         audit_counts = _extract_audit_counts(data)
 
         # Extract dbxrefs (GEO accessions, etc.)
@@ -103,9 +127,7 @@ class ExperimentSummary(BaseModel):
             assay_title=data.get("assay_title", ""),
             target=target,
             biosample_summary=data.get("biosample_summary", ""),
-            organism=data.get("organism", {}).get("scientific_name", "")
-            if isinstance(data.get("organism"), dict)
-            else "",
+            organism=_experiment_organism(data),
             organ=organ,
             biosample_type=biosample_type,
             status=data.get("status", ""),

encode_connector/client/tracker.py

@@ -23,6 +23,21 @@ logger = logging.getLogger(__name__)
 
 DEFAULT_DB_PATH = Path.home() / ".encode_connector" / "tracker.db"
 
+ASSEMBLY_SEPARATOR = ", "
+
+
+def _assembly_text(assembly: str | list[str] | None) -> str:
+    """Return the assembly value as the text the assembly column stores.
+
+    Experiment models carry ``assembly`` as a list (an experiment can have files on several
+    assemblies), and SQLite cannot bind a list, so the names are joined into one string.
+    """
+    if not assembly:
+        return ""
+    if isinstance(assembly, str):
+        return assembly
+    return ASSEMBLY_SEPARATOR.join(assembly)
+
 
 class ExperimentTracker:
     """SQLite-backed experiment tracker for ENCODE data."""
@@ -204,7 +219,7 @@ class ExperimentTracker:
                     experiment_data.get("description", ""),
                     experiment_data.get("lab", ""),
                     experiment_data.get("award", ""),
-                    experiment_data.get("assembly", ""),
+                    _assembly_text(experiment_data.get("assembly")),
                     experiment_data.get("replication_type", ""),
                     experiment_data.get("life_stage", ""),
                     experiment_data.get("url", ""),
@@ -237,7 +252,7 @@ class ExperimentTracker:
                     experiment_data.get("description", ""),
                     experiment_data.get("lab", ""),
                     experiment_data.get("award", ""),
-                    experiment_data.get("assembly", ""),
+                    _assembly_text(experiment_data.get("assembly")),
                     experiment_data.get("replication_type", ""),
                     experiment_data.get("life_stage", ""),
                     experiment_data.get("url", ""),
@@ -332,6 +347,17 @@ class ExperimentTracker:
         conn = self._get_conn()
         count = 0
         for pub in publications:
+            # The table is unique on (experiment, pmid). ENCODE lists some papers without a
+            # PMID; stored as "" they would all replace each other, so they are stored as NULL
+            # (which SQLite never treats as equal) and matched on DOI and title instead.
+            pmid = pub.get("pmid") or None
+            if pmid is None:
+                conn.execute(
+                    # older versions stored a missing PMID as "": replace such a row too
+                    "DELETE FROM publications WHERE experiment_accession = ? "
+                    "AND (pmid IS NULL OR pmid = '') AND doi = ? AND title = ?",
+                    (accession, pub.get("doi", ""), pub.get("title", "")),
+                )
             try:
                 conn.execute(
                     """
@@ -341,7 +367,7 @@ class ExperimentTracker:
                 """,
                     (
                         accession,
-                        pub.get("pmid", ""),
+                        pmid,
                         pub.get("doi", ""),
                         pub.get("title", ""),
                         pub.get("authors", ""),
@@ -363,7 +389,8 @@ class ExperimentTracker:
             "SELECT * FROM publications WHERE experiment_accession = ?",
             (accession,),
         ).fetchall()
-        return [dict(r) for r in rows]
+        # a missing PMID is stored as NULL; callers keep getting the empty string they always got
+        return [{**dict(r), "pmid": r["pmid"] or ""} for r in rows]
 
     # ------------------------------------------------------------------
     # Pipeline info
@@ -584,15 +611,19 @@ class ExperimentTracker:
             else:
                 compatible_aspects.append(f"Same organism: {exp1['organism']}")
 
-        # Check assembly
+        # Check assembly. An experiment can have files on several assemblies, stored as one
+        # joined string, so two experiments are comparable when they share at least one.
         if exp1.get("assembly") and exp2.get("assembly"):
-            if exp1["assembly"] != exp2["assembly"]:
+            shared = sorted(
+                set(exp1["assembly"].split(ASSEMBLY_SEPARATOR)) & set(exp2["assembly"].split(ASSEMBLY_SEPARATOR))
+            )
+            if not shared:
                 issues.append(
                     f"Different genome assemblies: {exp1['assembly']} vs {exp2['assembly']}. "
                     "Coordinate liftover needed before comparison."
                 )
             else:
-                compatible_aspects.append(f"Same assembly: {exp1['assembly']}")
+                compatible_aspects.append(f"Same assembly: {ASSEMBLY_SEPARATOR.join(shared)}")
 
