AI & Deep Learning Papers, Links, Articles etc

This page is to collect and save scientific citations and useful links.

At this time the research papers of interest are (1) quality reviews; (2) use cases in AI and ML use in drug discovery; (3) high-profile use cases of AI and ML in medical diagnostics; (4) regulatory and ethical aspects of AI application in drug discovery and medicine.

  1. AI-powered drug discovery captures pharma interest https://www.nature.com/nbt/journal/v35/n7/full/nbt0717-604.html
  2. Great intro to ML and Big Data Demystifying Big Data and Machine Learning for Healthcare  https://www.crcpress.com/Demystifying-Big-Data-and-Machine-Learning-for-Healthcare/Natarajan-Frenzel-Smaltz/p/book/9781138032637
  3. The Next Era: Deep Learning in Pharmaceutical Research https://www.ncbi.nlm.nih.gov/pubmed/27599991 - Ekins Nov 2016 
    https://www.pharma-iq.com/informatics/articles/is-big-pharma-really-on-cusp-of-ai-shake-out-0
  4. Review of AI June 2017 http://www.biorxiv.org/content/early/2017/05/28/142760
  5. Github discussions is exellent https://github.com/greenelab/deep-review/issues
  6. Excellent Blog from Bharath Ramsundar http://rbharath.github.io/what-cant-deep-learning-do/
  7. IBM Watson A Reality Check for IBM’s AI Ambitions https://www.technologyreview.com/s/607965/a-reality-check-for-ibms-ai-ambitions/
  8. June 2017 Next Generation AI algorithms need to make most of AI chips optimisation
  9. Greg Diamos, Head of Systems Research at Baidu Silicon Valley AI
  10.  https://www.forbes.com/sites/ciocentral/2017/06/21/we-need-next-generation-algorithms-to-harness-the-power-of-todays-ai-chips/#7f20f83a47a0
  11. WSJ June 2017How AI Is Transforming Drug Creation https://www.wsj.com/articles/how-ai-is-transforming-drug-creation-1498442760
  12. Forbes Aug 2017 https://www.forbes.com/sites/forbestechcouncil/2017/08/03/artificial-intelligence-in-drug-discovery-a-bubble-or-a-revolutionary-transformation/#26079df64494
  13. Beyond the Hype: Deep Neural Networks 2 Outperform Established Methods Using 3 A ChEMBL Bioactivity Benchmark Set http://www.biorxiv.org/content/biorxiv/early/2017/07/28/168914.full.pdf
  14. WSJ Article March 2017 - broader business space review https://www.wsj.com/articles/how-ai-is-transforming-the-workplace-1489371060
  15. Top 10 Recommendations for the AI Field in 2017 Oct 2017
  16. The challenge of AI technology adoption in healthcare https://www.linkedin.com/pulse/challenge-ai-technology-adoption-healthcare-jay-chyung-md-phd/
  17. Oct 2017 Challenages of AI adoption in Healthcare https://www.linkedin.com/pulse/challenge-ai-technology-adoption-healthcare-jay-chyung-md-phd/?trackingId=Cpa346%2FuUurbWLcO%2FhUTxw%3D%3D
  18. Jan 2017 First FDA Approved Cloud Based Deep learning https://www.forbes.com/sites/bernardmarr/2017/01/20/first-fda-approval-for-clinical-cloud-based-deep-learning-in-healthcare/#357cbfe1161c     (*** added 2017)

  1. Fundamental of Deep Learning https://www.analyticsvidhya.com/blog/2016/03/introduction-deep-learning-fundamentals-neural-networks/?utm_content=bufferf9225&utm_medium=social&utm_source=twitter.com&utm_campaign=buffer
  2. Drug Makers Guide to the Galaxy: Excentia and polypharmacology https://www.nature.com/news/the-drug-maker-s-guide-to-the-galaxy-1.22683
  3. Data is Key ingredient for AI https://www.elsevier.com/connect/5-reasons-data-is-a-key-ingredient-for-ai-applications?sf175330640=1
  4. HBR AI for the real world https://hbr.org/2018/01/artificial-intelligence-for-the-real-world
  5. AI for Health and Healtcare report (Mitre Group) https://www.healthit.gov/sites/default/files/jsr-17-task-002_aiforhealthandhealthcare12122017.pdf
  6. Deep Learning for Biology https://www.nature.com/articles/d41586-018-02174-z
  7. An automated curation procedure for addressing chemical errors and inconsistencies in public datasets used in QSAR modelling https://www.ncbi.nlm.nih.gov/pubmed/27885862
  8. The ELF Honest Data Broker: informatics enabling public–private collaboration in a precompetitive arena https://www.sciencedirect.com/science/article/pii/S1359644615004249?via%3Dihub
  9. Feb 2018: AI Startups https://blog.benchsci.com/startups-using-artificial-intelligence-in-drug-discovery?lipi=urn%3Ali%3Apage%3Ad_flagship3_feed%3BmEHpBm1fQ%2BKkySB%2FSg8G%2Fw%3D%3D#step11
  10. Opportunities And Obstacles For Deep Learning In Biology And Medicine https://www.biorxiv.org/content/early/2018/01/19/142760
  11. J. R. Soc. Interface 15: 20170387. http://dx.doi.org/10.1098/rsif.2017.0387
  12. Perspectives: Augmented intelligence https://cen.acs.org/articles/96/i14/Perspectives-Augmented-intelligence.html.html
  13. Computer system predicts products of chemical reactions: Machine learning approach could aid the design of industrial processes for drug manufacturing http://people.csail.mit.edu/tommi/papers/Connor_etal_ACS_2017.pdf
  14. ANN used for Image analysis - Novartis NIBR https://www.novartis.com/stories/discovery/machine-learning-poised-accelerate-drug-discovery and the original publication in Bioinformatics: https://academic.oup.com/bioinformatics/article/33/13/2010/2997285?searchresult=1
  15. The failure of IBM Watson: https://www.statnews.com/2018/07/25/ibm-watson-recommended-unsafe-incorrect-treatments/
  16. An optimistic editorial from Nature references success of Wuxi NextCode: https://www.nature.com/articles/d41586-018-05267-x
  17. AI interpretation of radiology images is hard, harder than initially anticipated: https://www.technologyreview.com/s/610552/google-x-ray-project-shows-ai-wont-replace-doctors-any-time-soon/
  18. PLASTER, Nvidia's methodology for assessment of AI performance (PDF): https://images.nvidia.com/content/pdf/plaster-deep-learning-framework.pdf
  19. UK national platform for AI? http://news.top-consultant.com//New-White-Paper-Calls-for-Government-wide-AI-Platform-19336.html
  20. How Technology can tame scientific literature https://www.nature.com/articles/d41586-018-06617-5
  21. Oncology use case: http://gate250.com/rk/2018FLAG_UsingArtificialIntelligence_Whitepaper_digital-Final.pdf  
  22. Rules of Machine Learning http://martin.zinkevich.org/rules_of_ml/rules_of_ml.pdf - could be expanded
  23. Google DeepMind and healthcare in an age of algorithms   https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5741783/
  24. "Winner's Curse" - How to do better science in AI: https://openreview.net/pdf?id=rJWF0Fywf
  25. A list of biomedical start-ups that claim AI as a core technology: https://blog.benchsci.com/startups-using-artificial-intelligence-in-drug-discovery
  26. AI used to predict CRISPR DNA cuts; in the future, this may be used for gene therapy: http://www.bio-itworld.com/2018/11/08/machine-learning-predicts-how-dna-breaks-under-crispr.aspx
  27. Augmenting Medicinal Chemist with data https://doi.org/10.1016/j.drudis.2018.03.011
  28. Review of Forrester Wave views on AI and Automation https://www.forbes.com/sites/gilpress/2018/11/06/ai-and-automation-2019-predictions-from-forrester/#788550a54cb5 Nov 2018
  29. Ethics in AI: Rabbi Jonathan Sacks explores how we should respond to the ways in which AI is transforming our world https://www.bbc.co.uk/sounds/play/b0bgrw3k
  30. What it means to open AI’s black box? http://usblogs.pwc.com/emerging-technology/to-open-ai-black-box/
  31. Drug Discovery Maps, a Machine Learning Model That Visualizes and Predicts Kinome–Inhibitor Interaction Landscapes https://pubs.acs.org/doi/full/10.1021/acs.jcim.8b00640      (*** added 2018)

