BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//aichemy - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://aichemy.ac.uk
X-WR-CALDESC:Events for aichemy
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20240101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=UTC:20251101T080000
DTEND;TZID=UTC:20260109T120000
DTSTAMP:20260412T185838
CREATED:20251104T103507Z
LAST-MODIFIED:20260209T165255Z
UID:5847-1761984000-1767960000@aichemy.ac.uk
SUMMARY:Catechol Benchmark Hackathon (NeurIPS 2025 DnB)
DESCRIPTION:ML model-building challenge for reaction yield prediction for catechol rearrangement reaction from transient flow dataset.\n\n\n\n\n\n\n\n\n\n\n\nKEY DETAILS\n\n\n\n\nLAUNCH DATE3rd November 8:00 AM CLOSING DATE9th January 12:00 PM \n\n\n\nVIEW COMPETITION ON kaggle\n\n\n\n\n\n\n\n\nOverview:\n\n\n\nWelcome to the Catechol Benchmark Hackathon competition!  \n\n\n\nIn this competition\, we will have multiple teams trying to prediction reaction outcomes of the rearrangement of allyl substituted catechol under different solvent and process conditions. \n\n\n\nThe data-set consists of multiple transient flow ramps\, which allow us to assess the amount of starting material and products after seeing the reaction at different temperatures and residence times (i.e. how long the chemicals reacted for). We also include many data-points for binary mixtures of solvents\, allowing us to treat the usually discrete solvent selection problem as a semi-continuous one. \n\n\n\nGoal: Build a machine learning model that achieves the best predictions on the collected data\, as measured by a cross-validation procedure\, which will demonstrate the ability of your model to predict on unseen solvent data.  \n\n\n\nDescription\n\n\n\nMore details of the data-set: \n\n\n\nData size and inputs\n\n\n\nThe data-set consists of 1227 data points on the allyl substituted catechol reaction\, covering 24 solvents at different temperatures and residence times. The inputs of the model will consist of: \n\n\n\n(1) A selection of two different solvents\, Solvent A and Solvent B\, with the corresponding amount of Solvent B in the mixture given by the percentage %B. \n\n\n\n(2) The temperature in °C at which the reaction was carried out. \n\n\n\n(3) The residence time of the reaction\, i.e.\, how long the reactants were subject to the reaction conditions applied. \n\n\n\nThe outputs consist of the yield of the starting material and the two observed products. We also created a smaller data set of 656 data-points in which solvent mixtures are not considered\, and only single solvent data\, along with residence times and temperatures is considered. \n\n\n\nEvaluation\n\n\n\nSubmissions will be evaluated according to a cross-validation procedure. This public notebook (https://www.kaggle.com/code/josepablofolch/catechol-benchmark-hackathon-template) shows the structure any submitted notebook must follow. In order to ensure fair participation among all competitors\, the submission must have the same last three cells as in the notebook template\, with the only allowed change being the line where the model is defined.  \n\n\n\nFor the avoidance of doubt\, the line  model = MLPModel() can be replaced with a new model definition in the third to last and second to last cells\, but everything else must remain the same. \n\n\n\nPrizes\n\n\n\nPrizes will be awarded on a per-person basis as follows: \n\n\n\nTotal Prizes Available: £2\,000 (GBP) \n\n\n\n\n1st Place – £250 per person (maximum £1000 total for a team of four)\n\n\n\n2nd Place – £150 per person (maximum £600 total for a team of four)\n\n\n\n3rd Place – £100 per person (maximum £400 total for a team of four)
URL:https://aichemy.ac.uk/event/catechol-benchmark-hackathon-neurips-2025-dnb/
CATEGORIES:Hackathon
ATTACH;FMTTYPE=image/png:https://aichemy.ac.uk/wp-content/uploads/2025/11/4.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20251119T140000
DTEND;TZID=UTC:20251119T150000
DTSTAMP:20260412T185838
CREATED:20250829T151653Z
LAST-MODIFIED:20260325T144038Z
UID:4970-1763560800-1763564400@aichemy.ac.uk
SUMMARY:AIchemy’s Monthly Webinar Series - November 2025
DESCRIPTION:KEY DETAILS\n\n\n\n\nDATE19 November 2025 TIME14:00 – 15:00 COSTFree \n\n\n\n\nRECORDINGSClick the YouTube links below to watch each session. \n\n\n\n\nBridging Molecular Design and Synthesis: AI and Automation for Reaction Optimisation Screening first\, AI on top \n\n\n\n\n\n\n\n\nWe are delighted to welcome you to our AIchemy Hub’s monthly webinar series. \n\n\n\nThis month’s talks: \n\n\n\nDr. Lauren Ye Seol Lee – UCL \n\n\n\nTalk Title: Bridging Molecular Design and Synthesis: AI and Automation for Reaction Optimisation \n\n\n\nAchieving efficient and sustainable chemical synthesis requires bridging molecular-level understanding with data-driven process optimisation. This seminar presents an integrated framework that connects molecular representation\, reaction modelling\, and autonomous experimentation\, illustrated through applications in pharmaceutical manufacturing. \n\n\n\nWe first enhance reaction yield prediction by embedding physically meaningful molecular descriptors and reaction context\, enabling models to capture both intra- and intermolecular interactions. We then extend this framework to model solvation effects on reaction kinetics\, where explicitly incorporating transition-state structures provides mechanistic insight into solvent-mediated reactivity. In parallel\, we model single-component solubility with explicit temperature dependence\, by establishing a foundation for future mixture and formulation predictions relevant to pharmaceutical processes. Finally\, we highlight ongoing work on automated amide synthesis using robotic platforms\, aiming to close the loop between computation\, experimentation\, and sustainable process development. \n\n\n\n\n\n\n\nDr. Omer Omar – CEO\, Apoello \n\n\n\nTalk Title: Screening first\, AI on top. \n\n\n\nHigh-throughput virtual screening is a method gaining quick traction in the world of materials discovery\, particularly for organic electronics. It finds its origins in drug discovery where simple cheminformatics can reign supreme; however\, to build vast datasets of optoelectronic properties required the advent of advanced hardware and (quantum chemical) code. The method is a simple funnel — look at exhaustive sets and filter down to the most promising candidates based on more and more stringent criteria. This is often done with de novo material libraries for given scaffolds for a given property. We go further by asking: what if we screened the whole synthetically-available chemical space? This way\, you can screen for multiple properties across the breadth of chemistry that exists today and determine the limit of exciting discoveries. This talk will go into the discoveries made through screening both with theory only and combined theoretical-experimental approaches. We will also consider: once we have the data\, how can ML & AI be used for i) improving the discovery engine\, and ii) bringing digestible insights to researchers who want to instantly discover new materials? \n\n\n\nFollowing the presentations\, there will be time for questions from the audience. \n\n\n\n\n\nSpeakers\n\n\n\n\n\nDr. Lauren Ye Seol LeeAssistant Professor – UCL\n\n\n\n\n\nOmer Omar CEO – Apoello\n\n\n\n\n\nTahereh Nematiaram Webinar Host
URL:https://aichemy.ac.uk/event/aichemys-monthly-webinar-series-november-2025/
CATEGORIES:Webinar
ATTACH;FMTTYPE=image/png:https://aichemy.ac.uk/wp-content/uploads/2025/11/Webinar-Nov-2025.png
END:VEVENT
END:VCALENDAR