Join us October 5-7, for a transformative Paperless Lab Academy® (PLA) conference in Orlando, Florida held in collaboration with 20/15 Visioneers. The event will focus on education and learning the skills necessary to achieve next-generation transformation in your labs. Subject Matter Experts who care about improving laboratory processes and the quality of work life will be present and involved. Already booked are experts from AstraZeneca and Takeda.

Today’s laboratories are evolving at an unprecedented pace. The following themes reflect the real-world needs and priorities that R&D organizations must address to thrive. By adopting in-silico-first approaches, researchers can accelerate discovery and boost lab efficiency by over 60%. Robust scientific informatics and effective data management are foundational to these advancements — they form the backbone of in-silico innovation and deeper insights. Building Smart and Smarter labs is the key to making this vision a reality.

Our hands-on labs equip scientists and IT professionals with the essential skills they need to navigate and succeed in today’s dynamic R&D environment.

Event Themes

In-Silico First Science : Using Artificial Intelligence and Machine Learning (AI/ML)to give a head start to your science

Scientific Informatics and Data Management : Your Data is an Asset that  must be organized and contextualized properly

Creating Smart or Smarter Labs:  Advanced automation and robotics will drive model quality data and reproducible science

Hands-On Labs

4 training sessions are programmed by Day 1

1. Building a BPM (Business Process Map) for Your Lab
2. Getting Started with Cheminformatics
3. Prompt Engineering for Scientists
4. Building No-Code LLM Workflows for Your Lab

Registration links

TICKETS: Registration is limited. Secure your admission by registering here and get ready for a new experience that will help you and your organization discover and develop more!

HOTEL: We have negotiated a discounted rate at the beautiful Florida Hotel, centrally located in downtown Orlando. Our block guarantees the lowest room rate and applies for an extended stay if you want to come early or stay late. To book your accommodations click here.

SPONSOR: Put your solutions and services in front of key decision makers. We are offering a range of sponsorship opportunities to maximize your visibility before, during, and after the event. Find out more here.

“The best events are those where experts can share and learn.  This is the culture that PLA® Orlando strives for.  It is a life sciences community event, and importantly an opportunity for you to advance your personal skillset and the capabilities across your organization,” John F. Conway, Founder & Chief Visioneer Officer, 20/15 Visioneers.

The post R&D Success to Make Laboratories Efficient Again appeared first on .

The “Data-driven” here implies much more than just technology and data.  it requires a special mentality,  a leadership attitudes, that makes it possible to take informed decisions by systematically using data to improve business performance.

To lead the data-driven culture, corporations need to first establish a stream of clean, accurate, reliable, and active data feeds reflecting all major business activities. All these qualities are critical for employees to trust the data, the technology, and the tools – any limitation can prove to be the single point of failure in making the data-driven vision happen.

The success of machine learning (ML) and artificial intelligence (AI) applications requires large quantities of training and test data. This need creates critical challenges not only concerning the availability of such data, but also regarding its quality.  ML and AI are highly dependent on the quality of data used to train models. Incomplete, erroneous, Poor data quality can lead to can lead to inaccurate predictions, unreliable model performance and ultimately poor decisions.

This why this session will be focused on the Data quality which is of critical importance especially in the era of Artificial Intelligence and automated decisions. Share real success stories on how the use of data allowed smart decisions with real financial gains for the company

There are many aspects to data quality, including consistency, integrity, accuracy, and completeness. According to Wikipedia, data is generally considered high quality if it is “fit for its intended uses in operations, decision making and planning, and data is deemed of high quality if it correctly represents the real-world construct to which it refers.”

Debabrata Sanyal, Senior General Manager – Corporate Quality Assurance and Digital Automation – MSN Laboratories Private Limited

Debabrata Sanyal is Senior General Manager in Corporate Quality Assurance and Digital Automation in MSN Laboratories Private Limited. He brings 22 years of experience in diversified field of Quality Management predominantly in Quality Assurance, Quality Compliance and Regulatory Affairs. Debabrata previously worked for Regulatory Affairs and Quality System in renowned organisations like Cadila Pharmaceuticals, Torrent research Center, Aurobindo Research Center and MSN Laboratories Private Limited. In his recent assignment at MSN Laboratories Private Limited, Debabrata works for transforming the long-term digitalisation and automation targets into process and solutions.