  1. Tuning artificial intelligence on the de novo design of natural-product-inspired retinoid X receptor modulators https://www.nature.com/articles/s42004-018-0068-1
  2. Artificial intelligence and its potential in oncology https://doi.org/10.1016/j.artmed.2018.08.008
  3. Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review, by Bernal, J., Artificial Intelligence In Medicine,
  4. https://doi.org/10.1016/j.artmed.2018.08.008
  5. Transforming Computational Drug Discovery with Machine Learning and AI ACS Med. Chem. Lett. 2018, 9, 11, 1065-1069
  6. The convergence of artificial intelligence and chemistry for improved drug discovery (AZ) https://www.future-science.com/doi/full/10.4155/fmc-2018-0161
  7. AI in Pharma, by LEK Consultinghttps://www.lek.com/insights/artificial-intelligence-life-sciences-formula-pharma-success-across-drug-lifecycle#.XAvu0zCNM7M.linkedin
  8. Are Ontologies relevant in a Machine Learning-centric world? By Lee Harland, based on our own Boston AI workshop: https://www.scibite.com/are-ontologies-relevant-in-a-machine-learning-centric-world/ 
  9. Computers turn neural signals into speech:http://science.sciencemag.org/content/363/6422/14?utm_campaign=wnews_sci_2019-01-03&et_rid=17144995&et_cid=2581434
  10. How is automated text summarization done? https://arxiv.org/pdf/1707.02268.pdf
  11. FREE ML courses (the title says 10, but the text contains links to over 30): https://www.kdnuggets.com/2018/12/10-more-free-must-see-courses-machine-learning-data-science.html
  12. Eric Topol: High-performance medicine: the convergence of human and artificial intelligence
  13. AI and Neural Net Summary in 21 pages:https://www.linkedin.com/feed/update/activity:6492067351771574272/      (*** added 01/2019)

  1. Dark Secret at heart of AI -  Black box https://www.technologyreview.com/s/604087/the-dark-secret-at-the-heart-of-ai/
  2. Classification of ligand-binding pockets in proteins with a convolutional neural network: https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1006718  (but only works well for nucleotide and heme binding sites, so only in a couple of highly specialized cases)
  3. Overfitting dangers with small datasets: https://www.chemistryworld.com/news/dispute-over-reaction-prediction-puts-machine-learnings-pitfalls-in-spotlight/3009912.article
  4. Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks (Nature): https://www.nature.com/articles/s41598-019-40041-7.pdf
  5. AI recognizes speech‐based markers for posttraumatic stress disorder in US veterans, with 89% classification rate: https://onlinelibrary.wiley.com/doi/abs/10.1002/da.22890
  6. A machine learning approach for somatic mutation discovery for diagnostics: https://stm.sciencemag.org/content/10/457/eaar7939  and the full-length research article: https://stm.sciencemag.org/content/11/489/eaat6177?utm_source=STAT+Newsletters&utm_campaign=50dc0470e5-MR_COPY_01&utm_medium=email&utm_term=0_8cab1d7961-50dc0470e5-149702353
  7. Learn the basics of statistics: https://www.statisticshowto.datasciencecentral.com/probability-and-statistics/ Well, not only the basics! Some advanced topics too.
  8. On the interpretability of Neural Net models: https://appsilon.com/please-explain-black-box/
  9. Predict risk of lung cancer by a Google AI model? Claimed 94% AUC, but refused to release the code: https://www.nature.com/articles/s41591-019-0447-x
  10. What is the difference between AI, ML, and Deep Learning models? See here: https://www.edureka.co/blog/ai-vs-machine-learning-vs-deep-learning/  and here: https://www.geospatialworld.net/blogs/difference-between-ai%EF%BB%BF-machine-learning-and-deep-learning/    (*** added 05/2019)

