Jack DiGiovanna

"Sequence modeling and design from molecular to genome scale with Evo" by Eric Nguyen, Michael Poli, Matthew Durrant, Armin Thomas,  Jeremy Sullivan, Madelena Ng, Ashley Lewis, Aman Patel, Aaron Lou, Stefano Ermon, Tina Hernandez-Boussard, Patrick Hsu, Brian Hie et al. "The genome is a sequence that completely encodes the DNA, RNA, and proteins that orchestrate the function of a whole organism. Advances in machine learning combined with massive datasets of whole genomes could enable a biological foundation model that accelerates the mechanistic understanding and generative design of complex molecular interactions. We report Evo, a genomic foundation model that enables prediction and generation tasks from the molecular to genome scale. Using an architecture based on advances in deep signal processing, we scale Evo to 7 billion parameters with a context length of 131 kilobases (kb) at single-nucleotide, byte resolution. Trained on 2.7M prokaryotic and phage genomes, Evo can generalize across the three fundamental modalities of the central dogma of molecular biology to perform zero-shot function prediction that is competitive with, or outperforms, leading domain-specific language models. Evo also excels at multi-element generation tasks, which we demonstrate by generating synthetic CRISPR-Cas molecular complexes and entire transposable systems for the first time. Using information learned over whole genomes, Evo can also predict gene essentiality at nucleotide resolution and can generate coding-rich sequences up to 650 kb in length, orders of magnitude longer than previous methods. Advances in multi-modal and multiscale learning with Evo provides a promising path toward improving our understanding and control of biology across multiple levels of complexity." Blog: https://lnkd.in/dDpfHZbd Paper: https://lnkd.in/dpaswkHR

43

2 Comments

I'm now a peer-reviewer at ResearchHub. Looking forward to contributing to this #DeSci project. Thanks to Patrick Joyce Brian Armstrong Jeffrey Koury Arshia Malek and the rest of the folks at ResearchHub and ResearchHub Foundation for setting this community and opportunity up! More info through the link below. Check it out! #blockchain #science https://lnkd.in/ePEg5x3q

66

15 Comments

Peering through the haze of quantum theory 😎 https://lnkd.in/eneAymv4 [..]Advances in technology allowed the team to detect and measure effects that were once beyond the reach of scientific instruments. "We realized we weren't just seeing an anomaly," [lead researcher] Brietweiser says. "We were breaking into a new regime of physics that we can access with this technology[..]" –by Ian Scheffler , University of Pennsylvania

3

2 Comments

The proposed 5 levels of #Artificial #General #Intelligence #AGI #Chatbots: AI with conversational language #Reasoners: human-level problem-solving #Agents: systems that can take actions #Innovators: AI that can aid in invention #Organizations: AI that can do the work of an organization https://lnkd.in/gniqV-VQ

3

A framework for human evaluation of large language models in healthcare derived from literature review With generative artificial intelligence (GenAI), particularly large language models (LLMs), continuing to make inroads in healthcare, assessing LLMs with human evaluations is essential to assuring safety and effectiveness. This study reviews existing literature on human evaluation methodologies for LLMs in healthcare across various medical specialties and addresses factors such as evaluation dimensions, sample types and sizes, selection, and recruitment of evaluators, frameworks and metrics, evaluation process, and statistical analysis type. Our literature review of 142 studies shows gaps in reliability, generalizability, and applicability of current human evaluation practices. To overcome such significant obstacles to healthcare LLM developments and deployments, we propose QUEST, a comprehensive and practical framework for human evaluation of LLMs covering three phases of workflow: Planning, Implementation and Adjudication, and Scoring and Review. QUEST is designed with five proposed evaluation principles: Quality of Information, Understanding and Reasoning, Expression Style and Persona, Safety and Harm, and Trust and Confidence. https://lnkd.in/giHmFEbA

7

At M42 Health, we've developed #MEDIC - a comprehensive framework that goes beyond simple MCQs to evaluate LLMs across critical dimensions in healthcare. Here's what makes it game-changing: 1️⃣ We rigorously evaluated both clinical and general-purpose LLMs on closed/open-ended QA tasks and real-world medical scenarios. 2️⃣ MEDIC features a novel cross-examination framework that quantifies performance in areas like coverage and hallucination detection for tasks like text summarization - no reference outputs needed! 3️⃣ We're releasing all score rubrics, system and user prompts to the ML community. Let's set a new standard for LLM evaluation in healthcare together! LLM assessment has always been tricky, especially in sensitive fields like medicine. With MEDIC, we're paving the way for more reliable, safer AI in healthcare. You can find the full paper here: https://lnkd.in/egTZAHSH It has been a lot of work putting together this evaluation framework. Thanks to the entire team, with a special shout-out to Shadab for his invaluable contributions. We couldn't have done it without you all! Clément, Marco, Tathagata, Nada, Hamza, Svetlana, Nasir, and Dr. Ronnie. G42 Hugging Face PyTorch