Use Cases of drug discovery automation and ML models

Samiron Phukan, Senior director Computational (AI/ML) Modelling & Digital Transformation integrated Drug Discovery and Development at Aragen LifeSciences

Samiron Phukan has nearly 20 years of experience in the field of informatics driven solution in drug discovery and development. He had worked in various pharmaceutical companies and CROs in India in the field of drug discovery and development from concept to clinic in various therapeutic areas like oncology, metabolic disorders and anti-infectives using computational modelling and informatics. He had set up the state-of-the-art informatics laboratories in various pharmaceutical companies like Jubilant Biosys, Dr. Reddys’s Laboratories, Lupin ltd. Presently he is heading the CADD/informatics division in Aragen Lifesciences Hyderabad. In addition to his current role of heading the scientific team of computer aided drug design scientist, he is involved digitization, automation and development of various proprietary platform technology using ML tools to aid drug discovery and development.

How communication and data standards enable the automation and data management lifecycle

Burkhard Schaefer, AnIML Task Group Lead, SiLA Consortium

Communication and data standards form the bedrock of efficient laboratory processes. This presentation explores the role of SiLA (Standardization in Lab Automation) and AnIML (Analytical Information Markup Language) in driving automation, data management, and machine learning. SiLA ensures seamless instrument control and workflow orchestration, while AnIML structures data for consistent analysis and collaboration. Learn how the synergy between these standards fuels closed-loop experimentation, enabling optimized parameter adjustments using real-time insights. Through real-world cases, this presentation discusses the impact of standards in shaping modern laboratory practices, fostering innovation, and accelerating research.

Followed by Panel Discussion: How to set standards for the Lab 4.0

DISCOVER FULL PROGRAM HERE

The post Data Quality Empowers AI, ML and automation appeared first on .

The relevance of search results is essential for finding information. Indeed, a user will almost never look further than the first few results of a search engine.
It is therefore necessary that the relevant information is ranked as high as possible so that the information sought by the user is found in the first results.

Search Results: Importance of Ranking

The order, or “ranking” of search results is essential for search engines, which will therefore use more or less complex algorithms to display the results that users will find most relevant first.

It is usually not possible to find the algorithms used by popular search engines.  Indeed this is considered as a major competitive advantage, on which the popularity of a search engine depends. These search engines index more or less documents but the capacity to order properly the results will be decisive from user perspective.

As search engines do not (or only partially) disclose their ranking criteria, some people try to find these criteria in order to improve their own ranking in Google-type search. Thus, it is possible to find some widely used criteria and algorithms, as described below.

Search Results: State of the art in ranking strategy

TF-IDF : Term Frequency-Inverse Document Frequency

In the case of a search including several terms (for example “acid deoxyribonucleic”), the question is what shall be used for the number of occurrences. Are we looking for the number of times the words “acid” and “deoxyribonucleic” are found side by side and in this order? The total number of times one of these two words is found in the text?

To solve this problem, most search engines use the concept of TF-IDF . A term is considered to be more or less important not only according to its number of occurrences, but also according to its specificity. For example, the term “acid” will be found in many documents about chemistry or biology, the frequency of documents with this term is surely high. The TF-IDF score will then be rather low. On the other hand the term “deoxyribonucleic” will only be found in documents mentioning DNA, the frequency of documents with this term is potentially low so TF-IDF will be high. To assign a score to documents containing these two terms, the number of occurrences of the term “deoxyribonucleic” will therefore be more taken into account than that of the term “acid” as its TF-IDF (= specificity) score is expected to be much higher.

Machine Learning is also there with the “learning to rank”

ML techniques applied to the relevance of the search are grouped under the term “Learning to rank “. Most WWW search engines use this type of technique to sort their results.