  1. Review: AI in Drug Design: https://www.mdpi.com/1420-3049/23/10/2520/htm
  2. Is China way ahead of the West in AI use in medicine? See here (may require registration for full-length paper): https://www.statnews.com/2019/06/05/china-leapfrogging-us-using-ai-in-medicine/
  3. ML Flow, a system for managing the AI model life cycle, and deployment to the cloud: https://mlflow.org/
  4. An interesting lecture in the history of science. Bernard Widrow, a Stanford professor, talks about the Least Mean-Squares (LMS) adaptive algorithm used to train first neuron models. The device shown in the lecture dates back to 1959 and is actually an electro-mechanical switch box. It has parts that broke due to age, but still functions, and can be trained to tell apart letters of the alphabet.  Part 1 and part 2
  5. Clinical validity and technical validity of AI methods in medicine: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6526255/#r10
  6. In a review of 516 research papers in the diagnostic analysis of medical images with AI, only 31 (or 6%) performed external validation, and none used best practices in clinical trial design: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6389801/  The papers reviewed were published between Jan 1st and Aug 18th 2018.
  7. FDA: Proposed Regulatory Framework for Modifications to Artificial Intelligence/Machine Learning (AI/ML)-Based Software as a Medical Device (SaMD) - Discussion Paper and Request for Feedback: https://www.regulations.gov/document?D=FDA-2019-N-1185-0001  (download the actual document in PDF format from this page)
  8. Example of QSAR in 3D using Convolutional Neural Network: https://www.jstage.jst.go.jp/article/cpb/67/5/67_c18-00757/_html/-char/en
  9. Nature Review: Technologies to watch in 2019: https://www.nature.com/articles/d41586-019-00218-6
  10. Machine Learning for Medical Ultrasound: Status, Methods, and Future Opportunities. This review includes organ segmentation, an apparently hard topic. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5886811/
  11. Predict Adverse Drug Reactions (ADRs) through drug-gene interactions: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5473874/  This review might be of interest in view of our recent drug repurposing datathon, where prediction of ADRs played a large role. (*** added 06/2019)

  1. Privacy of patients and data donors in the age of genomics and big data mining: https://genomebiology.biomedcentral.com/articles/10.1186/s13059-019-1741-0
  2. Automated de novo molecular design by hybrid machine intelligence and rule-driven chemical synthesis. By Alexander Button, Daniel Merk, Jan A. Hiss & Gisbert Schneider, Nature Machine Intelligence, volume 1, pages307–315 (2019)
  3. Review: Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery: https://pubs.acs.org/doi/full/10.1021/acs.chemrev.8b00728
  4. Machine and deep learning meet genome-scale metabolic modeling: https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1007084
  5. Disease gene prediction for molecularly uncharacterized diseases: https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1007078
  6. Not quite ML, but curious: Identifying determinants of persistent MRSA bacteremia using mathematical modeling: https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1007087
  7. A popular piece on using AI to mine Pubmed data in an attempt to diagnose a rare disease: "How an AI expert took on his toughest project ever: writing code to save his son’s life", but what is really interesting, is that this project has a public github page, from which one can get one's own copy of the software
  8. Artificial intelligence for assisting diagnostics and assessment of Parkinson's disease-A review. Main point is that after 48 completed studies, there is still not enough data.
  9. Putting benchmarks in their rightful place: The heart of computational biology. Editorial
  10. Ten simple rules for writing and sharing computational analyses in Jupyter Notebooks. Best practices
  11. Three pitfalls to avoid in machine learning (Nature, Google)  (*** added 07/2019)

  1. Review: Deep learning in drug discovery: opportunities, challenges and future prospects
  2. Learning Health System for Breast Cancer: Pilot Project Experience. "It is possible to extract, read, and combine data from the EHR to view the patient journey. The agreement between NLP and the gold standard was high, which supports validity."  
  3. WE-E-213CD-06: A Locally Adaptive, Intensity-Based Label Fusion Method for Multi- Atlas Auto-Segmentation. Comparison of proprietary anatomy segmentation methods for medical images.
  4. Best practices of AI use in medicine: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6599029/
  5. A collection of papers on use of AI and ML in diagnostic imaging: The use and performance of artificial intelligence applications in dental and maxillofacial radiology: A systematic review; State-of-the-Art Deep Learning in Cardiovascular Image Analysis; Artificial intelligence in cardiovascular imaging: state of the art and implications for the imaging cardiologistRadiomics and Artificial Intelligence for Biomarker and Prediction Model Development in Oncology
  6. The combination of computational chemistry and computational materials science with machine learning and artificial intelligence    This is relevant to AI in CADD
  7. "Learning rates of state-of-the-art artificial learning algorithms can be improved by adopting fundamental principles that govern the dynamics of the brain" Biological learning curves outperform existing ones in artificial intelligence algorithms
  8. Artificial intelligence in digital pathology
  9. An Analytical Review of Computational Drug Repurposing
  10. Automated Diagnosis of Lymphoma with Digital Pathology Images Using Deep Learning
  11. Yearbook of Medical Informatics, published by Thieme Journals in August 2019, contains many reviews on the AI applications in medical research and practice, for instance, "Recent Advances in Using Natural Language Processing to Address Public Health Research Questions Using Social Media and ConsumerGenerated Data", "Artificial Intelligence in Health: New Opportunities, Challenges, and Practical Implications", and many more. (*** added 08/2019)

  1. Exploring microRNA Regulation of Cancer with Context-Aware Deep Cancer Classifier
  2. PLATYPUS: A Multiple–View Learning Predictive Framework for Cancer Drug Sensitivity Prediction
  3. Tumor classification based on image analysis: A Novel Method for Classifying Liver and Brain Tumors Using Convolutional Neural Networks, Discrete Wavelet Transform and Long Short-Term Memory Networks
  4. Drug repurposing in oncology: Compounds, pathways, phenotypes and computational approaches for colorectal cancer
  5. Towards trustable machine learning  "Clinical implementations of machine learning that are accurate, robust and interpretable will eventually gain the trust of healthcare providers and patients"
  6. Gartner on ML in business (very general and not focused on pharma, but could be a good primer):    https://www.gartner.com/binaries/content/assets/events/keywords/catalyst/catus8/preparing_and_architecting_for_machine_learning.pdf
  7. NP-Scout: Machine Learning Approach for the Quantification and Visualization of the Natural Product-Likeness of Small Molecules
  8. Review: Looking beyond the hype: Applied AI and machine learning in translational medicine
  9. Special issue of the Journal of the American College of Radiology on AI and Data Science, with many application cases of AI to clinical image processing
  10. Statistical considerations for testing an AI algorithm used for prescreening lung CT images. Although a highly specialized use case is employed here, the statistical concepts are broadly valid.
  11. Deep learning enables rapid identification of potent DDR1 kinase inhibitors. Report from A. Zhavoronkov's group to Nature Biotechnology.
  12. Machine Learning to Predict, Detect, and Intervene Older Adults Vulnerable for Adverse Drug Events in the Emergency Department 
  13.  Extracting biological age from biomedical data via deep learning: too much of a good thing? An attempt to create a CNN predictor of the natural "biological clock"
  14. Computational prediction of diagnosis and feature selection on mesothelioma patient health records. Random forest outperformed all models tried, but MCC is low for all model categories. Data is available via the Irvine depository.
  15. Modelling the prevalence of diabetes mellitus risk factors based on artificial neural network and multiple regression. Logistic regression outperformes a neural net.    (*** added 09/2019)

