Bio-IT World Community Names Five New ‘Best of Show’ Products

May 19, 2023

By Bio-IT World Staff

May 19, 2023 | Earlier this week during the Bio-IT World Conference & Expo, Bio-IT World named five 2023 Best of Show Awards winners including new products from Data Cicada, Genomenon, GitHub, Monomer Bio, and Starfish Storage.

The Best of Show Awards program at Bio-IT World each year recognizes innovative product solutions to important problems facing the Life Sciences industry. The awards program is open to any Bio-IT World exhibitor with a new product updated or released in the past year and available for viewing at the event.

One of the awards—the People’s Choice Award—is chosen by the Bio-IT World community as a whole. The other awards are chosen by a panel of expert judges who reviews the entries before the event, narrows the list to finalists, and names winners after viewing the products and interviewing the companies live at the event. They select new (or updated) products that they believe deliver superior innovation, return on investment, and value to the life sciences community.

People’s Choice Award

This year 33 products were submitted for consideration. Bio-IT World Conference & Expo attendees voted for their favorite among the group during the event. This year’s People’s Choice Award winner is GitHub for GitHub CoPilot.  

Judges’ Awards for Best of Show

After reading about the entries before the event, narrowing the list to 12 finalists, and viewing them in person this week, the Judges chose to give five awards. In 2023 they chose to honor new products from DataCicada, Genomenon, GitHub, Monomer Bio, and Starfish Storage.

The product descriptions for all of the finalists are included below. Congratulations to all of our new products, finalists, and our winners.

2023 Best of Show Winners

DataCicada’s Tympana

DataCicada is proud to announce the launch of Tympana, a powerful web-based platform that brings Machine Learning tools to the hands of the domain experts. Tympana assists scientists in building high quality Machine Learning models for their complex data, allowing them to scale their expertise and serving as a multiplier in efforts. Designed to be user friendly, Tympana requires no programming or coding skills on the part of the user. Tympana integrates active learning, explainable AI, and generative AI to create robust models and datasets that can be exported for scientific workflows. Tympana currently has proof-of-concept use cases, in Protein Sequences, Image Object Detection and Sensor Signal detection. These use cases serve to demonstrate the capabilities of the Tympana platform. The active learning strategies utilized by Tympana have demonstrated a reduction in data volume requirements in initial experiments that will save scientists time in achieving comparable results. While it can be easy to instruct users at diverse education levels how to recognize a specific object within an image, it requires years of training to properly evaluate a sensor reading from a DNA sequencer, an X-ray, CT scan, or a particle accelerator. These domains require an inherent body of knowledge and experience that does not lend itself to annotation by the general public. Tympana enables scientists to comb through large volumes of data and teach the computer what features are important, putting scientists in the driver seat of their own analysis.

Genomenon’s Disease Prevalence (curated content)

For companies targeting rare diseases, this new curated dataset and report provides a more complete understanding of the genetic prevalence of autosomal recessive (AR) diseases. It combines Genomenon’s Mastermind Genomic Language Processing (GLP) technology and proprietary curation tools, and exhaustive knowledgebase of human genomic evidence, with our highly specialized genomic curation services to estimate the genetic prevalence of AR rare diseases. Following a rigorous approach, we:

  • Aggregate and classify all variants in the causative gene of interest. Our Mastermind Genomic Language Processing (GLP) identifies, extracts, and standardizes all published variants from the medical and scientific literature. Each variant is then interpreted according to gold-standard clinical guidelines by our genome scientists.  
  • Select variants to include in the genetic prevalence calculation. Pathogenic and Likely Pathogenic variants, as well as relevant Variants of Uncertain Significance (VUS) are included in the prevalence calculation based on understanding of the associated disease, published variant classifications, allele frequency, and data in clinical and functional studies.
  • Calculate the estimated genetic prevalence. Overall and population-specific allele frequencies of selected variants are downloaded from the Genome Aggregation Database (gnomAD). The Hardy-Weinburg equation is used to estimate the frequency of a disease-causing genotype. Multiple estimates are produced to present a spectrum based on the level of confidence that the included variants are truly disease-causing.
  • Deliver a comprehensive disease prevalence report. This report provides an executive summary of genetic prevalence estimates, a summary of the gene and disease of interest, any corresponding considerations for interpreting estimates, and a publication-ready description of methods.    