97

3 Comments

𝐄𝐱𝐩𝐥𝐨𝐫𝐢𝐧𝐠 𝐀𝐈'𝐬 𝐑𝐨𝐥𝐞 𝐢𝐧 𝐑𝐞𝐯𝐨𝐥𝐮𝐭𝐢𝐨𝐧𝐢𝐳𝐢𝐧𝐠 𝐃𝐫𝐮𝐠 𝐃𝐢𝐬𝐜𝐨𝐯𝐞𝐫𝐲: Dive into our latest article, "𝐂𝐨𝐦𝐩𝐚𝐧𝐢𝐞𝐬 𝐭𝐨 𝐖𝐚𝐭𝐜𝐡 𝐔𝐬𝐢𝐧𝐠 𝐀𝐈 𝐢𝐧 𝐃𝐫𝐮𝐠 𝐃𝐢𝐬𝐜𝐨𝐯𝐞𝐫𝐲 - Meet The Expert: Dr. Alexander Tropsha." We had the privilege of interviewing Dr. Tropsha, K.H. Lee Distinguished Professor at the UNC Eshelman School of Pharmacy, University of North Carolina at Chapel Hill, who shared his expert insights on how artificial intelligence is reshaping the landscape of pharmaceutical research. Companies mentioned: Atomwise, BenevolentAI, Google DeepMind, Insilico Medicine & Recursion Pharmaceuticals #AIDrugDiscovery #PharmaceuticalInnovation #HealthTech

2

Just returning from the COSBI Scientific Advisory Board meeting. Enjoyed learning about the latest work of the team and discussing how combing new data types and #AI with their more established computational and systems biology approaches (#PBPK, #QSP, etc.) could add value to use-cases such as disease understanding, biomarker discovery, improved treatments, etc. To learn more about these topics and COSBI, this video is a great place to start... https://lnkd.in/gERSwWVB #computationalbiology #systemsbiology #modeling

56

1 Comment

“The AI Scientist can produce papers that exceed the acceptance threshold at a top machine learning conference as judged by our automated reviewer.” Researchers have built a multi-AI system that comes up with AI ideas, implements and tests the ideas, and writes a paper. It can mess up in a lot of ways, but this is where we’re going in many realms. It brought up interesting safety issues too. When the AI scientist was running up against the human-imposed time limit, it attempted to change the timer code rather than do the work faster. #ai #stem #education #aieducation #school

21

12 Comments

📢 Academic Integrity: A Growing Concern (Part 2) Unlike traditional journals, preprint services (like arXiv, bioRxiv & medRxiv, EarthArXiv Preprint Service, Research Square) allow researchers to share their work without undergoing the typical peer review process. While this accelerates the sharing of ideas and collaboration, it also means there is less oversight, potentially allowing anyone to upload content without stringent checks. The integrity of citation metrics is crucial because these metrics play a significant role in how scientists are ranked and recognized globally. One such ranking is Stanford University and Elsevier top 2% Scientists list, which identifies scholars who are top-cited in their respective fields. This ranking is based on an analysis of citation impact across multiple scientific fields and subfields. Being included in such a list is a mark of distinction for researchers, and unethical practices like artificial citation manipulation can threaten the integrity of these rankings, misrepresenting the true impact of a scholar's work. 🛡️ Here are some steps we can take to address these issues: 📩 Contact Support: Reach out to support teams of these platforms with detailed information if you notice any misuse of citations. 🗂️ Document Incidents: Keep records of artificial papers and any communication with the platform, which can be useful if the issue escalates. 🏫 Inform Academic Institutions: Academic institutions can offer support and may help address such issues on a larger scale. 🧑‍⚖️ Consider Legal Advice: If misuse persists or causes reputational damage, exploring legal options might be necessary. #ResearchIntegrity #AcademicReputation #EthicalResearch #ScholarshipMatters #ScienceCommunication #HIndexGaming #IntegrityMatters #ProtectResearch #ResearchAccountability #ResponsibleResearch #FraudInResearch #PublishOrPerish #QualityResearch #AcademicFraud #ResearchEthicsMatter #ResearchQualityAssurance #TrustInAcademia #FakePapers #ResponsiblePublishing #IntegrityInScholarship