  1. AI used to make sonogram movies of living heart. STAT news report.
  2. User-centric design of AI products: People+AI Guidebook from Google
  3. AAIH whitepaper describes the basic AI techniques and discusses some applications in healthcare: https://www.theaaih.org/pdf/1571334853.pdf 
  4. AI in health care delivery: https://catalyst.nejm.org/health-care-ai-systems-changing-delivery/
  5. WanDB, a package to log hyperparameters and output metrics from your runs, explore model architectures, and compare results. (FYI only. We at Pistoia Alliance have NOT tested this).
  6. Bradshaw molecular design tool GSK Oct 2019  https://link.springer.com/article/10.1007/s10822-019-00234-8 
  7. Looking beyond the hype: Applied AI and machine learning in translational medicine
  8. Characterizing Artificial Intelligence Applications in Cancer Research: A Latent Dirichlet Allocation Analysis. Trends in AI publications in medicine.
  9. Patient similarity networks for precision medicine
  10. How far have decision tree models come for data mining in drug discovery?
  11. Ethics of Artificial Intelligence in Radiology: Summary of the Joint European and North American Multisociety Statement
  12. An Online Calculator for the Prediction of Survival in Glioblastoma Patients Using Classical Statistics and Machine Learning
  13. A collection of psychiatry-themed use cases of AI came out this month: 
    1. Complexity in mood disorder diagnosis: fMRI connectivity networks predicted medication‐class of response in complex patients
    2. Exploring the Utility of Community-Generated Social Media Content for Detecting Depression: An Analytical Study on Instagram
    3. Machine learning in major depression: From classification to treatment outcome prediction
    4. Prediction Models of Functional Outcomes for Individuals in the Clinical High-Risk State for Psychosis or With Recent-Onset Depression  Apparently, ML-based prognostic engine out-performs human psychiatrists
  14. The plan to mine the world’s research papers. Nature on a controversial plan to subvert the copyright
  15. Discovery of Novel Conotoxin Candidates Using Machine Learning. De-novo design of toxic peptides. Interesting but unfortunately does not include experimental validation of the pharmaceutical properties of these sequences
  16. Why deep-learning AIs are so easy to fool  DNNs are brilliant at highly specific tasks and brittle when unexpected input arrives. Nature editorial on adversarial learning in DNNs.
  17. Rethinking Drug Repositioning and Development with Artificial Intelligence, Machine Learning, and Omics. Review
  18. Artificial Intelligence, Responsibility Attribution, and a Relational Justification of Explainability. Responsibility to explain AI results is not only for the regulators, but mainly for patients.
  19. “A patient like me” – An algorithm-based program to inform patients on the likely conditions people with symptoms like theirs have.
  20. Key challenges for delivering clinical impact with artificial intelligence. "Robust clinical evaluation, using metrics that are intuitive to clinicians and ideally go beyond measures of technical accuracy to include quality of care and patient outcomes, is essential. Further work is required (1) to identify themes of algorithmic bias and unfairness while developing mitigations to address these, (2) to reduce brittleness and improve generalisability, and (3) to develop methods for improved interpretability of machine learning predictions."     (*** added 10/2019)

  1. A good primer, An Ophthalmologist’s Guide to Deciphering Studies in Artificial Intelligence
  2. Reliable Prediction of Human Cytochrome P450 Inhibition Using Artificial Intelligence Approaches
  3. Translational AI and Deep Learning in Diagnostic Pathology
  4. Artificial‐Intelligence‐Driven Organic Synthesis—En Route towards Autonomous Synthesis?
  5. Has Drug Design Augmented by Artificial Intelligence Become a Reality? By Ola Engkvist
  6. Transfer learning for biomedical named entity recognition with neural networks
  7. Machine Learning in Drug Discovery
  8. Fréchet ChemNet Distance: A Metric for Generative Models for Molecules in Drug Discovery
  9. Machine learning predicts individual cancer patient responses to therapeutic drugs with high accuracy
  10. AI algorithm detects melanoma in skin images with accuracy matching that of a specialist MD
  11. Artificial intelligence applications for pediatric oncology imaging. A review of a multitude of AI application in medical imaging in many modalities. Contrary to the title, case studies are not limited to juvenile patients, so the review is broadly applicable.
  12. Design of metalloproteins and novel protein folds using variational autoencoders. Automated protein engineering. Follows the best practice of making code fully and freely available (see ref).
  13. Superior skin cancer classification by the combination of human and artificial intelligence. What is interesting about this paper (yet another description of yet another clinical classifier), are: (1) the size of the collaboration effort; and (2) the combined approach of using AI and human input.
  14. Protein engineering with Machine Learning driven CAD: "One-shot optimization of multiple enzyme parameters: Tailoring glucose oxidase for pH and electron mediators"
  15. Pathways to breast cancer screening artificial intelligence algorithm validation. This paper focuses on external validation of diagnostic AI algorithms. How much validation is enough? Is the US FDA standard too permissive?
  16. The Last Mile: Where Artificial Intelligence Meets Reality discusses the challenges to the practical use of AI in the clinical setting
  17. A governance model for the application of AI in health care
  18. Clinical-grade computational pathology using weakly supervised deep learning on whole slide images (Nature Medicine)
  19. This may be important for all innovators, but the full text is behind a pay wall: Early Identification of Patentable Medical Innovations Use AI to browse descriptions of medical discoveries and flag those that are likely to be patentable
  20. BIPSPI: a method for the prediction of partner-specific protein–protein interfaces    Alas, leave-one-out validation method is prone to overfitting
  21. Automatic Organ Segmentation for CT Scans Based on Super-Pixel and Convolutional Neural Networks   Mentions some benchmark datasets for the organ segmentation problem ("Silver 7", (ref))
  22. An Efficient Implementation of Deep Convolutional Neural Networks for MRI Segmentation
  23. Computational Protein Design with Deep Learning Neural Networks   While interesting, the resulting accuracy of 38% indicates that there is much room for improvement
  24. Current trends in AI drug discovery start-ups, by our member Simon Smith
  25. 167 Startups Using Artificial Intelligence in Drug Discovery, by Simon Smith. This list was started in 2017 and is continuously updated.
  26. 62 Drugs in the Artificial Intelligence in Drug Discovery Pipeline, by Simon Smith
  27. By this moment (11.2019) the US FDA has approved at least 26 medical devices that use AI. Link   Link to the original Eric Topol post from the middle of 2019 and to his Nature paper
  28. Statement from FDA Commissioner Scott Gottlieb, M.D. on steps toward a new, tailored review framework for artificial intelligence-based medical devices: "We are exploring a framework that would allow for modifications to algorithms to be made from real-world learning and adaptation, while still ensuring safety and effectiveness of the software as a medical device is maintained. A new approach to these technologies would address the need for the algorithms to learn and adapt when used in the real world"   
  29. DeepWAS: Multivariate genotype-phenotype associations by directly integrating regulatory information using deep learning   
  30. Machine Learning Models Based on Molecular Fingerprints and an Extreme Gradient Boosting Method Lead to the Discovery of JAK2 Inhibitors
  31. Artificial intelligence in clinical and genomic diagnostics. Review (*** added 11/2019)