         # Check assay type
         if exp1.get("assay_title") and exp2.get("assay_title"):
@@ -698,7 +729,8 @@ class ExperimentTracker:
             if pub.get("title"):
                 entry += f"  title = {{{pub['title']}}},\n"
             if pub.get("authors"):
-                entry += f"  author = {{{pub['authors']}}},\n"
+                # stored as "A, B, C"; BibTeX separates names with " and "
+                entry += f"  author = {{{' and '.join(pub['authors'].split(', '))}}},\n"
             if pub.get("journal"):
                 entry += f"  journal = {{{pub['journal']}}},\n"
             if pub.get("year"):
@@ -755,8 +787,14 @@ class ExperimentTracker:
     # ------------------------------------------------------------------
 
     def get_metadata_table(self, accessions: list[str] | None = None) -> list[dict]:
-        """Get a metadata table of tracked experiments for analysis."""
+        """Get a metadata table of tracked experiments for analysis.
+
+        ``None`` selects every tracked experiment; a list selects those accessions, so an empty
+        list (a filter that matched nothing) selects nothing.
+        """
         conn = self._get_conn()
+        if accessions is not None and not accessions:
+            return []
         if accessions:
             placeholders = ",".join("?" for _ in accessions)
             rows = conn.execute(
@@ -891,7 +929,7 @@ class ExperimentTracker:
             organ=organ,
         )
 
-        table = self.get_metadata_table([e["accession"] for e in experiments] if experiments else None)
+        table = self.get_metadata_table([e["accession"] for e in experiments])
 
         # Enrich with external reference counts and PMIDs
         conn = self._get_conn()

encode_connector/server/main.py

@@ -273,6 +273,7 @@ async def encode_search_experiments(
     """
     client = await _get_client()
     limit = clamp_limit(limit)
+    offset = max(0, offset)
 
     filter_warnings = _validate_filters(assay_title, organ, biosample_type)
 
@@ -321,11 +322,13 @@ async def encode_search_experiments(
 async def encode_get_experiment(accession: str) -> str:
     """Get full details for a specific ENCODE experiment by accession ID.
 
-    Returns complete experiment metadata including all associated files,
-    quality metrics, controls, replicate information, and audit status.
+    Returns the experiment's metadata, all associated files, the accessions of its possible
+    controls, replicate counts, and the number of audit flags at each level (ERROR,
+    NOT_COMPLIANT, WARNING, INTERNAL_ACTION). It does not return QC metric values such as
+    FRiP or NSC; those are on the experiment's page at encodeproject.org.
 
     WHEN TO USE: Use when you have a specific accession and need full details
-    including files, quality metrics, and audit status.
+    including files, controls, and audit counts.
     RELATED TOOLS: encode_list_files, encode_track_experiment, encode_compare_experiments
 
     Args:
@@ -471,6 +474,7 @@ async def encode_search_files(
     """
     client = await _get_client()
     limit = clamp_limit(limit)
+    offset = max(0, offset)
     filter_warnings = _validate_filters(assay_title, organ, biosample_type)
     result = await client.search_files(
         file_format=file_format,
@@ -648,6 +652,7 @@ async def encode_batch_download(
     verify_md5: bool = True,
     limit: int = 100,
     dry_run: bool = True,
+    offset: int = 0,
 ) -> str:
     """Search for files and download them all in batch.
 
@@ -686,6 +691,8 @@ async def encode_batch_download(
         verify_md5: Verify downloads with MD5 checksums (default True)
         limit: Max files to download (default 100, safety limit)
         dry_run: If True (default), only preview what would be downloaded. Set False to download.
+        offset: Skip the first N matching files; pass the next_offset of the previous reply to
+            continue a search that has more files than limit
 
     Returns:
         JSON with download preview (dry_run=True) or download results (dry_run=False).
@@ -694,6 +701,7 @@ async def encode_batch_download(
     downloader = _get_downloader()
     validate_organize_by(organize_by)
     limit = clamp_limit(limit)
+    offset = max(0, offset)
     filter_warnings = _validate_filters(assay_title, organ, biosample_type)
 
