orange-assay — plate-image & dose-response widgets for Orange Data Mining
English | 中文
Three Orange Data Mining widgets that turn assay plate photos into tables and fit dose-response curves — without writing code. The image core reuses the coffee-ring-analyzer algorithm, so results match its Streamlit / mobile / CLI versions. Sibling package to orange-spectra.
| Widget | What it does |
|---|---|
| Microplate Reader | Read a microtitre-plate photo (6–384 wells) into a per-well table: mean intensity, or thresholded count / intensity, with well labels (A1…H12). |
| Coffee-Ring Reader | Quantify a spotted-assay (coffee-ring) plate: per-cell area/intensity over a grid, blank-column (col 0) normalization and replicate averaging → a concentration / ratio table. |
| Dose-Response Fit | Fit a 3- or 4-parameter logistic curve to any concentration + signal table and report EC50, LOD and R², with the fitted curve overlaid on the points. |
The outputs are ordinary Orange Tables, so they plug straight into Data
Table, scatter plots, PCA, or the classification widgets — e.g. the
Dose-Response Fit widget accepts either reader's output, or any colorimetric
assay you already have in a spreadsheet.
Pipeline
Microplate Reader ─wells──┐
├──► Dose-Response Fit ──► EC50 / LOD / curve
Coffee-Ring Reader ─cells─┘ (also: PCA · PLS-DA · Data Table)
Install
Works on Windows, macOS (Apple Silicon & Intel), and Linux — pure Python (numpy / scipy / matplotlib / Pillow / Orange3).
A. Desktop App (from orangedatamining.com):
Options ▸ Add-ons… ▸ Add more…, type orange-assay, tick it, OK,
restart.
B. pip Orange:
pip install orange-assay
python -m Orange.canvas
After restarting Orange, an Assay category with the three widgets appears in the toolbox. Each widget has an ℹ How to use box, and F1 opens its online help page. Full tutorial: https://tai-shengyeh.github.io/spectraview/assay.html (English).
Traditional-Chinese Windows note: if the Add-ons dialog crashes with
UnicodeDecodeError: 'cp950' codec…, install from a command prompt instead:"…\Programs\Orange\python.exe" -m pip install orange-assay, then restart Orange (or set thePYTHONUTF8=1environment variable).
Quick start
- Microplate Reader → choose a plate photo → pick the format (e.g. 96) → Wells output → Data Table.
- Or Coffee-Ring Reader → choose a spotted-plate photo → set rows × columns (column 0 = blank) → enter the concentrations → Cells output.
- Feed either output to Dose-Response Fit → pick the concentration and signal columns → read EC50 / LOD / R² and the fitted curve.
Tests
python tests/test_core.py # pure logic
QT_QPA_PLATFORM=offscreen python tests/test_widgets.py # widget smoke tests
License
MIT.
中文說明
orange-assay — Orange Data Mining 盤面影像與劑量反應 widgets
English | 中文
三個 Orange Data Mining widgets,把檢測盤照片 變成資料表並擬合劑量反應曲線——全程拖拉、免寫程式。影像核心重用 coffee-ring-analyzer 的演算法,結果與其 Streamlit/手機/CLI 版本一致。與 orange-spectra 為姊妹套件。
| Widget | 功能 |
|---|---|
| Microplate Reader | 讀微孔盤照片(6–384 孔)成每孔一列的表:平均亮度,或閾值面積/強度,附孔位標籤(A1…H12)。 |
| Coffee-Ring Reader | 量化點樣(咖啡環)盤:格點逐格取面積/強度、除以同列 blank(第 0 欄)、平均重複列 → 濃度/比值 表。 |
| Dose-Response Fit | 對任何 濃度+訊號 表擬合 3 或 4 參數邏輯曲線,回報 EC50、LOD、R²,並把擬合曲線疊在資料點上。 |
輸出都是一般的 Orange Table,可直接接 Data Table、散佈圖、PCA 或分類 widget;
Dose-Response Fit 接受兩個 reader 的輸出,也吃你已在試算表裡的比色法數據。
工作流程
Microplate Reader ─wells──┐
├──► Dose-Response Fit ──► EC50 / LOD / 曲線
Coffee-Ring Reader ─cells─┘ (也可接 PCA · PLS-DA · Data Table)
安裝
可在 Windows、macOS(Apple 晶片與 Intel)、Linux 執行——純 Python (numpy / scipy / matplotlib / Pillow / Orange3)。
A. 桌面版 App:Options ▸ Add-ons… ▸ Add more… 輸入 orange-assay →
打勾 → OK → 重啟。
B. pip 版 Orange:
pip install orange-assay
python -m Orange.canvas
重啟後工具箱會出現 Assay 分類(3 個 widgets)。每個 widget 都有 「ℹ 說明」盒子,按 F1 會開線上說明頁。教學網頁:https://tai-shengyeh.github.io/spectraview/assay.html(English)。
繁體中文 Windows 注意: 若 Add-ons 對話框出現
UnicodeDecodeError: 'cp950' codec…崩潰,改用命令列安裝:"…\Programs\Orange\python.exe" -m pip install orange-assay,再重開 Orange (或設環境變數PYTHONUTF8=1)。
快速上手
- Microplate Reader → 選盤面照片 → 選規格(如 96)→ Wells 輸出 → Data Table。
- 或 Coffee-Ring Reader → 選點樣盤照片 → 設列×欄(第 0 欄=blank)→ 填濃度 → Cells 輸出。
- 任一輸出接 Dose-Response Fit → 選濃度與訊號欄 → 讀 EC50/LOD/R² 與曲線。
測試
python tests/test_core.py # 純邏輯
QT_QPA_PLATFORM=offscreen python tests/test_widgets.py # widget 煙霧測試
授權
MIT。
Metadata
Release files for orange-assay 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| orange_assay-0.1.1.tar.gz | 20.6 kB | With provenance | Details for orange_assay-0.1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| orange_assay-0.1.1-py3-none-any.whl | Python 3 | none | any | Details for orange_assay-0.1.1-py3-none-any.whl |
Total release size: 43.1 kB
Release files / orange_assay-0.1.1.tar.gz
| Download URL | orange_assay-0.1.1.tar.gz |
|---|---|
| Size | 20.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
94fdc806f96790d1e3a8f1734c08b46ba19d7d62369836e14ded15e4c8dd89f2
|
|
BLAKE2b-256 checksum How to use checksums |
837ad7b1cd44fca0126e6740c5f7337fc2fc951b069257a3d13937a18d8a3b73
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 5, 2026.
Transparency logRelease files / orange_assay-0.1.1-py3-none-any.whl
| Download URL | orange_assay-0.1.1-py3-none-any.whl |
|---|---|
| Size | 22.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
7f69e03c11ff3c33c904ec4e945c0a991ffc7a4512e63d27f9dfdfcb885f7b2f
|
|
BLAKE2b-256 checksum How to use checksums |
6dc96067c2b1bdd8ab9cc2d6759aadf9207051c254bac2473e14bceb4341ff89
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 5, 2026.
Transparency logSecurity for orange-assay 0.1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for orange_assay-0.1.1.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 5, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.