Infinite Dimensions Captured In One Equation

Increasing evidence points to the fact that the transcriptome captures the entirety of a disease state at a multi-cellular level, not just of the tumor, but of the surrounding microenvironment as well.

This provides a radically multi-dimensional blueprint for a specific disease, collapsing and capturing infinite biological interactions that would never be understood sequentially or on a pathway-basis — both at the multi-cellular state of the tumor and the microenvironment.

It's an answer key in code, waiting to be perfectly cracked.

What’s a Rich Text element?

The rich text element allows you to create and format headings, paragraphs, blockquotes, images, and video all in one place instead of having to add and format them individually. Just double-click and easily create content.

Learn More

Static and dynamic content editing

A rich text element can be used with static or dynamic content. For static content, just drop it into any page and begin editing. For dynamic content, add a rich text field to any collection and then connect a rich text element to that field in the settings panel. Voila!

How to customize formatting for each rich text

Headings, paragraphs, blockquotes, figures, images, and figure captions can all be styled after a class is added to the rich text element using the "When inside of" nested selector system.

RNA is the Magic

For drug development, SHEPHERD Technology's ability to crack this code yields unparalleled opportunities for indication and patient selection, improved combination design, and more.

SHEPHERD’s database of transcriptomes comprises over 160 forms of cancer and almost 100,000 unique samples including histological and molecular subtypes and metastatic and naive samples.

A Mathematical Approach

SHEPHERD unleashes proprietary, computational mathematical algorithms and AI to understand the entire impact of any drug on the entire transcriptome — i.e. the multi-cellular state of the tumor and the surrounding microenvironment. This goes infinitely beyond a single target or pathway-based approach and captures everything a specific therapeutic does — on and off-target, known and unknown — to yield a complete picture of therapeutic effect. By applying proprietary, advanced algorithms to high-volume, raw, whole transcriptomic data, successfully treating cancer becomes a data and mathematics problem — the complex answer to which can only be found computationally.

SHEPHERD in Action

For each therapeutic, SHEPHERD identifies the RNA signature by using proprietary algorithms to analyze the drug’s therapeutic impact across at least 100 cancer models representing many cancer types and states. The diversity of this training data enables SHEPHERD to mathematically capture every biological interaction responsible for whether a therapeutic is effective or not and to what degree. The result is the full “Transcriptomic Impact Signature” for any drug.

Shepherd then applies that signature to predict with a remarkable degree of accuracy whether a specific drug will work for a specific patient or group of patients and to what degree. For drugs in development, SHEPHERD identifies patient populations predicted to achieve radical response rates. For an individual patient, the SHEPHERD platform identifies the specific therapeutics - single agent and combinations - predicted to achieve a radical response based on the patient’s most recent RNA sequencing of their tumor.

Making Drugs the Best They Can Be to Treat the Patients They Help the Most

Population Identification

SHEPHERD’s platform can identify patient populations from among over 160 cancer types defined by between 1 and over 400 RNA-markers. Clinical trial selection criteria can be identified, contingent upon development goals, to support a variety of designs and goals:

  1. Full sequencing-based trial
  2. Single marker-based trial
  3. Known cancer indication-based trial
  4. Population selection via pre-treatment
  5. Population selection via combination selection

Patient Stratification

SHEPHERD can identify and stratify patient populations predicted to display various degrees of response — from radical and strong responders all the way to those predicted most resistant.

Combo Identification

SHEPHERD is able to identify the specific drug combinations leveraging standards of care that will maximize the potential for synergy with therapies in development.

Immunotherapy Specific Markers

SHEPHERD can find advanced biomarkers for immunotherapies by leveraging bulk, deconvoluted, and/or single-cell transcriptomic data paired with endpoints. This approach offers the opportunity to progressively refine clinical trial inclusion criteria to maximize impact and therapeutic reach.

Toxicity Prediction

Healthy tissue also has unique transcriptomic characteristics - by applying the derived signature of the therapeutic to raw RNA representing healthy tissue, SHEPHERD is able to predict whether a therapeutic will have toxic side effects and on which organs.

Model Selection

By applying DELVE to sequenced models from a 5,000+ in vitro, ex vivo, and in vivo model repository, SHEPHERD can identify the preclinical models predicted to have the most significant response and most accurately represent the target patient population.