     # Search for files
@@ -710,18 +718,34 @@ async def encode_batch_download(
         status="released",
         preferred_default=preferred_default,
         limit=limit,
+        offset=offset,
     )
 
     files = search_result["results"]
+    # the file search may stop before it has read every experiment; keep its note in every reply
+    total_note = search_result.get("total_note")
 
     if not files:
+        # with an offset, an empty page means "past the last match", not "nothing matches"
+        search_total = search_result.get("total", 0)
+        if search_total:
+            message = f"No files at offset {offset}: the search matches {search_total} file(s). Use a smaller offset."
+            suggestion = "Call again with offset=0 to start from the first matching file."
+        else:
+            message = "No files found matching the search criteria."
+            suggestion = (
+                "Try broadening your search filters. Use encode_get_facets to see what data is "
+                "available for your criteria."
+            )
         empty_result = {
-            "message": "No files found matching the search criteria.",
-            "total": 0,
+            "message": message,
+            "total": search_total,
             "has_more": False,
             "next_offset": None,
-            "suggestion": "Try broadening your search filters. Use encode_get_facets to see what data is available for your criteria.",
+            "suggestion": suggestion,
         }
+        if total_note:
+            empty_result["total_note"] = total_note
         if filter_warnings:
             empty_result["filter_warnings"] = filter_warnings
         return json.dumps(empty_result, indent=2)
@@ -734,8 +758,10 @@ async def encode_batch_download(
             f"Found {preview['file_count']} files ({preview['total_size_human']}). Set dry_run=False to download."
         )
         preview["search_total"] = search_total
-        preview["has_more"] = search_total > limit
-        preview["next_offset"] = limit if search_total > limit else None
+        preview["has_more"] = search_total > offset + limit
+        preview["next_offset"] = offset + limit if search_total > offset + limit else None
+        if total_note:
+            preview["total_note"] = total_note
         if filter_warnings:
             preview["filter_warnings"] = filter_warnings
         return json.dumps(_serialize(preview), indent=2)
@@ -754,9 +780,11 @@ async def encode_batch_download(
             "total_size": sum(r.file_size for r in results if r.success),
             "total_size_human": _human_size(sum(r.file_size for r in results if r.success)),
         },
-        "has_more": search_total > limit,
-        "next_offset": limit if search_total > limit else None,
+        "has_more": search_total > offset + limit,
+        "next_offset": offset + limit if search_total > offset + limit else None,
     }
+    if total_note:
+        output["total_note"] = total_note
     if filter_warnings:
         output["filter_warnings"] = filter_warnings
     return json.dumps(output, indent=2)
@@ -1124,7 +1152,7 @@ async def encode_list_tracked(
     )
 
     # Build metadata table
-    table = tracker.get_metadata_table([e["accession"] for e in experiments] if experiments else None)
+    table = tracker.get_metadata_table([e["accession"] for e in experiments])
 
     # Remove raw_metadata from output
     for row in table:

{encode_toolkit-0.3.2.dist-info → encode_toolkit-0.3.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: encode-toolkit
-Version: 0.3.2
+Version: 0.3.4
 Summary: MCP server for querying and downloading ENCODE Project genomics data directly from Claude
 Project-URL: Homepage, https://github.com/ammawla/encode-toolkit
 Project-URL: Repository, https://github.com/ammawla/encode-toolkit
@@ -37,7 +37,7 @@ Description-Content-Type: text/markdown
 
 [![License: AGPL-3.0](https://img.shields.io/badge/license-AGPL--3.0-green.svg)](LICENSE)
 [![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
-[![Version](https://img.shields.io/badge/version-0.3.2-green)](CHANGELOG.md)
+[![Version](https://img.shields.io/badge/version-0.3.4-green)](CHANGELOG.md)
 [![Status](https://img.shields.io/badge/status-beta-yellow)]()
 [![Skills](https://img.shields.io/badge/skills-47-orange)](docs/skill-vignettes/)
 [![Tools](https://img.shields.io/badge/MCP_tools-20-purple)](src/encode_connector/server/main.py)
@@ -331,7 +331,7 @@ Search ENCODE experiments with 20+ filters.
 
 | Parameter | Type | Description |
 |-----------|------|-------------|
-| `assay_title` | string | Assay type: "Histone ChIP-seq", "ATAC-seq", "RNA-seq", "Hi-C", etc. |
+| `assay_title` | string | Assay type: "Histone ChIP-seq", "ATAC-seq", "total RNA-seq", "Hi-C", etc. |
 | `organism` | string | Species (default: "Homo sapiens") |
 | `organ` | string | Organ: "pancreas", "brain", "liver", "heart", "kidney", etc. |
 | `biosample_type` | string | "tissue", "cell line", "primary cell", "organoid" |
@@ -496,7 +496,7 @@ Get grouped statistics of your tracked experiment collection.
 </details>
 