  1. Real-time multi-model ensemble forecasts for seasonal influenza in the U.S.
  2. A mathematical-descriptor of tumor-mesoscopic-structure from computed-tomography images annotates prognostic- and molecular-phenotypes of epithelial ovarian cancer  Nature Communications
  3. Are we doing a good job in validation of medical devices that are powered by AI? Lifecycle Regulation of Artificial Intelligence– and Machine Learning–Based Software Devices in Medicine, JAMA
  4. How to Read Articles That Use Machine Learning. JAMA  2019 Users’ Guides to the Medical Literature
  5. Adversarial Controls for Scientific Machine LearningACS Chemical Biology 2018 "Machine learning algorithms readily exploit confounding variables and experimental artifacts instead of relevant patterns, leading to overoptimistic performance and poor model generalization."
  6. CDSeq: A novel complete deconvolution method for dissecting heterogeneous samples using gene expression data. A machine-learning technique
  7. Algorithms on regulatory lockdown in medicine. Science paper on the regulation of AI-driven medical technologies.
  8. Rethinking drug design in the artificial intelligence era. Nature review with an extensive reference list. Gisbert et al..
  9. Attitudes Of Chinese Cancer Patients Toward The Clinical Use Of Artificial Intelligence. Cancer patients trust human doctors more than AI when AI recommendations and human MD opinions differ. Going forward this topic of trust will be gaining importance
  10. A Bayesian graph convolutional network for reliable prediction of molecular properties with uncertainty quantification.
  11. Visualizing structure and transitions in high-dimensional biological data. An algorithm to present highly complex, multi-dimensional data in a form with reduced dimensionality, suitable for human review.
  12. PathFlowAI: A High-Throughput Workflow for Preprocessing, Deep Learning and Interpretation in Digital Pathology. Using AI to analyze liver microscopy images
  13. Pacific Symposium in Biocomputing announcement of the workshop in ethics of AI.
  14. DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequences
  15. Ten quick tips for effective dimensionality reduction
  16. Random forest prediction of Alzheimer’s disease using pairwise selection from time series data. Not AI but machine learning
  17. Converging a Knowledge-Based Scoring Function: DrugScore2018.  DrugScore2018 is a competitive scoring and objective function for structure-based ligand design purposes.
  18. Practical Model Selection for Prospective Virtual Screening. Random Forest wins over complex NN methods.
  19. Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions Nature Communications 2019 Gasteiger et al
  20. Rule of thumb: Which AI / ML algorithms to apply to business problems. Has a small section on problems in health sciences. Ideally we'd be able to produce a similar guide but for problems specific to life science research.
  21. Conditional Molecular Design with Deep Generative Models
  22. The global landscape of AI ethics guidelines. Nature 09/2019
  23. Artificial Intelligence in medical imaging practice: looking to the future. A short review that covers the major application advances in the field as well as the ethical part of the AI use in medical decision-making. 11/2019
  24. Drug combination sensitivity scoring facilitates the discovery of synergistic and efficacious drug combinations in cancer. Use ML to cluster cancer cell lines based on their drug combination sensitivity profiles. PLOS Comp Bio 05/2019
  25. Implementation of machine learning algorithms to create diabetic patient re-admission profiles  using public data sources at UC Irvine Machine Learning Repository
  26. Machine Learning Technical Landscape picture
  27. Bayesian Nonparametric Models tutorial
  28. Comparison Study of Computational Prediction Tools for Drug-Target Binding Affinities
  29. From What to How: An Initial Review of Publicly Available AI Ethics Tools, Methods and Research to Translate Principles into Practices
  30. How the FDA Regulates AI
  31. Ethical considerations about artificial intelligence for prognostication in intensive care "Respect for patients’ autonomy during decision-making requires transparency of the data processing by AI models to explain the predictions derived from these models."  (*** added 12/2019)
  32. International evaluation of an AI system for breast cancer screening. This is a Google-developed tool which is claimed to achieve a higher accuracy in diagnosis of breast cancer than that by human oncologists. However, code and data used to build the classifier are not released.
  33. Applications of Machine Learning Approaches in Emergency Medicine; a Review Article. In this paper the authors compare performance of a different ML and AI methods for prediction (diagnosis, to be precise) of various diseases from EHR records. Performance is variable and the methods used for different disease types are vastly different. 
  34. Identification of pharmacodynamic biomarker hypotheses through literature analysis with IBM Watson
  35. Opportunities for Artificial Intelligence in Advancing Precision Medicine. Review of ML methods used to analyze "-omics" data.
  36. Towards A Rigorous Science of Interpretable Machine Learning. Arxiv
  37. Applications of Deep-Learning in Exploiting Large-Scale and Heterogeneous Compound Data in Industrial Pharmaceutical Research
  38. The MELLODDY Consortium. Pharma Companies Join Forces to Train AI for Drug Discovery Using Blockchain
  39. Addressing Bias in Artificial Intelligence in Health Care. Abstract only.
  40. AI in biomedical sciences attracted over $5B in VC investment. Market report
  41. Deep Learning-driven research for drug discovery: Tackling Malaria. PLOS
  42. Contract offers unprecedented look at Google deal to obtain patient data from the University of California. UCSF allowed Google to use patient data for AI research, which raises all kinds of ethical questions.
  43. A comparative study of deep learning architectures on melanoma detection
  44. Gartner Hype Cycle for Artificial Intelligence, 2019
  45. A Deep Learning Approach to Antibiotic Discovery    (*** added 02/2020)