7

Augment and Invent ✨ 💡 In a recent substack post (https://lnkd.in/g4iCuVaY), the always insightful Rishad Tobaccowala presents "10 thoughts about AI, Humans and Work in 10 minutes". They are all worth pondering (although I would not invoke Suleyman in # 3) but one that struck a chord with me, Thought # 6, summarizes two important themes: human augmentation and business (re)invention. Here is the thought: "6. The simpler questions are about efficiency and effectiveness. The real question is more existential. AI will deliver efficiencies by getting things done faster and cheaper and as importantly more effectively by unleashing insights and freeing talent to work on areas where humans excel and let the math and pattern finding and the rest be done by the machine. But the smart companies are thinking about how to re-invent, re-imagine and re-think their business. In the world we live today with distributed and unbundled work, next generation technologies and multi-polar globalization why are more companies not re-imagining their businesses versus just focussing on making yesterdays model cheaper and more effective?" Obvious pockets of inefficiencies will be addressed with #AI in the short term by businesses, thereby quickly eliminating any competitive advantage (a point made very nicely by Martin Reeves in a recent HBR article https://lnkd.in/gsaHk4V2). Any sustainable advantage will have to come from new ideas about augmentation (that amplify a company's unique assets) and from novel ideas in general for businesses. So, first, augmentation. I have been for 25 years a proponent of thinking about "unleashing insights and freeing talent to work on areas where humans excel and let the math and pattern finding and the rest be done by the machine". What is missing from a lot of the discourse on augmentation is what form it should take, specifically, how do humans and AIs interface? The chatbot form factor has been surprisingly effective (surprising to me at least) at opening floodgates of creativity from all kinds of horizons. It can't be the last frontier of human-AI interfacing. That needs to be invented. Which takes us to the second part: (re)invention. The winners will use #genAI to create new products, services, experiences that are not even conceivable without AI. Business model disruption driven by AI is just beginning. When you product or service can be 80% replaced by a self-serve AI-based version at 0.001% of the cost, you have to seriously rethink where you create value. And as Rishad Tobaccowala writes in thought # 7, "A company’s best opportunities and threats are likely come from outside its immediate category and AI allows it to extend into new areas."

3

Polygenic Risk Scoring (PRS) has come a long way from being a static genetic predictor to a dynamic tool in personalized medicine. Learn how generative AI makes PRS models more useful for predicting diseases: https://cogniz.at/401b2KF #BeCognizant #Lifesciences #GenerativeAI

2

I recently submitted a commentary for review on AI. "Is it hype or hope right now in oncology?" I was surprised at the response I got to my disclosure:. ***This editorial is co-authored by Marcus, a customized GPT developed specifically for Total Health’s medical writing team. As an AI-driven writer tuned to the needs of oncology professionals, Marcus has been instrumental in shaping the analysis that follows. While generative AI like Marcus brings speed and breadth to research and content, it’s the synergy between human and AI perspectives that can transform ideas into practice-changing insights. Together, we hope to offer a vision of AI’s true potential in oncology—and a sober reflection on the hurdles it must overcome to get there. In the evolving landscape of medical writing, the integration of AI tools has become increasingly significant. A recent and great article in the NEJM Group discusses the role of large language models in scientific communication and emphasizes the importance of transparency in their use. https://lnkd.in/g2w_bzTX At Total Health, we embrace innovation to enhance our content. In line with the principles of transparency and ethical AI usage, we disclose when AI tools, such as Marcus, assist in our scientific commentaries. This approach ensures that our audience is aware of the methodologies behind our content creation, maintaining trust and integrity in our communications. As we continue to explore the potential of AI in #medicaleducation, we remain committed to upholding the highest standards of transparency and ethical practice. #AI #Author #Transparency #Ethics #Innovation

7

1 Comment

AI in Drug Discovery: Disproving the Hype Skeptics This New Yorker article offers compelling evidence that AI is far from just hype, especially in drug research: ➡️Tangible Breakthroughs • Rapid Results: AI has dramatically accelerated the drug discovery process, screening millions of compounds in days instead of years. • Novel Discoveries: Machine learning algorithms have designed entirely new molecules with potential therapeutic properties. ➡️Real-World Impact • COVID-19 Response: AI tools played a crucial role in rapidly identifying potential treatments and vaccine candidates during the pandemic. • Repurposing Existing Drugs: AI has successfully found new applications for approved medications, saving time and resources. ➡️Beyond Speculation • Practical Applications: Unlike speculative AI hype, drug discovery showcases AI's concrete, life-saving potential. • Industry Adoption: Major pharmaceutical companies are increasingly integrating AI into their R&D processes, validating its effectiveness. This progress in drug research demonstrates that AI is not just buzzwords but a powerful tool delivering tangible results in one of the most critical fields of science. What's your take on how AI is reshaping the pharmaceutical industry? How do you think this impacts public perception of AI's potential?

19

10 Comments

The Reality of #AI and Biorisk "We find that existing studies around AI-related biorisk are nascent, often speculative in nature, or limited in terms of their methodological maturity and transparency." ~ Sara Hooker et al. https://lnkd.in/guBHFEEt #GenerativeAI

5