 <details>
-<summary><strong>Provenance and export tools (4)</strong></summary>
+<summary><strong>Provenance and export tools (5)</strong></summary>
 
 ### `encode_log_derived_file`
 
@@ -624,7 +624,7 @@ When installed as a Claude Code plugin, ENCODE Toolkit includes 47 literature-ba
 </details>
 
 <details>
-<summary><strong>Workflow skills (7)</strong></summary>
+<summary><strong>Workflow skills (10)</strong></summary>
 
 | Skill | Description |
 |-------|-------------|
@@ -681,7 +681,7 @@ Each pipeline includes a SKILL.md overview, 5-stage reference files (preprocessi
 | File | Description |
 |-------|-------------|
 | `skills/histone-aggregation/references/histone-marks-reference.md` | Comprehensive chromatin biology catalog (1,442 lines) — 21 histone marks with writers/erasers/readers, 5 novel acylation marks, ChromHMM state models (5 to 51 states), TF co-binding patterns, chromatin remodeling complexes, DNA methylation-chromatin interplay, nucleosome dynamics, 3D genome organization, chromatin in disease. 74 primary references |
-| `skills/*/references/literature.md` | 33 per-skill literature reference documents — ~250 papers cataloged with DOI, PMID, citation counts, and skill-relevant key findings |
+| `skills/*/references/literature.md` | 47 per-skill literature reference documents — about 240 papers cataloged with DOI, PMID, citation counts, and skill-relevant key findings |
 
 </details>
 
@@ -710,12 +710,12 @@ Most genomics tools give you one thing. ENCODE Toolkit gives you the full resear
 | Category | Assays |
 |----------|--------|
 | **Histone/Chromatin** | Histone ChIP-seq, TF ChIP-seq, ATAC-seq, DNase-seq, CUT&RUN, CUT&Tag, MNase-seq |
-| **Transcription** | RNA-seq, total RNA-seq, small RNA-seq, long read RNA-seq, CAGE, RAMPAGE, PRO-seq, GRO-seq |
+| **Transcription** | total RNA-seq, polyA plus RNA-seq, small RNA-seq, long read RNA-seq, CAGE, RAMPAGE, PRO-seq, GRO-seq |
 | **3D Genome** | Hi-C, intact Hi-C, Micro-C, ChIA-PET, HiChIP, PLAC-seq, 5C |
 | **DNA Methylation** | WGBS, RRBS, MeDIP-seq, MRE-seq |
 | **Functional** | STARR-seq, MPRA, CRISPR screen, eCLIP, iCLIP |
-| **Single Cell** | scRNA-seq, snATAC-seq, 10x multiome, SHARE-seq, Parse SPLiT-seq |
-| **Perturbation** | CRISPRi + RNA-seq, shRNA + RNA-seq, siRNA + RNA-seq |
+| **Single Cell** | scRNA-seq, snATAC-seq, snRNA-seq, long read scRNA-seq |
+| **Perturbation** | CRISPRi RNA-seq, shRNA RNA-seq, siRNA RNA-seq, CRISPR RNA-seq |
 
 **Supported file formats**: `fastq` `bam` `bed` `bigWig` `bigBed` `tsv` `csv` `hic` `tagAlign` `bedpe` `pairs` `fasta` `vcf` `tar`
 