  1. Machine learning in chemoinformatics and drug discovery. Review, may be valuable due to multiple references cited.
  2. Machine learning with random subspace ensembles identifies antimicrobial resistance determinants from pan-genomes of three pathogens. PLOS Comp Bio
  3. Systematic Review of Privacy-Preserving Distributed Machine Learning From Federated Databases in Health Care. Review
  4. COVID-19 Open Research Dataset (CORD-19) of scholarly literature has been released. Suitable for ML.
  5. In-Silico Molecular Binding Prediction for Human Drug Targets Using Deep Neural Multi-Task Learning. A comparison of many single-task and multi-task ML methods. Contrary to earlier observations, single-task models perform better. Multi-task models work well for groups of highly similar targets (as expected, more data results in better predictive performance).
  6. Predicting or Pretending: Artificial Intelligence for Protein-Ligand Interactions Lack of Sufficiently Large and Unbiased Datasets. More data, better, less biased benchmarks are needed.
  7. Large-scale comparison of machine learning methods for drug target prediction on ChEMBL.
  8. A deep learning framework for automatic diagnosis of unipolar depression. A classifier for diagnosis of major depression from EEG data.
  9. ARPNet: Antidepressant Response Prediction Network for Major Depressive Disorder. Not an ideal study set-up, likely resulting in overfitting. But the overall proposal to automate selection of drugs for personalized therapy is good.
  10. DDI-PULearn: a positive-unlabeled learning method for large-scale prediction of drug-drug interactions. Absence of a reported interaction does not equal a negative case due to sparsity of experimental data. 
  11. Human–machine partnership with artificial intelligence for chest radiograph diagnosis. Collective intelligence has a long history in medicine, and here is a high-tech twist on it.
  12. Improving Oral Cancer Outcomes with Imaging and Artificial Intelligence. Abstract only.
  13. Computer science versus COVID-19
  14. The ethics in AI research. Nature. The battle for ethical AI at the world’s biggest machine-learning conference. "Bias and the prospect of societal harm increasingly plague artificial-intelligence research — but it’s not clear who should be on the lookout for these problems."
  15. Using AI to create potentials for protein folding: AlphaFold (Nature) and DeepECA.
  16. AI is not really artificial reasoning, but a sophisticated classifier. "AI isn't" in response to "Deconstructing the diagnostic reasoning of human versus artificial intelligence"
  17. Best practices for AI in medicine: "Machine learning and artificial intelligence research for patient benefit: 20 critical questions on transparency, replicability, ethics, and effectiveness". BMJ. A lot of the best practices identified in this paper overlap with those identified by us, in an R&D application. A related paper: "Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies"
  18. Real world study for the concordance between IBM Watson for Oncology and clinical practice in advanced non‐small cell lung cancer patients at a lung cancer center in China. Compare this report to the best practices described in the previous link. This study focuses on concordance between AI and human MD recommendations (in reality, for IBM Watson, cohort recommendation of US-based MDs who provide input to IBM Watson, versus recommendations by individual overseas doctors), and not on clinically relevant metrics (improved outcomes).
  19. Deconstructing the diagnostic reasoning of human versus artificial intelligence. How do human doctors and AI tools arrive at diagnosis, and how do they mis-diagnose?
  20. Large-scale comparison of machine learning methods for drug target prediction on ChEMBL. Chemical Science
  21. In light of multiple announcements (see Kaggle and Decentralized.ai sites) of AI challenges to help combat COVID-19, a skeptical outlook: is there enough data? "Debate flares over using AI to detect Covid-19 in lung scans"  StatNews   (*** added 03/2020)

  1. Ethics in the AI world. Exclude the "black box" from making of important decisions. Science.
  2. Irreproducible results in biomarker research. This is not Ai strictly speaking, but this is a review of some data sources that we mine. 
  3. An Ai model that predicts COVID-19 patient decline is pushed into the clinic without sufficient testing (STAT newsletter). This is an indicator of a troubling trend.
  4. The need for a system view to regulate artificial intelligence/machine learning-based software as medical device. A somewhat controversial viewpoint paper.
  5. Ensuring Trustworthy Use of Artificial Intelligence and Big Data Analytics in Health Insurance. "Unless an enabling ethical environment is in place, the use of such analytics will likely contribute to the proliferation of unconnected data systems, worsen existing inequalities, and erode trustworthiness and trust."
  6. Asilomar ethical principles for AI. Published in 2017.
  7. Design of Natural‐Product‐Inspired Multitarget Ligands by Machine Learning. An interesting fully-automated ligand discovery that combines conventional molecular docking, chemoinformatics and AI approaches. The results of the computational molecular design were validated in-vitro.
  8. Primer on an ethics of AI-based decision support systems in the clinic
  9. P7003 - Algorithmic Bias Considerations. A proposal for a standard by IEEE.   (*** added 04/2020)

