• Skip to primary navigation
  • Skip to main content
  • Skip to footer

info@sambasci.com | 833-GO-SAMBA

  • Facebook
  • Instagram
  • LinkedIn
  • Twitter
  • YouTube

Contact Us

Samba Scientific

Samba Scientific

Marketing and Media for Life Science Brands

  • Services
    • Content & Collateral
    • HubSpot Onboarding
    • Inbound Marketing
    • Lead Generation
    • Strategy
    • Videos
    • Webinars
    • Website Design
  • Case Studies
  • Careers
    • Samba Job Openings
    • Biotech Job Board
  • Blog
    • News
Let's Talk

What pictures of bears can teach us about cancer

October 16, 2019

In the quest to better understand cancer, we rely heavily on computation. Computers learn from data in a process called machine learning. Computer scientists use machine learning to automatically generate captions for images. This sounds simple, but it actually requires really sophisticated techniques. Scientists at the cutting edge of a new field called quantitative biology are using similar techniques to transform medical research.

Computers get calculus, but they’re confused by bears

You know those little “I’m not a robot” tests online, where you have to identify all the images with trucks in them? Those security walls work, because real humans are naturally good at identifying objects in photos. Computers are not.

Consider the picture below

One of many images from the Microsoft COCO 2015 image captioning challenge.

To you, this probably looks like a picture of bears.

Circa 2005, a computer might have correctly guessed that there is a bear in this picture a little more than half the time. Fast forward to 2012, computers could tell that there’s an animal in the picture, but they might have thought it was a wolf.

Enter machine learning

Traditionally, people have had to try to explain to computers how to caption images. But while we’re good at identifying bears intuitively, we’re not very good at describing the process to computers. We don’t break the image down into pixels and quantify the colors, we just see a bear and know it’s a bear. 

Machine learning sort of bypasses the human-to-computer communication step. In machine learning, the computer looks for patterns among images and captions and learns from them. That means, the more images we can give a computer to learn from, the better it will get at generating captions.

In 2015, researchers on the Google Brain Team used 10 million captioned images to train an image captioning model. According to their model, the image above contains “two brown bears sitting on top of rocks.” That’s pretty good.

Others have developed machine learning models so sophisticated, that they can tell the difference between images of animals that humans struggle to distinguish, like related breeds of dog.

From identifying bears to classifying cancer

The real strength of machine learning is that the computer isn’t told what to look for by humans. That means computers can find patterns we wouldn’t think to examine.

In 2011, Daphne Koller’s lab at the University of Stanford used machine learning to find unknown patterns in breast cancer tissue.

When cancerous tissue is biopsied, it’s sliced thin, stained, placed on a glass slide, and imaged. Those images are analyzed by an experienced pathologist. The pathologist looks for patterns that are consistent with images they’ve encountered before to suggest a treatment and predict how quickly the disease is likely to progress.

Koller’s team set out to see if computers could make the same predictions. They used machine learning to create an “automated pathologist,” that was able to differentiate biopsies from patients with a more or less severe prognosis.

Remarkably, the model’s predictions were not based off of known prognostic indicators. It was patterns in the cells adjacent to the tumor cells that tipped the model off. This turned out to be among the earliest evidence suggesting that the microenvironment in which a tumor finds itself is important in shaping how the cancer will progress.

From images to sequencing data

Tumor biopsies are an important diagnostic tool, but they’re not the only one. As costs continue to decrease, there is mounting interest in using sequencing to diagnose cancer and rare diseases. In much the same way that computers can learn to identify what patterns link images with their captions, they could also learn to link genotypes with phenotypes.

In the last ten years genome wide association studies have identified thousands of mutations that correlate with particular diseases. But not all of those variants are important.  “There is signal in the genetics, it’s just that we don’t know how to read it,” said Koller in a recent talk at SynBioBeta. She argued that finding that signal is a job for machine learning.

If we continue at the current—faster than exponential—rate, we will have sequenced between one and two billion genomes by 2025. The amount of phenotypic data is also increasing. In a project called the UK Biobank, data was collected on 500,000 people over 30 years on everything from urinary biomarkers to lifestyle choices. The US is currently embarking on a similar project called “All of Us.” That’s a lot of training data for machine learning models.