encode_toolkit-0.3.4.dist-info/RECORD

@@ -0,0 +1,18 @@
+encode_connector/__init__.py,sha256=m2jzlw8g0WFGPmR0OLkpNcOo5ao8U4Bwzp9g2nQnFac,311
+encode_connector/__main__.py,sha256=hX7Hv1cKkwjnZrQkgsV-Kkx-60ywaNmobOuLuRfLZ-o,106
+encode_connector/client/__init__.py,sha256=wyIOQXMUZoUqGdv8_h5lW7vfWZ6Ohq_ttz2aLN7Mvo8,216
+encode_connector/client/auth.py,sha256=SnQZ3Hkq7BhpQD6vBZudAi6Lr2zCB47WXEWeFy_4xZg,9576
+encode_connector/client/constants.py,sha256=8l5kUaNPEoVC0bDbQW4IaTEQJfsAfit8IVqX-ZUHmUo,11259
+encode_connector/client/downloader.py,sha256=hDPLkGs8MO3Jr5gxJnPxhl211I5iZkoytZd7m7EeTFk,11877
+encode_connector/client/encode_client.py,sha256=yom0wAPQogRMF0euLN-ItczgRjDleLLMfF5zqqaROPM,23303
+encode_connector/client/models.py,sha256=lkt-2lr0dqBCPDBlSb7ozvSvvrlp-0JH7KtSpyjZil8,14830
+encode_connector/client/tracker.py,sha256=ts_B4fOuGtL4Xz1GrCph7XyPjfcyeUNGJRO_rFOyAIs,46777
+encode_connector/client/validation.py,sha256=vssV9tu9iTQes98jxCUvfSNsABtn_o8AzGKEJ2RqWf0,7814
+encode_connector/server/__init__.py,sha256=qE1SX7iMPz3bwjVuuvMlXNN1g_iHB-sIUQY-LtGgAPw,33
+encode_connector/server/__main__.py,sha256=gVilW3ql6i1R9fJ34xUi5RmGFDy2E_fyy9j0wcQ3tUg,124
+encode_connector/server/main.py,sha256=dWFNjaX-eNbKeV4BwcbycA-0fkftypmkRtUWHl2G72I,59200
+encode_toolkit-0.3.4.dist-info/METADATA,sha256=c7VqORxOgAQTex5aSHzeBmrFAtm7lyFZgSX1yDkmN-c,34459
+encode_toolkit-0.3.4.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
+encode_toolkit-0.3.4.dist-info/entry_points.txt,sha256=ZNqGYIpnig7ZLZKSP1xZTRZ1FdTSRLt8BcY9cqmCOW8,69
+encode_toolkit-0.3.4.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
+encode_toolkit-0.3.4.dist-info/RECORD,,

{encode_toolkit-0.3.2.dist-info → encode_toolkit-0.3.4.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.32.3
+Generator: hatchling 1.32.4
 Root-Is-Purelib: true
 Tag: py3-none-any

encode_toolkit-0.3.2.dist-info/RECORD

@@ -1,18 +0,0 @@
-encode_connector/__init__.py,sha256=A1xhCKU_XGnBkePtv1NmXWFX-A0WTcm62YQfMgaYwE8,124
-encode_connector/__main__.py,sha256=hX7Hv1cKkwjnZrQkgsV-Kkx-60ywaNmobOuLuRfLZ-o,106
-encode_connector/client/__init__.py,sha256=wyIOQXMUZoUqGdv8_h5lW7vfWZ6Ohq_ttz2aLN7Mvo8,216
-encode_connector/client/auth.py,sha256=SnQZ3Hkq7BhpQD6vBZudAi6Lr2zCB47WXEWeFy_4xZg,9576
-encode_connector/client/constants.py,sha256=x3XWhgHICZv_osWAyQrvR8GiYA8byZ3a9F0qscZ8GKc,9709
-encode_connector/client/downloader.py,sha256=hDPLkGs8MO3Jr5gxJnPxhl211I5iZkoytZd7m7EeTFk,11877
-encode_connector/client/encode_client.py,sha256=PiSGepIWoaxryX1YhcYfLTuKhJxrm4fgACmZNglAUs8,21314
-encode_connector/client/models.py,sha256=hNukcSisnM2Dw9xms-trt72Ymj1H1_yhi2iAxn3jfn0,13804
-encode_connector/client/tracker.py,sha256=8x6JNlla6UIpzgVDj8HOGnssfjQPRp-WdpmiirjLDI8,44804
-encode_connector/client/validation.py,sha256=vssV9tu9iTQes98jxCUvfSNsABtn_o8AzGKEJ2RqWf0,7814
-encode_connector/server/__init__.py,sha256=qE1SX7iMPz3bwjVuuvMlXNN1g_iHB-sIUQY-LtGgAPw,33
-encode_connector/server/__main__.py,sha256=gVilW3ql6i1R9fJ34xUi5RmGFDy2E_fyy9j0wcQ3tUg,124
-encode_connector/server/main.py,sha256=2oYZKnDM_XxW-z_NOXxlGdGOmauw5NuQdu7d3-aAbow,57826
-encode_toolkit-0.3.2.dist-info/METADATA,sha256=rZIBBJ6Yazo_ogyJb6tNCO9raY15xjMCrUgHfFIPdiY,34436
-encode_toolkit-0.3.2.dist-info/WHEEL,sha256=THafob7ofN-NsuMN7Mg4qZyHaQI7KkD-QlcQatYhXPo,87
-encode_toolkit-0.3.2.dist-info/entry_points.txt,sha256=ZNqGYIpnig7ZLZKSP1xZTRZ1FdTSRLt8BcY9cqmCOW8,69
-encode_toolkit-0.3.2.dist-info/licenses/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
-encode_toolkit-0.3.2.dist-info/RECORD,,