Laboratory Notebooks Research Articles

Application and Integration of Computer Vision Technologies for Automated Recognition and Recording of Chemical Experiments

Abstract Advancements in computer vision have significantly improved motion and object recognition accuracy. These advancements should aid the automatic recognition of chemical experiments, potentially contributing to the recording of experiments. Creating an electronic laboratory notebook from experiment filming enhances convenience and allows more detailed information storage compared to traditional manual recording methods. Our previous research focused on employing object detection and action recognition to automate the recognition of chemical experiments. This paper presents a novel system that combines object detection, action recognition, multiple object tracking, and barcode recognition to automatically generate experimental flowcharts. We implemented our system as a graphical user interface-based application for laboratory use that successfully constructs flowcharts from videos of chemical experiments, including simple chemical manipulations.

Large language models recover scientific collaboration networks from text

Science is a collaborative endeavor. Yet, unlike co-authorship, interactions within and across teams are seldom reported in a structured way, making them hard to study at scale. We show that Large Language Models (LLMs) can solve this problem, vastly improving the efficiency and quality of network data collection. Our approach iteratively applies filtering with few-shot learning, allowing us to identify and categorize different types of relationships from text. We compare this approach to manual annotation and fuzzy matching using a corpus of digital laboratory notebooks, examining inference quality at the level of edges (recovering a single link), labels (recovering the relationship context) and at the whole-network level (recovering local and global network properties). Large Language Models perform impressively well at each of these tasks, with edge recall rate ranging from 0.8 for the highly contextual case of recovering the task allocation structure of teams from their unstructured attribution page to 0.9 for the more explicit case of retrieving the collaboration with other teams from direct mentions, showing a 32% improvement over a fuzzy matching approach. Beyond science, the flexibility of LLMs means that our approach can be extended broadly through minor prompt revision.

Woodward-Hoffmann or Hoffmann-Woodward? Cycloadditions and the Transformation of Roald Hoffmann from a "Calculator" to an "Explainer".

On May 1, 1965, Roald Hoffmann and R. B. Woodward published their second joint communication, Selection Rules for Concerted Cycloaddition Reactions, in the Journal of the American Chemical Society. Herein is presented a historical analysis of Woodward and Hoffmann's determination of the mechanism of cycloadditions. This analysis is based on thorough analyses with Roald Hoffmann of his 1964 and 1965 laboratory notebooks and his archived documents and on numerous in-person, video, and email interviews. This historical research pinpoints several seminal moments in chemistry and in the professional career of Hoffmann. For example, now documented is the fact that Woodward and Hoffmann had no anticipation that their collaboration would continue after the publication of their first 1965 communication on electrocyclizations. Also pinpointed is the moment in Hoffmann's professional and intellectual trajectories that he became a full-fledged, equal collaborator with Woodward and Hoffmann's transition from a "calculator" to an "explainer."

Finding Relevant Retrosynthetic Disconnections for Stereocontrolled Reactions.

Machine learning-driven computer-aided synthesis planning (CASP) tools have become important tools for idea generation in the design of complex molecule synthesis but do not adequately address the stereochemical features of the target compounds. A novel approach to automated extraction of templates used in CASP that includes stereochemical information included in the US Patent and Trademark Office (USPTO) and an internal AstraZeneca database containing reactions from Reaxys, Pistachio, and AstraZeneca electronic lab notebooks is implemented in the freely available AiZynthFinder software. Three hundred sixty-seven templates covering reagent- and substrate-controlled as well as stereospecific reactions were extracted from the USPTO, while 20,724 templates were from the AstraZeneca database. The performance of these templates in multistep CASP is evaluated for 936 targets from the ChEMBL database and an in-house selection of 791 AZ designs. The potential and limitations are discussed for four case studies from ChEMBL and examples of FDA-approved drugs.