Koller is confident that machine learning can help us solve all sorts of predictive problems in biology. For instance, we can create genetic diversity in a test tube, probe that diversity with potential drug candidates, and use machine learning to find patterns. Those patterns could help narrow down candidate drugs to stymie the exponentially escalating cost of drug discovery.

Koller predicts that the combination of machine learning and biology will define the next scientific epoch. But it isn’t without its challenges. Machine learning algorithms are really good at homing in on subtle signals, she said, which means they could get thrown off course by subtle artefacts. Good algorithms start with good data.

Samba gives a big thank you to Daphne Koller, Founder and CEO of Insitro, for giving an amazing talk at SynBioBeta and sharing a recording of another amazing talk at the MARS conference.

Related Posts

5 ways to repurpose your life science content
5 Ways to Repurpose Your Life Science Content
Life Sciences and Biotech Marketing and Sales Strategy
Meaningful Gated Content for Lead Conversion

4 companies redefining pharma with living medicines
4 companies redefining pharma with living medicines

Share this page on social

  • Tweet
  • LinkedIn
  • Share

Category iconScience - Tools & Technologies,  Uncategorized Tag iconArtificial Intelligence,  Image Captioning,  Machine Learning

Ready to get started?

See what Samba can do for you.

Get a Free Consultation

Footer

Samba Scientific

  • HubSpot Onboarding
  • Inbound Marketing
  • Lead Generation
  • Marketing Strategy
  • Technical Writing
  • Video Services
  • Webinar Services
  • Website Design
samba logo hubspot badge

Let’s chat

info@sambasci.com 833-GO-SAMBA

Get a Free Consulation

Recent Posts

  • Collaboration is Easy With MarkUp
  • Personalized Medicine: A Rewarding Career at the Cutting Edge of Healthcare

Follow us

  • Facebook
  • Instagram
  • LinkedIn
  • Twitter
  • YouTube

Get the latest tips, tricks and news

Copyright © 2023 Samba Scientific. All rights reserved.

 Privacy Policy

Return to top
Digital Marketing

Job Type: Full Time – Remote

Reports to: Team Lead – Sr. Digital Marketing Manager

Key Responsibilities include:

  • Follows company’s values, vision, and mission.
  • Reports weekly employee measurables/ KPI 
  • Follows and complete tasks assigned in Asana or other project management tools.
  • Attends to companywide meetings on a weekly basis.
  • Manage the setup, measurement, and optimization for HubSpot and Marketo.
  • Develop Marketing strategies for clients and Samba.
  • Perform monthly site audits on all clients (including Google Analytics, HubSpot and site performance) 
  • Optimize marketing automation and lead nurturing processes through email, content, and social channels. 
  • Explore new ways to engage and new social networks to reach our target buyers. 
  • Manage and build various email lists and campaigns, including the design templates, calls-to-action, and content used in email sends. Segment lists based on behaviors like past email engagement and website interactions (content downloads, site page visits, etc.). 
  • Research and test partnerships with new vendors to expand our reach and/or lower cost-per-acquisition. 
  • Stay up to date with digital marketing trends and potential new channels 
  • Manage both on-site and off-site SEO for the company and clients. 
  • Manage of organic search engine performance and goal setting based on site impressions, clickthrough rates, traffic, and conversions. 
  • Manage key conversion points in the marketing funnel, including landing pages, website calls-to-action (CTAs), and lead-generating forms. 
  • Monitors and reports to teammates on the performance of various marketing channels and campaigns.  
  • Create scalable, innovative approaches to extracting, managing, and analyzing data from customers. 
  • Utilize, optimize, and report on many components of the Google Suite: Google Analytics, Search Console, Tag Manager, Data Studio, Page Speed Insight.
Web Developer

Type: Full Time, Remote

Report to: Sr. Developer

Key Responsibilities:

  • Follows company’s values, vision, and mission.
  • Reports weekly employee measurables/ KPI 
  • Follows and complete tasks assigned in Asana or other project management tools.
  • Attends to companywide meetings on a weekly basis.
  • Maintains constant communication with the team daily
  • Implement client websites/template offerings from approved design, site architecture, and user interface to finished deliverable
  • Code and implement WordPress sites from XD layout
  • Update re-usable code libraries to streamline WordPress development cycle
  • Support, extend and/or enhance existing code
  • Document technical and functional specifications
  • Write clean, well-documented code
  • Ensure that ‘go-live’ deadlines are met for all sites
  • Maintain and optimize existing sites
  • Facilitate site documentation and maintenance
  • Provide technical consultancy services to internal team
  • Testing and debugging issues
  • Managing project timelines and tasks
  • Updating technical documents
  • Other duties as required
Technical Writer

Job Type: Full Time – Remote

Reports to: Operations Manager

Key Responsibilities include:

  • Follows company’s values, vision, and mission.
  • Reports weekly employee measurables/ KPI 
  • Follows and complete tasks assigned in Asana or other project management tools.
  • Attends to companywide meetings on a weekly basis.
  • Determinate the clearest and most logical way to present information for greatest reader comprehension.
  • Generate innovative ideas for content and workflow solutions
  • Meet with subject matter experts to ensure specialized topics are appropriately addressed
  • Analyze information required for the development or update of policy, procedure, and form documentation.
  • Review and/ or copy Edith content developed by other members of the team
  • Research, write, edit and revise content that is both engaging and accessible to user personas with both non-technical and technical backgrounds
  • Maintain tracking in Asana to ensure deadlines are met and client deliverables and received on time.
  • Collaborate with the internal operations team like Web Developer, graphic designer and Digital Marketing Manager.
Graphic Designer

Job type: Full Time – remote

Reports to: Sr. Graphic Designer

Key Responsibilities include:

  • Follows company’s values, vision, and mission.
  • Reports weekly employee measurables/ KPI 
  • Follows and complete tasks assigned in Asana or other project management tools.
  • Attends to companywide meetings on a weekly basis
  • Collaborate, brainstorm, and strategize with multiple teams or clients for a wide range of materials that may include web pages, presentations, programming collateral, signage, internal communication, newsletters, and marketing materials
  • Translate strategic direction into high-quality design within an established brand identity
  • Develop concepts by hand or with software, and execute original content determining ideal usage of color, text, font style, imagery, and layout
  • Manage the design and uploading process of all project material, understanding best practices for using a content management system
  • Use trend intelligence and an understanding of the current and historical business and market to design and execute specific classifications
Project Manager

Job Type: Full Time

Reports to: Sr. Project Manager / Account Manager

Key Responsibilities include:

  • Follows company’s values, vision, and mission.
  • Reports weekly employee measurables/ KPI 
  • Follows and complete tasks assigned in Asana or other project management tools.
  • Attends to companywide meetings on a weekly basis.
  • Creating long – term and short=term plans, including setting targets for milestones and adhering to deadlines
  • Delegating task and creating task in Asana to Designer, Digital marketing, and Web developers
  • Making Effective decision when presented with multiple options for how to progress with the project
  • Serving as a point of contact for team when multiple units are assigned to the same project to ensure team actions remain in synergy
  • Communicating with Account Managers to keep the project aligned with their goals
  • Adjusting schedules and targets on the project as needs or hours work in Harvest for the project change.
  • Other tasks as assigned
Account Manager

Job Type: Full Time – Remote

Report To: Director of Client Management

Key Responsibilities include:

  • Follows company’s values, vision, and mission.
  • Reports weekly employee measurables/ KPI 
  • Follows and complete tasks assigned in Asana or other project management tools.
  • Attends to companywide meetings on a weekly basis.
  • Communicating with clients clearly and addressing their concerns and resolving any conflicts that arise.
  • Raising Client’s business concerns and needs to the company’s management
  • Negotiating and closing on project schedules and date lines with existing and new clients
  • Delivering sales pitch to prospective clients
  • Preparing and presenting business and account updates management and clients
  • Following up clients to ensure they are satisfied with the company’s services
  • Monitoring the budget of the clients on hours worked, explaining cost or expenditures, and discussing new terms if necessary
  • Contributing to information to sales strategies by assessing current product results, monitoring competitive services, assessing needs to be filled and analyzing costumer reactions