  1. What ML techniques are most frequently used to make diagnostic and therapeutic care models for diabetes? "Artificial Intelligence Applications in Type 2 Diabetes Mellitus Care: Focus on Machine Learning Methods"
  2. Diagnostic models based on epigenetic data. Review. Machine learning and clinical epigenetics: a review of challenges for diagnosis and classification.
  3. On the interpretability of machine learning-based model for predicting hypertension
  4. Predicting effective drug combinations using gradient tree boosting based on features extracted from drug-protein heterogeneous network. Predictive model is limited by availability of negative examples (failed drug combinations) in the training set.
  5. Predicting synthetic lethal interactions in human cancers using graph regularized self-representative matrix factorization. Same issue with the data: no negative examples. A reference to a very peculiar database of synthetic lethal gene interactions.
  6. Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis. Even small deviations from the 50/50 in the training data result in degradation of model performance on the under-represented gender. (ChestXpert data set, used in one of the reported studies, is 60% male and 40% female). Effectively it is a data consistency problem, similar to the two papers above.
  7. Improving reproducibility in computational biology research. This is not a full paper, but a declaration of intent to run a study.
  8. The Affective Ising Model: A computational account of human affect dynamics. Is Ising Model really ML? Not quite sure. But this paper makes a curious attempt to compute human emotions.  (*** added 05/2020)
  1. Prioritizing and Analyzing the Role of Climate and Urban Parameters in the Confirmed Cases of COVID-19 Based on Artificial Intelligence Applications. Ultimately, this study resulted in a simple regression model, confirming what would seem already known: higher population density and higher relative humidity levels result in higher incidence of the COVID-19.
  2. An Open-Source, Vender Agnostic Hardware and Software Pipeline for Integration of Artificial Intelligence in Radiology Workflow. This publication is notable because it makes the source code accessible; see https://github.com/bdrad/clinical_ml_integration
  3. Artificial intelligence in chemistry and drug design. Editorial. Section that discusses relative performance of ML models over other QSAR approaches may be noteworthy.
  4. Medicinal Chemists Versus Machines Challenge: What Will It Take to Adopt and Advance Artificial Intelligence for Drug Discovery? Quote: " To ensure continued evolution of AI technologies, we propose a series of challenges of increasing complexity by comparing and combining the machine and human intelligence in medicinal chemistry."
  5. Application of explainable ensemble artificial intelligence model to categorization of hemodialysis-patient and treatment using nationwide-real-world data in Japan
  6. Progressive learning: A deep learning framework for continual learning. An attempt to step forward from complex yet standardized classifiers into real machine learning with an explicit codification of transfer learning.
  7. SEVERITAS: An Externally Validated Mortality Prediction for Critically Ill Patients in Low and Middle-Income Countries.
  8. Predicting Parameters in Deep Learning. CNNs are often created too complex with too many parameters. In this study up to 95% of neural net's parameters could be predicted from the values of other parameters, suggesting that these extra parameters have no real predictive power. This phenomenon is already well-known to the practitioners of simple machine learning models, who routinely review input data sets for co-linearity between independent variables. 
  9. SD-UNet: Stripping down U-Net for Segmentation of Biomedical Images on Platforms with Low Computational Budgets. Unfortunately, you get what you pay for, and this is very much visible in figure 9 that illustrates performance of the simplified method on a microscopy dataset.
  10. Regulation of predictive analytics in medicine: Algorithms must meet regulatory standards of clinical benefit. Science 02/2019
  11. Predicting translational progress in biomedical research. PLOS Biol.  An 84% accurate machine learning system that detects whether a paper is likely to be cited by a future clinical trial or guideline.
  12. Mechanism of Baricitinib Supports Artificial Intelligence-Predicted Testing in COVID-19 Patients.
  13. Advancing Drug Discovery via Artificial Intelligence. Review in Cell, with a vast collection of references to computational methods.
  14. Artificial Intelligence-Powered Search Tools and Resources in the Fight Against COVID-19.
  15. Measuring the Quality of Explanations: The System Causability Scale (SCS). Comparing Human and Machine Explanations
  16. Accuracy of Artificial Intelligence-Assisted Detection of Upper GI Lesions: A Systematic Review and Meta-Analysis. AI is accurate in the detection of upper GI neoplastic lesions and HP infection status. However, most of these studies were based on retrospective review of selected images, which would require further validation in prospective trials.
  17. Human Gut Microbiome Aging Clock Based on Taxonomic Profiling and Deep Learning.
  18. Deep learning in mental health outcome research: a scoping review.
  19. Sex and gender differences and biases in artificial intelligence for biomedicine and healthcare.
  20. Transitional Mesothelioma and Artificial Intelligence: Do We Need One More Subtype? and Do We Need Computers to Identify Them?   A contrarian viewpoint: instead of training AI to make differential diagnosis of more vs less aggressive tumor sub-types, train pathologists. (*** added 07/2020)

  1. Artificial intelligence in chemistry and drug design. Review with multiple references to methods, but without critical assessment.
  2. Artificial Intelligence in Drug Discovery: Into the Great Wide Open. Editorial in the special issue of the J Med Chem on AI. (The direct link to this special issue is not yet available).
  3. The upside of being a digital pharma player. Review. Deep Dive Into Big Pharma AI Productivity: One Study Shaking The Pharmaceutical Industry is a commentary on the previous paper, with interviews with the authors, and some interesting statistics of business activity and publishing in the AI field in big pharmaceutical firms.
  4. Reflections on sharing clinical trial data.
  5. Research summary: Principles alone cannot guarantee ethical AI.  (*** added 08/2020) 

  1. 2020 Special Section on Ethics in Health Informatics 
  2. Artificial Intelligence and Suicide Prevention: A Systematic Review of Machine Learning Investigations
  3. Digitizing clinical trials   
  4. Medical Information Extraction in the Age of Deep Learning
  5. Recommendations for machine learning validation in biology. A preprint of a paper submitted by our members from Elixir EU to Nature Methods.
  6. Ten simple rules to power drug discovery with data science. One more best practices paper.     (*** added 09/2020)

  1. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension
  2. Minimum information about clinical artificial intelligence modeling: the MI-CLAIM checklist
  3. Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension
  4. "Ghost writer" Creating clinical study reports with AI
  5. AI Index Report 2019
  6. An Artificial Intelligence Approach to Proactively Inspire Drug Discovery with Recommendations
  7. Transparency and reproducibility in artificial intelligence     (*** added 10/2020)