Large language models in electronic laboratory notebooks: Transforming materials science research workflows

In recent years, there has been a surge in research efforts dedicated to harnessing the capabilities of Large Language Models (LLMs) in various domains, particularly in material science. This paper delves into the transformative role of LLMs within Electronic Laboratory Notebooks (ELNs) for scientific research. ELNs represent a pivotal technological advancement, providing a digital platform for researchers to record and manage their experiments, data, and findings. This study explores the potential of LLMs to revolutionize fundamental aspects of science, including experimental methodologies, data analysis, and knowledge extraction within the ELN framework. We present a demonstrative showcase of LLM applications in ELN environments and, furthermore, we conduct a series of empirical evaluations to critically assess the practical impact of LLMs in enhancing research processes within the dynamic field of materials science. Our findings illustrate how LLMs can significantly elevate the quality and efficiency of research outcomes in ELNs, thereby advancing knowledge and innovation in materials science research and beyond.

Advancements in hand-drawn chemical structure recognition through an enhanced DECIMER architecture

Accurate recognition of hand-drawn chemical structures is crucial for digitising hand-written chemical information in traditional laboratory notebooks or facilitating stylus-based structure entry on tablets or smartphones. However, the inherent variability in hand-drawn structures poses challenges for existing Optical Chemical Structure Recognition (OCSR) software. To address this, we present an enhanced Deep lEarning for Chemical ImagE Recognition (DECIMER) architecture that leverages a combination of Convolutional Neural Networks (CNNs) and Transformers to improve the recognition of hand-drawn chemical structures. The model incorporates an EfficientNetV2 CNN encoder that extracts features from hand-drawn images, followed by a Transformer decoder that converts the extracted features into Simplified Molecular Input Line Entry System (SMILES) strings. Our models were trained using synthetic hand-drawn images generated by RanDepict, a tool for depicting chemical structures with different style elements. A benchmark was performed using a real-world dataset of hand-drawn chemical structures to evaluate the model's performance. The results indicate that our improved DECIMER architecture exhibits a significantly enhanced recognition accuracy compared to other approaches.Scientific contributionThe new DECIMER model presented here refines our previous research efforts and is currently the only open-source model tailored specifically for the recognition of hand-drawn chemical structures. The enhanced model performs better in handling variations in handwriting styles, line thicknesses, and background noise, making it suitable for real-world applications. The DECIMER hand-drawn structure recognition model and its source code have been made available as an open-source package under a permissive license.Graphical

Implementation of electronic lab notebooks (ELNs) in science laboratory classes: student response and lessons learned

As data and protocols are increasingly generated, accessed, and manipulated electronically, many labs are shifting to storing data in electronic laboratory notebooks (ELNs). ELNs provide clear advantages in readability, shareability, searchability, accessibility, and data security over their paper counterparts. Our interdisciplinary program implemented ELNs across several sections of our gateway molecular biology laboratory course and analyzed the impact on 384 students (13 sections total from Fall 2016 to Spring 2018) using surveys, focus groups, and grade data. We found that students prefer the electronic format, citing the ease of transitioning to lab reports and the longevity of their data. Course grades overall were not affected by the change. Based on our experience, we offer suggestions for smoothing the transition to an ELN system in undergraduate and graduate laboratory courses, including use during remote teaching.

Solvent flashcards: a visualisation tool for sustainable chemistry

Selecting greener solvents during experiment design is imperative for greener chemistry. While many solvent selection guides are currently used in the pharmaceutical industry, these are often paper-based guides which can make it difficult to identify and compare specific solvents. This work presents a stand-alone version of the solvent flashcards that were developed as part of the AI4Green electronic laboratory notebook. The functionality is an intuitive and interactive interface for the visualisation of data from CHEM21, a pharmaceutical solvent selection guide that categorises solvents according to “greenness”. This open-source software is written in Python, JavaScript, HTML and CSS and allows users to directly contrast and compare specific solvents by generating colour-coded flashcards. It can be installed locally using pip, or alternatively the source code is available on GitHub: https://github.com/AI4Green/solvent_flashcards. The documentation can also be found on GitHub or on the corresponding Python Package Index webpage: https://pypi.org/project/solvent-guide/.Scientific ContributionThis simple and easy-to-use digital tool provides a visualisation of solvent greenness data through a novel intuitive interface and encourages green chemistry. It offers numerous advantages over traditional solvent selection guides, allowing users to directly customise the solvent list and generate side-by-side comparisons of only the most important solvents. The release as a standalone package will maximise the benefit of this software.Graphical

