Create ML Pipeline

Data Selection

Configuration

Review & Run

Filter by Cohort:

Only include participants from the selected cohort

Cancel

Selection Summary

Please select at least one dataset to proceed.

Total Records:

0

Step 2: ML Configuration

Job NameGive this ML job a descriptive name

Python VersionSelect the Python environment for training

Target ColumnThe column you want to predict (label/outcome)

Feature ColumnsSelect columns to use as features (hold Ctrl/Cmd to select multiple)

AlgorithmChoose the machine learning algorithm to use

Feature Selection

Process of selecting a subset of relevant features for model construction.

Learn more →

Enable Hyperparameter Tuning
Automatically search for optimal hyperparameters using the methods below.

Data Treatment Options

Missing Values

Scaling Method

Outlier Handling

Feature Engineering

Polynomial Features

Interaction Terms

Log Transformation

Ratio Builder

Feature Selection

Selection Method

Number of Features

Validation Strategy

Strategy

Number of Splits

Cancel

Configuration Summary

Complete the form to see a summary

	Participant ID
	Study ID
	Battery Name
	Test Name
	Test Code
	Result Value
	Units
	Reference Range
	Result Flag
Specific Tests (Optional) Select to include specific tests as features
	Basophils
	CRP
	ESR
	Eosinophils
	Hematocrit
	Hematocrit(HCT)
	Hemoglobin
	Hemoglobin(HB)
	Lymphocytes
	MCH
	MCHC
	MCV
	Monocytes
	Neutrophils
	Platelet Count(PLT)
	Platelets
	RBC
	Red Blood Cell(RBC)
	WBC
	White Blood Cell(WBC)

	Participant ID
	Study ID
	Visit Date
	Sample Collection DateTime
	Food/Drink Time Since Last
	Had Food/Drink in Last 24hrs
	Caffeine Time Since Last
	Had Caffeine in Last 24hrs
	Tobacco Time Since Last
	Had Tobacco in Last 24hrs
	Alcohol Time Since Last
	Had Alcohol in Last 24hrs
	Blood Sample Collected
	Urine Sample Collected
	Stool Sample Collected
	Bristol Stool Scale Card 1
	Bristol Stool Scale Card 2

Protein Columns
	Participant ID
	Protein Name
	UniProt ID
	Abundance
	Fold Change
	P-Value
	Collection Date
	Study ID
Select Proteins Choose which proteins to include
	Adiponectin
	Albumin
	C-Reactive Protein
	Ferritin
	Hemoglobin A1c
	IGF-1
	Immunoglobulin G
	Insulin
	Interleukin-6
	Leptin
	Transferrin

Taxon Columns
	Participant ID
	Sample ID
	Sample Type
	Taxon Name
	Taxonomic Rank
	Relative Abundance (%)
	Sequencing Technology
	Instrument Model
	Collection Date
	Study ID
Select Taxonomic Biomarkers Choose which taxa to include (relative abundance)
	Actinobacteria
	Akkermansia
	Bacteroides
	Bacteroidetes
	Bifidobacterium
	Blautia
	Faecalibacterium
	Firmicutes
	Prevotella
	Proteobacteria
	Roseburia
	Ruminococcus
	Verrucomicrobia

Create ML Pipeline

Specific Tests (Optional)

Direct Columns

Questionnaire Columns

Metabolite Columns

Select Metabolites

Protein Columns

Select Proteins

Taxon Columns

Select Taxonomic Biomarkers

0

Step 2: ML Configuration

Hyperparameters

Data Treatment Options

Feature Engineering

Feature Selection

Validation Strategy

Direct Columns
	Participant ID
	Study ID
	Questionnaire Completed At
	Age
	Sex
	Living Alone
	General Health
	Takes Supplements
	Supplement Count
	Age (SDC)
	Sex (SDC)
	Living Alone Status
Questionnaire Columns 281 columns available
	CMMI_ADM_QX_COMPLETION
	CMMI_DIS_ACUTE_FAIL_EVER
	CMMI_DIS_ADDICTION_DISORDER_EVER
	CMMI_DIS_ALZHEIMER_EVER
	CMMI_DIS_ANGINA_EVER
	CMMI_DIS_ANKYLOSING_SPONDYLITIS_EVER
	CMMI_DIS_ANXIETY_DIS_EVER
	CMMI_DIS_ANXIETY_EVER
	CMMI_DIS_ARRHYTHMIA_EVER
	CMMI_DIS_ARTHRITIS_EVER
	CMMI_DIS_ARTHRITIS_OA_EVER
	CMMI_DIS_ARTHRITIS_OTHER_EVER
	CMMI_DIS_ARTHRITIS_RA_EVER
	CMMI_DIS_ARTHRITIS_TYPE_OTSP
	CMMI_DIS_ASTHMA_EVER
	CMMI_DIS_ATRIAL_EVER
	CMMI_DIS_BIPOLAR_DIS_EVER
	CMMI_DIS_BONES_EVER
	CMMI_DIS_CANCER_EVER
	CMMI_DIS_CARDIO_EVER
	CMMI_DIS_CB_EVER
	CMMI_DIS_CELIAC_EVER
	CMMI_DIS_CHD_EVER
	CMMI_DIS_CHRONIC_FAIL_EVER
	CMMI_DIS_CH_EVER
	CMMI_DIS_COPD_EVER

Metabolite Columns
	Participant ID
	Study ID
	Metabolite Name
	HMDB ID
	Concentration (µM)
	Concentration Unit
	Below LOD
	Date of Measurement
	Operator
	Run ID
	Experimental Method
	Experimental Conditions
	Storage Conditions
	Internal Sample ID
Select Metabolites Choose which metabolites to include
	1,3-Diaminopropane
	1,3-Dimethyluric Acid
	1-Methylguanosine
	1-Methylinosine
	1-Methylnicotinamide
	1-Methyluric acid
	1H-Indole-4-carboxaldehyde
	2,5-Furandicarboxylic acid
	2-Aminopimelic acid
	2-Hydroxy-2-methylbutyric acid
	2-Hydroxy-3-methylvaleric acid+2-hydroxy-4-methylpentanoic acid
	2-Hydroxybutyric acid
	2-Hydroxyisobutyric acid
	2-Hydroxyisovaleric acid
	2-Hydroxyphenylacetic acid
	2-Isopropylmalic acid
	2-Methylbutyrlglycine
	2-Methylglutaric acid
	2-Oxoadipic acid
	2-Oxoisocaproic acid
	2-Phenylpropionic acid
	2-hydroxyglutaric acid
	2-oxovaleric acid
	3,4-Dihydroxybutyric acid