At the core of our company is Scailyte’s best-in-class analytical platform ScaiVision™. It unravels hidden secrets of complex single-cell multiomics data to extract composite biomarkers associated with different cell populations. Using a convolutional neural network, ScaiVision automatically learns molecular patterns associated with relevant clinical outcomes. These signatures can then be applied to classify new samples.
Disease diagnosis
Identify novel biomarkers for an early disease diagnosis
Patient stratification
Identify patients with higher chance to respond to treatment
Mode of
Action
Understand the effect on patient’s immune response
Patient monitoring
Identify prognostic and predictive biomarkers
Patient stratification
We are looking for a predictive biosignature in our Phase I trial to inform patient selection for our Phase II clinical trial and we have single-cell data.
Which patients respond to our treatment?
Single-cell data provides unprecedented resolution to disease biology. Our AI-driven analytical approach is unbiased, cluster-free, annotation-free and very sensitive in extracting the maximum information from a single-cell dataset.
Our AI platform ScaiVision requires baseline samples from minimum 10 responder and 10 non-responder patients to be trained, learn and extract the cellular and molecular profile of responders to your therapy.
Our approach allows for the discovery of novel cell types, complex signatures from different cell types and data modalities. We translate these signatures to clinically-relevant technologies that can be measured in the clinic to select the patient population for your later-stage clinical programs most probable to respond to your therapy.
Recommended data: CITE-seq, TCR-seq, secretome
Patient stratification
We are looking for a predictive biosignature in our Phase I trial to inform patient selection for our Phase II clinical trial and we have single-cell data.
Which patients experience toxicity?
Single-cell data provides unprecedented resolution to disease biology. Our AI-driven analytical approach is unbiased, cluster-free, annotation-free and very sensitive in extracting the maximum information from a single-cell dataset.
Our AI platform ScaiVision requires baseline samples from minimum 20 patients who experience toxicities to be trained, learn and extract the cellular and molecular profile of responders to your therapy.
Our approach allows for the discovery of novel cell types, complex signatures from different cell types and data modalities. We translate these signatures to clinically-relevant technologies that can be measured in the clinic to select the patient population for your later-stage clinical programs most probable to respond to your therapy.
Recommended data: CITE-seq, TCR-seq, secretome
Patient stratification
We are looking for an integrative approach to analyse our data and find a combined predictive biosignature from our phase I clinical trial to inform patient selection for our phase II clinical trial, and have generated multiple data modalities including single-cell-resolution data.
Which patients respond to our treatment?
Single-cell data provides unprecedented resolution to disease biology. Our AI-driven analytical approach is unbiased, cluster-free, annotation-free and very sensitive in extracting the maximum information from a single-cell dataset.
Our AI platform ScaiVision requires baseline samples from minimum 10 responder and 10 non-responder patients to be trained, learn and extract the cellular and molecular profile of responders to your therapy.
Our approach allows for the discovery of novel cell types, complex signatures from different cell types and data modalities. We translate these signatures to clinically-relevant technologies that can be measured in the clinic to select the patient population for your later-stage clinical programs most probable to respond to your therapy.
Recommended data: CITE-seq, TCR-seq, FC, secretome, microbiome, WES, WGS, TMB, IHC
Patient stratification
We are looking for an integrative approach to analyse our data and find a combined predictive biosignature from our phase I clinical trial to inform patient selection for our phase II clinical trial, and have generated multiple data modalities including single-cell-resolution data.
Which patients experience toxicity?
Single-cell data provides unprecedented resolution to disease biology. Our AI-driven analytical approach is unbiased, cluster-free, annotation-free and very sensitive in extracting the maximum information from a single-cell dataset.
Our AI platform ScaiVision requires baseline samples from minimum 20 patients who experience toxicities to be trained, learn and extract the cellular and molecular profile of responders to your therapy.
Our approach allows for the discovery of novel cell types, complex signatures from different cell types and data modalities. We translate these signatures to clinically-relevant technologies that can be measured in the clinic to select the patient population for your later-stage clinical programs most probable to respond to your therapy.
Recommended data: CITE-seq, TCR-seq, FC, secretome, microbiome, WES, WGS, TMB, IHC
Mode of Action
We need to understand the cellular and molecular components involved and affected by our drug candidate.
Single-cell data provides unprecedented resolution to disease biology. Our AI-driven analytical approach is unbiased, cluster-free, annotation-free and very sensitive in extracting the maximum information from a single-cell dataset.
Our AI platform ScaiVision requires single-cell data from a minimum of 10 pre- and 10 post-treatment samples to be trained, learn and extract complex dependencies and signatures and to discover known and unknown targets, cellular features and molecular pathways affected by your treatment.
Recommended data: scRNA-seq, CITE-seq
High-quality Cell Therapy product
We would like to improve our cell therapy manufacturing success and develop a simple predictive test.
Single-cell data provides unprecedented resolution to disease biology. Our AI-driven analytical approach is unbiased, cluster-free, annotation-free and very sensitive in extracting the maximum information from a single-cell dataset.
Our AI platform ScaiVision requires data from the input product from a minimum of 10 successful and 10 unsuccessful cell therapy products to be trained, learn and extract the cellular and molecular profile of input samples predictive of successfully manufactured protocols. Our approach allows for the discovery of complex signatures from different cell types. We translate these signatures to simpler assays that can be applied routinely in the lab such as qPCR or flow cytometry.
Recommended data: CITE-seq