Resistance Assessment as a Strategy to Increase the Adoption of Electronic Laboratory Notebooks

Electronic Lab Notebooks (ELNs) have seen a significant rise in research laboratories. However, realizing the benefits of ELNs requires the active participation of employees within an organization. This study aims to identify the factors contributing to resistance towards adopting an ELN, specifically eLabFTW. A semistructured questionnaire, validated by experts, was administered to record book requesters at the René Rachou Institute (FIOCRUZ MG). The findings revealed that individual decision-making factors include peer influence within the research group and familiarity with traditional physical logbooks. Assessing resistance can serve as a strategic tool to enhance system adoption.

Enhancing self-learning skills and quality through formative actions and feedback within chemistry classes in the laboratory – A useful model

In here a novel method is described to improve student success rates in a first-year basic chemistry theoretical/practical hybrid course (n = 31 students) by implementing simple ways of formative assessment. This to reduce student dropout rates following the philosophy of encouraging students’ self-control. Essential is to train first-year bachelor students in their self-learning skills and to enhance their evaluative judgment. As a result, students are able to provide better quality of the assessment products at the end of the course. In practice the course is redesigned and intervention tools are integrated at multiple levels throughout the course. The lecturers’ role was adapted to a coaching role, thereby introducing low-effort personalized micro-interventions to meet the personalized needs of students. To clarify these learning needs for students, awareness of the quality desired for the final assessment products is important. Awareness was improved by providing examples of varying quality and introducing multiple peer- and self-assessment moments during the course. The final evaluation of the course examination products showed that the quality of the laboratory notebook was substantially higher after following this approach. Additionally students learned other important skills such as self-learning skills, collaborating in practical work and giving and receiving feedback. Unexpectedly, the high perceived lecturers’ workload decreased. The work presented here provides a novel approach in the form of a model and a practical blueprint with tools for a practical chemistry course design which develops students’ self-learning skills thereby substantially improving student success rates. In our example course, the ultimate student success rate increased form 83 % to 95 % after using this novel approach.

Do Chemformers Dream of Organic Matter? Evaluating a Transformer Model for Multistep Retrosynthesis.

Synthesis planning of new pharmaceutical compounds is a well-known bottleneck in modern drug design. Template-free methods, such as transformers, have recently been proposed as an alternative to template-based methods for single-step retrosynthetic predictions. Here, we trained and evaluated a transformer model, called the Chemformer, for retrosynthesis predictions within drug discovery. The proprietary data set used for training comprised ∼18 M reactions from literature, patents, and electronic lab notebooks. Chemformer was evaluated for the purpose of both single-step and multistep retrosynthesis. We found that the single-step performance of Chemformer was especially good on reaction classes common in drug discovery, with most reaction classes showing a top-10 round-trip accuracy above 0.97. Moreover, Chemformer reached a higher round-trip accuracy compared to that of a template-based model. By analyzing multistep retrosynthesis experiments, we observed that Chemformer found synthetic routes, leading to commercial starting materials for 95% of the target compounds, an increase of more than 20% compared to the template-based model on a proprietary compound data set. In addition to this, we discovered that Chemformer suggested novel disconnections corresponding to reaction templates, which are not included in the template-based model. These findings were further supported by a publicly available ChEMBL compound data set. The conclusions drawn from this work allow for the design of a synthesis planning tool where template-based and template-free models work in harmony to optimize retrosynthetic recommendations.

A blueprint most wonderful, the homeobox discovery.

This is a personal, non-linear summary of the discovery of the homeobox, a short DNA sequence encoding a DNA-binding domain conserved in developmental control genes. It is based on our recollections, a few decaying lab notebooks and letters, the early research papers we published, and conversations with a few colleagues who were in Basel at the time. It presents a simple story, when the research we did was anything but, with failed experiments, blind alleys and dumb ideas. Homeobox DNA sequences were independently discovered by Matt Scott and Amy Weiner in Thomas Kaufmann's lab at Indiana University ( Scott and Weiner, 1984). The accompanying Perspective from Scott (2024), provides their fascinating story.