  1. REINVENT 2.0: An AI Tool for De Novo Drug Design
  2. A collection of papers on ethics in biomedical use of AI came out this month:
    1. The ethical adoption of artificial intelligence in radiology. Ownership, trading in patients' data, and anonymization are among the topics addressed.
    2. Identifying Ethical Considerations for Machine Learning Healthcare Applications. With dozens of public comments, such as Respect and Trustworthiness in the Patient-Provider-Machine Relationship: Applying a Relational Lens to Machine Learning Healthcare Applications and Where Bioethics Meets Machine Ethics, and even An Ethical Framework to Nowhere
    3. These papers talk to the ideas expressed in Do no harm: a roadmap for responsible machine learning for health care, published in Nature a year ago
  3. Transfer learning enables prediction of CYP2D6 haplotype function
  4. Inconsistency in the use of the term "validation" in studies reporting the performance of deep learning algorithms in providing diagnosis from medical imaging   reminds one of the importance of standards in description and reporting of AI models.
  5. A review on drug repurposing applicable to COVID-19
  6. Global gene network exploration based on explainable artificial intelligence approach (*** added 11/2020)

  1. A High Recall Classifier for Selecting Articles for MEDLINE Indexing
  2. McKinsey The State of AI in 2020
  3. Gartner Hype Cycle for AI in 2020
  4. Artificial Intelligence of COVID-19 Imaging: A Hammer in Search of a Nail. A critical review of a flood of similar publications reporting binary classifiers of unknown quality and clinical utility.
  5. Stochastic Channel-Based Federated Learning With Neural Network Pruning for Medical Data Privacy Preservation: Model Development and Experimental Validation
  6. Artificial intelligence in the early stages of drug discovery. Review
  7. Multi-objective optimization methods in novel drug design
  8. Incorporating biological structure into machine learning models in biomedicine. Review
  9. Spectrum of deep learning algorithms in drug discovery. Review
  10. Identifying transcriptomic correlates of histology using deep learning
  11. Repurposing therapeutics for COVID-19: Rapid prediction of commercially available drugs through machine learning and docking
  12. Medical Information Extraction in the Age of Deep Learning
  13. Artificial Intelligence (AI)-Based Systems Biology Approaches in Multi-Omics Data Analysis of Cancer
  14. Deep metabolome: Applications of deep learning in metabolomics
  15. MSpectraAI: a powerful platform for deciphering proteome profiling of multi-tumor mass spectrometry data by using deep neural networks
  16. Predictive article recommendation using natural language processing and machine learning to support evidence updates in domain-specific knowledge graphs. IBM PARSe program.
  17. Why We Need to Bust Some Myths about AI. And the site referenced: https://www.aimyths.org/
  18. Superethics Instead of Superintelligence: Know Thyself, and Apply Science Accordingly. "We don't need superintelligence, we need superethics"
  19. The clinical artificial intelligence department: a prerequisite for success. A critical outlook on the clinical utility of AI.
  20. Radiomics for precision medicine: Current challenges, future prospects, and the proposal of a new framework. Review.
  21. A novel virtual screening procedure identifies Pralatrexate as inhibitor of SARS-CoV-2 RdRp and it reduces viral replication in vitro.
  22. Application of Computational Biology and Artificial Intelligence Technologies in Cancer Precision Drug Discovery. Review. (*** added 12/2020)

  1. Prognostic gene expression signatures of breast cancer are lacking a sensible biological meaning   Correlation is not causation, and molecular signatures are not unique
  2. Prediction of the confirmed cases and deaths of global COVID-19 using artificial intelligence
  3. Approval of artificial intelligence and machine learning-based medical devices in the USA and Europe (2015–20): a comparative analysis
  4. From 'molecules of life' to new therapeutic approaches, an evolution marked by the advent of artificial intelligence: the cases of chronic pain and neuropathic disorders. Review at DDT
  5. Cognitive analysis of metabolomics data for systems biology. Nature Protocols
  6. Use of artificial intelligence to enhance phenotypic drug discovery. Review. DDT
  7. Implementation of model explainability for a basic brain tumor detection using convolutional neural networks on MRI slices. "In conclusion, the early implementation of model explainability features can greatly benefit the development of neural networks in radiology as they can help to detect biases introduced with the training data and to assess the potential of an approach. In later stages of the development of a neural network, model explainability features become mandatory to provide physicians with the information they need to integrate the model’s predictions into a meaningful clinical decision." However the paper lacks detail on how exactly the features used in explaining the results were selected.
  8. Regulatory considerations for artificial intelligence technologies in GI endoscopy. Clear description of established and emergent regulatory approval procedures for the AI software as a medical device.
  9. STAT’s database of FDA-cleared AI tools. Requires subscription to read the full text. Excerpt: "Of 161 AI products cleared by the FDA in recent years, only 73 disclosed the amount of patient data used to validate the performance of their devices in public documents. Only seven reported the racial makeup of their study populations, and just 13 provided a gender breakdown"  (*** added 01/2021)

  1. SAveRUNNER: A network-based algorithm for drug repurposing and its application to COVID-19
  2. DeepMIB: User-friendly and open-source software for training of deep learning network for biological image segmentation
  3. Artificial intelligence in drug discovery: what is realistic, what are illusions? Part 1 and Part 2   (***added 04/2021)
  4. Applications of machine learning in drug discovery and development
  5. Opportunities for Artificial Intelligence in Advancing Precision Medicine
  6. Systematic literature review of machine learning methods used in the analysis of real-world data for patient-provider decision making
  7. Artificial intelligence to deep learning: machine intelligence approach for drug discovery
  8. SIMON: Open-Source Knowledge Discovery Platform
  9. GNNExplainer: Generating Explanations for Graph Neural Networks
  10. Therapeutics Data Commons: Machine Learning Datasets and Tasks for Therapeutics  (*** added 05/2021)

Conferences and Events Worth Remembering

  1. Yearly Neural Information Processing Systems 
  2. Precision Medicine World Congress: https://www.pmwcintl.com/2019sv/
  3. Open Data Science Conferences (this one is in SF, but there are events in London too): https://odsc.com/california
  4. Re-work AI summit, San Francisco (+ other events from the same organizers): https://www.re-work.co/