Learning to rank methods are based on learning a model with the aim to discover  the best order in which display search results. The score found by the algorithms is not absolute, it only helps to sort results between each others.

The variables used by the different algorithms vary between search engines, but remain very close to the ranking criteria that can be used for classical ranking: TF-IDF, age or popularity of the result, term found in the title,… (see last chapter ‘other usual criteria’ below)

There are several types of algorithms for learning to rank, more or less fast or efficient. But the major problem is to obtain a training data set.

Indeed, as with any machine learning algorithm, it is necessary to use a data set to train a model. In the case of learning to rank, this dataset must include a set of queries, query results, and manual assessment of the query results. This is specially hard  in our life science and/or enterprise context, there are much fewer users in the system than WWW search engines!

Search Results: Two Assessment Types

There are two types of assessment that can be made on the results of a query, which are explicit or implicit assessments:

• Explicit: experts will give a score to each search result (early adopters, test team, …) The explicit assessment are precise but very expensive to build.
• Implicit: users’ behavior will be used to deduct judgments. We can for example take into account the number of clicks on a result, or on the contrary the fact that the user did not click on the first three results, the fact of rephrasing a request, the time spent on a page visited … Implicit assessment are much easier to obtain, but contains noise that require clean up.

Search Results: Content Augmentation

The idea of ​​“content augmentation” is to add pseudo-content to each document, which is a set of terms not present in the document but linked to its concepts.

For example, in an article which  contains the word “cardiac”, there is a high probability that it also contains the words “heart”, “arrest” and “circulatory”, but a low probability that it contains the words “Clown” or “pajamas”.

By analyzing the co-occurrence of the words in a set of documents, we can deduce correlations, and for each document we can generate a set of words which “could” be in the document but are not.

In practice, search engines do not just count the co-occurrences of words, but use more sophisticated methods such as the algorithms “Latent semantic analysis”, “Latent Dirichlet allocation” or more recently “Word2vec”.

Use of ontologies in content augmentation

In our specific domain, biological ontologies (like Disease ontology, cheBI, pathway ontology) offer link between concepts. For example Alzheimer disease is known as a Central Nervous System disease. An idea is to use the term directly linked (SubClassOf), a synonym (hasExactSynonym), or an external reference (hasDbXref) to augment the content of a document. At DEXSTR, this is something that we specifically found as an improvement.

Search Results: Other common criteria

Some criteria are only applicable to web pages (loading time, availability, HTML tags …), but others are more generic and may interest us.

Here are some examples:

• The terms do not include spelling errors
• If the query contains several terms, the terms that are close in the documents found will have a better score: (“viral disease” > “viral […] disease” ).
• Documents will have a higher score if the terms are found in an important field. This is especially true for the file or path name in most contexts.
• Documents will have a higher score if the terms are found at the start of a field
• Newest data
• Number of clicks or downloads, …

Search Results: User Personalisation

Many search engines adapt the order of search results to the user who requests it: has the user already shown affinities for a type of content? Is it possible to identify other users similar to the one making the request?

Search history can also be used to influence search results.

Search Results: Take away message

There are many ranking strategies, some mentioned in this article, others can be found (via a nicely ranked web search!). If you need to improve the quality of your own search engine, the first thing you need to do is to set up performance / relevance indicators (implicit or explicit as described upper). That way, you can playfully follow the improvement of your search page and the happiness of your users !

DEXSTR is sponsoring the Paperless Lab Academy since 2018. They’ll run a workshop at the #PLA2020 about DEXSTR Inquiro: different ways to reveal Insights from your data

Erwan David, Chief technical Officer and founder at DEXSTR

Over 10 years of experience in scientific IT projects in big pharma. Erwan has conducted large projects around compound logistics and improving an Enterprise Data Warehouse to manage new data types (biologics, toxicological data).  Erwan focuses on transforming unstructured large dataset (mainly scientific files) into searchable assets . He founded together with David Peyruc, a translational science company DEXSTR 

Charlotte Raillière, Back-end lead developer at DEXSTR

The post How to provide relevant Search Results appeared first on .