Use of OneNote class notebook as a combined electronic laboratory notebook and content delivery tool in an introductory biochemistry laboratory course.

The COVID-19 pandemic has forced a shift in thinking regarding the safe delivery of wet laboratory courses. While we were fortunate to have the capacity to continue delivering wet laboratory experiments with physical distancing and other measures in place, modifications to the mechanisms of delivery within courses were necessary to minimize risk to students and teaching staff. One such modification was introduced in BCH370H, an introductory biochemistry laboratory course, where a OneNote Class Notebook (ONCN) was used as an electronic laboratory notebook (ELN) in place of the traditional hardbound paper laboratory notebook (PLN) used prior to the pandemic. The initial reasoning for switching to an ELN was around safety-allowing course staff and students to maintain physical distancing whenever possible and eliminating the need for teaching assistants to handle student notebooks; however, the benefits of the ONCN proved to be significantly more. OneNote acted not only as a place for students to record notes but the Class Notebook's unique features allowed easy integration of other important aspects of the course, including delivery of laboratory manuals, posting of student results, notetaking feedback, sharing of instructional materials with teaching assistants, and more. Student and teacher experiences with the ONCN as used within a fully in person biochemistry laboratory course, as well as learned best practices, are reviewed.

NMRium: Teaching nuclear magnetic resonance spectra interpretation in an online platform.

NMRium is the first web-based software that allows displaying, processing, interpretation, and teaching of 1D and 2D NMR data in a user-friendly interface. It can import the most common data formats (e.g., JCAMP-DX, Bruker, Varian, and Jeol). While the scope for the use of NMRium encompasses a variety of applications such as being a component in data repositories or electronic lab notebooks (ELN), performing structure elucidation or preparing raw spectral data for publication, it also excels in enhancing teaching of NMR interpretation. In this paper, we present some current possibilities of this new tool. Several series of exercises are already provided on https://www.nmrium.org/teaching.

Web-BO: towards increased accessibility of Bayesian optimisation (BO) for chemistry.

Historically, the chemical discovery process has predominantly been a matter of trial-and-improvement, where small modifications are made to a chemical system, guided by chemical knowledge, with the aim of optimising towards a target property or combination of properties. While a trial-and-improvement approach is frequently successful, especially when assisted by the help of serendipity, the approach is incredibly time- and resource-intensive. Complicating this further, the available chemical space that could, in theory, be explored is remarkably vast. As we are faced with near infinite possibilities and limited resources, we require improved search methods to effectively move towards desired optima, e.g. chemical systems exhibiting a target property, or several desired properties. Bayesian optimisation (BO) has recently gained significant traction in chemistry, where within the BO framework, prior knowledge is used to inform and guide the search process to optimise towards desired chemical targets, e.g. optimal reaction conditions to maximise yield, or optimal catalyst exhibiting improved catalytic activity. While powerful, implementing BO algorithms in practice is largely limited to interfacing via various APIs - requiring advanced coding experience and bespoke scripts for each optimisation task. Further, it is challenging to seamlessly link these with electronic lab notebooks via a graphical user interface (GUI). Ultimately, this limits the accessibility of BO algorithms. Here, we present Web-BO, a GUI to support BO for chemical optimisation tasks. We demonstrate its performance using an open source dataset and associated emulator, and link the platform with an existing electronic lab notebook, datalab. By providing a GUI-based BO service, we hope to improve the accessibility of data-driven optimisation tools in chemistry; https://suprashare.rcs.ic.ac.uk/web-bo/.

Unlocking biomedical data sharing: A structured approach with digital twins and artificial intelligence (AI) for open health sciences.

