About BenevolentFrom Data to Medicine.Our team is harnessing the power of AI to accelerate the journey from data to medicine. It’s a journey that starts with formulating a hypothesis that predicts the underlying cause of a disease and follows that through many rounds of experimentation and testing until we validate that hypothesis. Then we begin the process of designing, synthesising and developing a new compound to treat that disease for a specific group of patients that are most likely to respond to that medicine. This is a radically different approach to traditional drug discovery and helps uncover new knowledge to discover and develop more effective medicines, faster than ever before.BenevolentAIBAI_e59cbdf6-7e9a-11ea-88d1-bfdf0983ea00Powerful Synergies.BenevolentAI integrates AI technologies at every step of the drug discovery process: from early discovery to late stage clinical development.Our platform of computational and experimental technologies and processes, draws on vast quantities of mined and inferred biomedical data and is built and used by our world-class scientists, researchers, and technologists, working side-by-side, to improve and accelerate every step of the drug discovery process.The Benevolent Management TeamOur passionate leadership team brings experience from businesses in technology, science and consulting, and guides cross-functional practice at BenevolentAI.Ken MulvanyExecutive ChairmanJoanna ShieldsCEOJackie HunterCE Clinical and Strategic PartnershipsMichael BrennanHead of Corporate DevelopmentAlix LacosteVP Data ScienceAnne PhelanChief Scientific OfficerBen MedlockChief Technology OfficerBruce CampbellScientific AdvisorCatherine TuckerVP Business DevelopmentDaniel NeilVP Artificial IntelligenceDavy SuveeSVP TechnologyDylan CurleySVP Product DevelopmentEve BerryVP Head of Finance OperationsGareth JonesVP Intellectual PropertyIvan GriffinCo-founder and SVP PartnershipsJB MichelScientific AdvisorJustin StebbingScientific AdvisorMark DaviesSVP Biomedical InformaticsNuala JohnsonVP Financial Planning Analysis & ReportingPeter CoxVP Drug DiscoveryTom HolgateGroup Finance DirectorTrecilla LoboSVP PeopleWill ScrimshawGeneral CounselTo drive transformational change through scalable technology solutions that result in a consistent pipeline of successful trials and new medicines for patients._e59cbf54-7e9a-11ea-88d1-bfdf0983ea00To unlock the power of AI to transform drug discovery and bring effective medicines to every patient._e59cc044-7e9a-11ea-88d1-bfdf0983ea00HumanityWe do it to benefit humanity.TransformationWe do it to transform the way medicines are discovered and developed.ImportanceAnd we do it because it matters.IntegrationOur strength comes from [our] integrated, end-to-end approach, combined with a relentless pursuit of scientific and technological excellence.ScienceTechnologyExcellenceCollaborationBenevolent disease sprints: cross-functional collaboration.At Benevolent we run disease sprints. We combine cross-functional teams of scientists and technologists to work from multiple angles to tackle complicated diseases. We deliberately break down the boundaries between technology and science, human and machine. This brings focus. It enables innovation, quick experimentation and continuous feedback loops. Building the right team means harnessing the right mix of broad biology, chemistry, informatics and drug discovery perspectives. It requires machine learning experts who can tackle the most demanding challenges, working constantly with scientists who develop and embrace new ideas.Our strength comes from this integrated approach where we focus our collective energy on a single disease with one common goal. We develop a deep understanding of that disease and tailor our machine learning models to reason specifically about the disease. Patient FocusPut patients first.* Everything we do is geared to getting the right medicine to the right patient, faster.* We each know the impact we create every day in helping to deliver value to patients.* We place patient insights and data at the heart of our work.BoundarylessnessBreak boundaries.* We deliberately cross traditional boundaries between technology and science, human and machine, to create unique approaches* We fearlessly invite difficult questions and diverse opinions* We relentlessly challenge assumptions and ask “why not?”OwnershipOwn the solution.* We never hold back from contributing our point of view and taking responsibility* We say what we’re doing and we do what we’re saying* We champion positivity and persistence, focusing on solutions, not problemsSuccessDrive to delivery.* We use data to drive decision-making and deliver with the right level of validation* We support each other in taking measured risks in order to innovate* We prioritise ruthlessly and fixate on the fastest path to successDrugsApply scientific data to make more effective drugs._e59cc134-7e9a-11ea-88d1-bfdf0983ea00What we do.Unlocking the power of scientific data to make more effective drugs for the people that need them.KnowledgeKeep up with and process the wealth of information that exists to garner real insight._e59cc224-7e9a-11ea-88d1-bfdf0983ea001The biomedical big data challenge.90% of the world's data was produced in the last two years. This rapid increase in data creation is felt most acutely in medical science. The sheer quantity of biomedical information available to scientists is increasing exponentially: from biomedical, genomic, patient, clinical trial and molecular data to consumer genetic data. Add to that the fact that the human body is one of the most complex data systems with over 37 trillion cells. This presents a task that is impossible for even the most learned scientists and research teams to keep up with, let alone process the wealth of information that exists to garner real insight. This is a massive human limitation, but it represents a perfect opportunity for machine learning.Curation & StandardisationCurate and standardise knowledge from structured and unstructured biomedical data sources._e59cc440-7e9a-11ea-88d1-bfdf0983ea001.1The perfect machine learning opportunity.BenevolentAI has spent the last five years developing a knowledge pipeline that pulls data from various structured and unstructured biomedical data sources and curates and standardises this knowledge via a data fabric.Extraction & ContextualisationExtract and contextualise the relevant