Build a Dual-Species Metagenomic Contamination Classifier

Examine mixed-read FASTA sequence repositories to detect microbial contamination in mammalian cell-line catalogs. Compute sequence complexity indices and generate quarantine manifests for cell-line biocurators.

Genomics Core Facility Scientist

Load multi-sample FASTA sequence files from cell-line research gene package downloads.

Compute GC ratio distributions and pentamer frequencies using Biopython parsing modules.

Compare sequence composition against known mammalian and mycoplasma reference distributions.

Export a validated sequence purity index and alert biocurators to suspected microbial contamination.

Web console showing read distribution plots, GC-content shift metrics, and sample disposition actions.

Download public gene data packages with NCBI Datasets (--taxon rodent) and introduce synthetic microbial control fragments. Starter examples below are synthetic. They are not downloaded records.

Biopython Employ Biopython SeqIO readers and nucleotide counting functions to compute base composition metrics.

mlflow, biopython, numpy. mlflow logs assay quality parameters, GC-drift distributions, and contamination threshold runs over time. Local script execution with optional hosted LLM for generating biocurator narrative summaries.

Submit runnable source, pinned dependencies, setup commands, a working interface, example outputs, and a recorded end-to-end demo. Include tests and an action log.

Calculates sequence GC percentages across all ingested FASTA reads via Biopython.

Detects bimodal GC distributions indicative of dual-species foreign contamination.

Logs assay quality parameters and metric artifacts into an MLflow experiment run.

Emits human-actionable quarantine notifications for samples exceeding 15% contamination.

```json [ { "input": { "run_id": "RUN-CELL-881", "host_species": "Mus musculus", "expected_gc_mean": 0.42, "reads": [ { "id": "R1", "seq": "GCGCGCGCGCGCGCGCGCGCGCGCGC" }, { "id": "R2", "seq": "ATATATATATATATATATATATATAT" }, { "id": "R3", "seq": "ATCGATCGATCGATCGATCGATCGAT" } ] }, "expected_output": { "run_id": "RUN-CELL-881", "samples_analyzed": 3, "contamination_detected": true, "anomalous_read_ids": [ "R1" ], "recommendation": "flag_for_microbial_assay" } }, { "input": { "run_id": "RUN-CELL-882", "host_species": "Homo sapiens", "expected_gc_mean": 0.45, "reads": [ { "id": "R4", "seq": "ATCGATCGATCGATCGATCGATCGAT" } ] }, "expected_output": { "run_id": "RUN-CELL-882", "samples_analyzed": 1, "contamination_detected": false, "anomalous_read_ids": [], "recommendation": "pass" } } ] ```

Analytical quality assurance for cell line research; synthetic data only; no medical or in vitro diagnostic claims. Use mock external writes. Require human review before any real deployment.