Data sharing promotes the scientific progress. However, not all data can be shared freely due to privacy issues. This work is intended to foster FAIR sharing of sensitive data exemplary in the biomedical domain, via an integrated computational approach for utilizing and enriching individual datasets by scientists without coding experience. We present an in silico pipeline for openly sharing controlled materials by generating synthetic data. Additionally, it addresses the issue of inexperience to computational methods in a non-IT-affine domain by making use of a cyberinfrastructure that runs and enables sharing of computational notebooks without the need of local software installation. The use of a digital twin based on cancer datasets serves as exemplary use case for making biomedical data openly available. Quantitative and qualitative validation of model output as well as a study on user experience are conducted. The metadata approach describes generalizable descriptors for computational models, and outlines how to profit from existing data resources for validating computational models. The use of a virtual lab book cooperatively developed using a cloud-based data management and analysis system functions as showcase enabling easy interaction between users. Qualitative testing revealed a necessity for comprehensive guidelines furthering acceptance by various users. The introduced framework presents an integrated approach for data generation and interpolating incomplete data, promoting Open Science through reproducibility of results and methods. The system can be expanded from the biomedical to any other domain while future studies integrating an enhanced graphical user interface could increase interdisciplinary applicability.

Using <em>OpenBIS</em> as Virtual Research Environment: An ELN-LIMS Open-Source Database Tool as a Framework within the <em>CRC 1411 Design of Particulate Products</em>

The digital transformation and consequent use of new digital technologies not only have a substantial impact on society and companies, but also on science. Analog documentation as we have known it for centuries will eventually be replaced by intelligent and FAIR (Findable, Accessible, Interoperable, and Reusable) systems. In addition to the actual research data and results, metadata now plays an important role not only for individual, independently existing projects, but for future scientific use and interdisciplinary research groups and disciplines as well. The solution presented here, consisting of an electronic laboratory notebook and laboratory information management system (ELN-LIMS) based on the openBIS (open Biology Information System) environment, offers interesting features and advantages, especially for interdisciplinary work. The Collaborative Research Centre (CRC) 1411 ‘Design of Particulate Products’ of the German Research Foundation is characterized by the cooperation of different working groups of synthesis, characterization, and simulation, and therefore serves as a model environment to present the implementation of openBIS. OpenBIS, as an open source ELN-LIMS solution following FAIR principles, provides a common set of general entries with the possibility of sharing and linking (meta-)data to improve the scientific exchange between all users.

Engaging students in a genetics course-based undergraduate research experience utilizing Caenorhabditis elegans in hybrid learning to explore human disease gene variants.

Genetic analysis in model systems using bioinformatic approaches provides a rich context for a concrete and conceptual understanding of gene structure and function. With the intent to engage students in research and explore disease biology utilizing the nematode Caenorhabditis elegans model, we developed a semester-long course-based undergraduate research experience (CURE) in a hybrid (online/in-person) learning environment-the gene-editing and evolutionary nematode exploration CURE (GENE-CURE). Using a combination of bioinformatic and molecular genetic tools, students performed structure-function analysis of disease-associated variants of uncertain significance (VUS) in human orthologs. With the aid of a series of workshop-style research sessions, students worked in teams of two to six members to identify a conserved VUS locus across species and design and test a polymerase chain reaction-based assay for targeted editing of a gene in the nematode and downstream genotyping. Research session discussions, responsible conduct of research training, electronic laboratory notebook, project reports, quizzes, and group poster presentations at a research symposium were assessed for mastery of learning objectives and research progress. Self-reflections were collected from students to assess engagement, science identity, and science efficacy. Qualitative analysis of these reflections indicated several gains suggesting that all students found many aspects of the GENE-CURE rewarding (learning process of research, self-confidence in research and science identity, and personal interest) and challenging (iterative research and failure, time management, COVID-19 pandemic, and life issues).

Dear Diary

While a debug log is helpful, it's not the same thing as a laboratory notebook. If more computer scientists acted like scientists, we wouldn't have to fight over whether computing is an art or a science.

Results of a Three-Year Survey on the Implementation of Research Data Management and the Electronic Laboratory Notebook (ELN) Chemotion in an Advanced Inorganic Lab Course

Results of a Three-Year Survey on the Implementation of Research Data Management and the Electronic Laboratory Notebook (ELN) Chemotion in an Advanced Inorganic Lab Course