information._e59cc5a8-7e9a-11ea-88d1-bfdf0983ea001.2This is fed into our proprietary knowledge graph which extracts and contextualises the relevant information. The knowledge graph is made up of a vast number of contextualised, machine curated relationships between diseases, genes, drugs and with over 20 types of biomedical entities.TargetsFocus on the most promising targets to progress into molecular design_e59cc6a2-7e9a-11ea-88d1-bfdf0983ea002Target identification.Human biology is one of the most complex information systems, and any variations of the underlying biological processes can cause symptoms and diseases to occur. Yet, the origin of a disease and the exact biological processes or pathways involved are often not clear.Genes & ProteinsDetermine which genes and proteins are associated with a disease and can be altered._e59cc788-7e9a-11ea-88d1-bfdf0983ea002.1ML ExpertsEngineering ExpertsBiology ExpertsBioinformatics ExpertsChemistry ExpertsDetermining which genes and proteins are associated with a disease and can be altered is the first step in being able to develop effective drug therapies. To do this, we bring together experts across ML, engineering, biology, bioinformatics, and chemistry together for each of our research programmes.ML & Data ScienceUse machine learning and data science._e59ccaee-7e9a-11ea-88d1-bfdf0983ea002.1.1Technology enabled target identification.We use machine learning and data science to guide the entire process of target identification. Relation inference AI models help us predict potential non-obvious disease targets that may be overlooked by scientists. Our differential expression based models help us identify proteins or genes that express differently in a disease and healthy cell.ViewsLook at the data in many different ways._e59ccbf2-7e9a-11ea-88d1-bfdf0983ea002.1.2The workflows we have developed look at the data in many different ways at the same time, allowing our scientists to establish solid hypotheses for possible drug targets.OrderingOrder targets based on criteria._e59cccf6-7e9a-11ea-88d1-bfdf0983ea002.1.3Data-driven triage process.Our AI triage process automatically orders targets based on criteria such as chemical opportunity, safety and druggability and then presents the ranked targets, together with rich metadata, to our scientists for an informed and nuanced evaluation. This allows them to focus on the most promising targets to progress into molecular design.Testing & FeedbackTest the targets feed the results back to the inference models._e59ccdfa-7e9a-11ea-88d1-bfdf0983ea002.1.4These targets are tested in the lab and the results are fed back to our inference models.DesignRecognise and design drug-molecules that ensure safety, potency, duration of impact and novelty._e59ccefe-7e9a-11ea-88d1-bfdf0983ea003Medicinal ChemistsMedicinal chemists train for decades to recognise and design drug-molecules that ensure safety, potency, duration of impact and novelty. This is a true art form and even the best chemists can only optimise a limited number of properties at any given time.Molecular Design.The chemical space for exploration is almost infinitely vast and only a small fraction of it can potentially be made into medicines.CompoundsAccelerate compound optimisation using AI._e59cd002-7e9a-11ea-88d1-bfdf0983ea003.1By leveraging advanced AI, our EvoChem product is continuously learning from this vast chemical space and generating drug-like molecules with desirable properties that can be synthesised 'on demand'. EvoChem designs de novo compounds based on multiparametric optimisations with a scoring function that factors in all the properties we are seeking to optimise for that molecule.Ranking & SelectionRank and select the best candidates for synthesis_e59cd110-7e9a-11ea-88d1-bfdf0983ea003.1.1The compound ideas are ranked and the best candidates are selected directly for synthesis, whilst others serve to inspire chemists to further explore the chemical space.Data & FeedbackCombine experimental data and expert feedback._e59cd21e-7e9a-11ea-88d1-bfdf0983ea003.1.2Iterative design cycles combining experimental data and expert feedback.Synthesis, Feedback & RefinementSynthesise the selected compounds and generate data to feed back in and refine the models._e59cd34a-7e9a-11ea-88d1-bfdf0983ea003.1.3We then take these selected compounds, synthesise them in our labs and generate real experimental data which is then fed back in, to refine the models. But what’s unique about our process is that it is assisted, from start to finish, by our AI algorithms and generative models. The result is a system that is self-correcting and requires fewer molecules to be synthesized, speeding up the process of selecting a final candidate from an industry average of 4.5 years to just 14 months.EndotypesDefine endotypes to improve target identification and clinical trial design._e59cd598-7e9a-11ea-88d1-bfdf0983ea004PatientsPrecision Medicine.Better defining endotypes to improve target identification and clinical trial design.Traditionally diseases have been defined by symptoms or location in the body, not by their underlying molecular mechanisms, pathways or the biological processes specific to a patient. The result is that 30-50% of top selling drugs don’t work in the patients they are prescribed for. PatientsApply machine learning models to identify patient groups._e59cd6c4-7e9a-11ea-88d1-bfdf0983ea004.1Patient GroupsThis precision medicine guided approach allows us to identify patient subtypes more likely to respond to drugs, further increasing the probability of success in the clinic. At BenevolentAI we apply machine learning models to identify patient groups by the molecular signature of their disease and design, allowing us to run faster clinical trials.Existing MedicinesApply this approach to existing medicines as well._e59cd7dc-7e9a-11ea-88d1-bfdf0983ea004.2This approach has benefits for existing medicines too: it can be used to elucidate the mechanism of action, identify new patient responders, improve diagnosis and more precisely target treatment.MechanismsElucidate the mechanism of action._e59cd8fe-7e9a-11ea-88d1-bfdf0983ea004.2.1Patient RespondersIdentify new patient responders._e59cda20-7e9a-11ea-88d1-bfdf0983ea004.2.2DiagnosesImprove diagnosis._e59cdbec-7e9a-11ea-88d1-bfdf0983ea004.2.3TreatmentsTarget treatments more precisely._e59cdd22-7e9a-11ea-88d1-bfdf0983ea004.2.42020-04-14https://benevolent.ai/our-visionOwenAmburOwen.Ambur@verizon.net