GitHub’s Copilot

GitHub Copilot is an AI-powered pair programmer that provides autocomplete-style suggestions to developers while they code. This tool offers two ways for developers to receive suggestions: by starting to write the code they want to use or by writing natural language comments that describe what they want the code to do. Using contextual information from the file being edited, as well as related files, Copilot offers suggestions within the IDE. This helps developers stay in flow and avoid cognitive overload caused by switching out of their development environment to search for answers. Copilot can even handle boilerplate code, freeing developers to focus on solving business problems. GitHub Copilot is based on OpenAI Codex and is trained on all the programming languages used in public repositories. It is available as an extension in Visual Studio Code, Visual Studio, Neovim, and the JetBrains suite of IDEs, making it accessible to both individual developers and businesses. GitHub Copilot works with any programming language, however developers that will benefit most are those who write code in the best-supported languages in open source: Python, JavaScript, TypeScript, Go, Ruby and Java.

Monomer Bio’s Cell Culture Platform

Monomer provides a modern software solution that powers fully-automated cell culture workcells. We combine a best-in-class experiment execution platform with a purpose-built cell culture data management platform that makes it easy to manage culture data, view images, track progress, and make decisions about how to proceed. The Execution layer features instrument drivers, a dynamic scheduler, experiment orchestration layer, and a domain-specific protocol language for translating cell culture protocols to automation steps. Monomer’s Execution layer turns readily available hardware into fully integrated workcells that can operate continuously with minimal intervention. The Data management layer automatically ingests microscope images, computes confluence and growth curves, and flags and surfaces process anomalies, helping scientists make decisions about how to proceed with experimentation. Monomer provides an AI-ready framework for managing and processing thousands of culture images. Customers can easily integrate ML image analysis pipelines to help streamline decisions like when to passage. With this innovation, Monomer customers report a dramatic reduction in manual work, including weekend shifts, along with an increase in experiment capacity and reproducibility. Customers can culture 100s of concurrent plates, 24/7, while capturing high quality, curated datasets.

Starfish Storage’s Starfish 6.5

Starfish: Empowering Users to Participate in Unstructured Data Management and Curation at Scale. Starfish is a software platform with a unique approach to unstructured data management, addressing both the technical and the human challenges associated with housekeeping and curation. The Technical: Starfish is the most flexible and powerful solution for managing unstructured data at scale. We conquer the world's most demanding file environments by combining DISCOVERY with EXECUTION. The DISCOVERY side of Starfish is a SQL-based data catalog that enumerates files and directories across any number of file systems (HPC, scale-out NAS, tape, etc.) and buckets. The catalog is enhanced with metadata in the forms of tags and key-value pairs. It is used for reporting, analytics, search, user portal, workflow, and policy enforcement. Most metadata operations are automated or delegated to end users. The execution side of Starfish is a scale-out batch processor and data-mover that acts on the result set of a query to the catalog. In other words, you make a DISCOVERY and you EXECUTE a job to do something about it. Jobs are parallelized across multiple servers in multiple geographies. For the humans: Starfish presents relevant sections of file system contents to designated users, so that they can visualize their collections and provide simple inputs to guide data deletion, archiving, and any other automations. Starfish provides users with essential tools that enable them to be the stewards of their own data. Starfish is Linux software with Linux and Windows agents. Version 6.5 added research data workflow management.

2023 Best of Show Finalists

Deloitte’s ConvergeHEALTH CognitiveSpark for Clinical

Deloitte’s ConvergeHEALTH Miner Evidence, Release 4.5’s Platform for Life Sciences

Genomenon’s Mastermind Discovery

Ontotext’s Target Discovery v1.1

TetraScience’s Tetra Scientific Data Cloud

The Hyve’s Fairspace