from __future__ import annotations

import gradio as gr
import pandas as pd

RESOURCES = [
    {
        "Dataset": "Upper-limb Kinect movement",
        "What it contains": "3D coordinates for nine upper-body joints, task events, movement features, and benchmark tables",
        "People / samples": "18 adults with SMA type III + 19 controls",
        "Access": "Open download",
        "Available files": "Four PLOS supplements and four derived tables",
        "Repository": "https://huggingface.co/datasets/YannisTevissen/sma-upper-limb-kinect",
    },
    {
        "Dataset": "Spinal-stimulation figure data",
        "What it contains": "Gait, EMG, strength, stimulation settings, and response measurements",
        "People / samples": "3 adults with SMA type III",
        "Access": "Open download",
        "Available files": "CSV and spreadsheets for main and extended figures",
        "Repository": "https://huggingface.co/datasets/YannisTevissen/sma-spinal-stimulation-figure-data",
    },
    {
        "Dataset": "BforSMA reported biomarkers",
        "What it contains": "Reported protein, metabolite, and transcript results",
        "People / samples": "Study reports 108 children with SMA + 22 controls",
        "Access": "Open reported results",
        "Available files": "Five tables, two appendices, and one list",
        "Repository": "https://huggingface.co/datasets/YannisTevissen/sma-bforsma-reported-biomarkers",
    },
    {
        "Dataset": "GSE108094 motor-neuron RNA-seq",
        "What it contains": "Differential expression, alternative splicing, GEO metadata, and SRA run metadata",
        "People / samples": "8 libraries from 4 cell lines",
        "Access": "Open download",
        "Available files": "Two processed outputs, three family-metadata files, and one run inventory",
        "Repository": "https://huggingface.co/datasets/YannisTevissen/sma-gse108094-motor-neuron-rnaseq",
    },
    {
        "Dataset": "TREAT-NMD SMA registry",
        "What it contains": "Harmonized clinical-registry schema",
        "People / samples": "International registry network",
        "Access": "Application required",
        "Available files": "Public 120-item core schema; participant data by reviewed enquiry",
        "Repository": "https://www.treat-nmd.org/what-we-do/core-datasets/sma/",
    },
    {
        "Dataset": "Cure SMA Clinical Data Registry",
        "What it contains": "Natural history, treatments, and outcomes",
        "People / samples": "More than 1,000 reported participants",
        "Access": "Application required",
        "Available files": "Registry information; participant data through a governed process",
        "Repository": "https://www.curesma.org/impact-report/",
    },
    {
        "Dataset": "JEWELFISH digital measures",
        "What it contains": "Touchscreen, motion, respiratory, and upper-limb signals",
        "People / samples": "116 reported participants",
        "Access": "Sponsor controlled",
        "Available files": "Study description; participant-level sensor streams not public",
        "Repository": "https://www.sciencedirect.com/science/article/pii/S0960896623001797",
    },
]

FRAME = pd.DataFrame(RESOURCES)


def filter_resources(access: str, search: str):
    result = FRAME
    if access != "All":
        result = result[result["Access"] == access]
    if search.strip():
        needle = search.strip().lower()
        result = result[
            result.astype(str).apply(lambda row: row.str.lower().str.contains(needle).any(), axis=1)
        ]
    return result


with gr.Blocks(title="Open SMA Data Explorer") as demo:
    gr.Markdown(
        """
        # Open SMA Data Explorer 🧬

        A catalogue of SMA research datasets by modality, cohort, available files, and access level.
        These resources describe specific study populations and experimental settings.
        """
    )
    with gr.Tab("Find datasets"):
        with gr.Row():
            access = gr.Dropdown(
                choices=["All", "Open download", "Open reported results", "Application required", "Sponsor controlled"],
                value="All",
                label="Access",
            )
            search = gr.Textbox(label="Search", placeholder="Try motion, RNA, gait, biomarker…")
        table = gr.Dataframe(
            value=FRAME,
            headers=list(FRAME.columns),
            datatype=["str"] * len(FRAME.columns),
            interactive=False,
            wrap=True,
        )
        access.change(filter_resources, [access, search], table)
        search.change(filter_resources, [access, search], table)

    with gr.Tab("Kinect benchmark"):
        gr.Markdown(
            """
            ## Reach-intent classification

            The Kinect records a stick figure while one button appears and the person reaches for it.

            **Input:** the first 25%, 50%, or 100% of that movement.  
            **Question:** which of the ten buttons are they reaching toward?  
            **Answer:** a number from 0 to 9.

            We test three versions:

            1. **Generic** — learn from other people, then meet a completely new person.
            2. **Personalized** — see one or five examples from the new person first.
            3. **Across visits** — learn from their first visit and test months later.

            The provided evaluation reports overall accuracy, macro target recall, and SMA/control slices at each
            movement checkpoint. Participant folds prevent recordings from the same person appearing in both
            training and test data.
            """
        )
        gr.Markdown(
            "[Open the benchmark dataset](https://huggingface.co/datasets/YannisTevissen/sma-upper-limb-kinect)"
        )

    with gr.Tab("Responsible use"):
        gr.Markdown(
            """
            - These cohorts are small and incomplete representations of SMA.
            - Controlled-access participant data are not included in the catalogue repository.
            - Results should not be used for diagnosis, prognosis, or treatment decisions.
            - Dataset cards record source citations, terms, file sizes, and checksums.
            """
        )


if __name__ == "__main__":
    demo.launch()