Steven M. Muskal, Ph.D.

The two overlays show the same pair and deliberately disagree, which is the point of putting them next to each other.

ChIP searches reaction routes rather than molecules. A gene is a synthesis route: it names the transforms and the catalogue blocks fed into them, is enumerated into the products it would make, and those products are built in 3D and fingerprinted against the reference with PharmPrint-style 3D pharmacophore fingerprints. Because every candidate is by construction the product of real reactions on orderable material, the output is synthesisable by design. The two easy alternatives both fail here: screening a catalogue by 2D similarity returns analogues, which is the thing being avoided, and generative models return molecules that may not be makeable.

The published example takes Orforglipron, Lilly's oral GLP-1 receptor agonist approved in April 2026, as its reference. Fitness was pharmacophore similarity and nothing else; 2D Morgan similarity was recorded for every product but never entered selection. The winning design matches the reference at 0.838 pharmacophore similarity while sharing only 0.138 two-dimensional similarity with it. Across the 115 retained designs pharmacophore similarity ranges from 0.824 to 0.838 while Morgan similarity stays between 0.081 and 0.174, and that 2D value stayed low on its own without ever being penalised. These are not Orforglipron analogues; they are structurally distinct scaffolds presenting a similar arrangement of features in space.

Limitations. This is a computational simulation. The campaign used no potency model and no target structure, and its objective was pharmacophore similarity to a reference molecule and nothing else. No biological activity is claimed or predicted anywhere in it. Read it as a search result, not as a biological claim. It is a different demonstration from the Kinase Foundation Model, where the objective was predicted potency.

Medical education

Study with Hannah: Medical School Study Cards

Searchable medical school study cards with USMLE prep notes, medical images, and an AI study tutor.

Request Access

Tens of thousands of medical-school flashcards and lecture notes across anatomy, physiology, pathology, pharmacology, and immunology, with keyword plus semantic image search. Hannah keeps the archive current throughout her studies; the public landing page introduces the system, while the study content is access-controlled.

Counts update from the Study with Hannah public archive feed.

AI-Steve: Personal Research & Coaching Assistant

My daily companion for research recall, journaling, and family knowledge capture. AI-Steve pulls in emails and attachments, calendar events, to-do items, iMessages, Mac Photos plus curated imports, chat sessions, Q&A, and Socratic pairs extracted from mail, embedding them into PostgreSQL so Claude can respond with grounded context. Search Content, sentiment, and health intelligence fuel daily reflections (including 1, 3, 5, 7, and 10-year lookbacks) plus end-of-week recaps that project the week ahead. Built entirely through natural-language coding (speaking into Wispr Flow driving agentic CLIs like Droid, Claude Code, Codex, Gemini CLI) and able to handle small coding or automation projects on demand, similar to how I built Toast apps and AI-Dad.

Features at a glance

PostgreSQL + embeddings Claude reasoning Multi-source ingest Chat history memory

Chat UI grounded in embeddings and transcripts with instant access to images and stats.

Multi-year reflections surfaced daily (1, 3, 5, 7, 10 years ago).

Live mix of emails, Q&A, photos, attachments, calendar, to-dos, iMessages, and curated imports.

User-modifiable RAG weight control.

AI-Steve Architecture →

AI-Dad: Preserving Legacy Through Conversational AI

An innovative application of RAG (Retrieval-Augmented Generation) technology to create an interactive AI assistant embodying 60+ years of intellectual property legal expertise and family wisdom. Built using natural language programming and Claude Code, this deeply personal project preserves my father's extensive knowledge in IP law alongside decades of family history and personal interactions, making his guidance on both legal and life matters accessible for future generations.

Legal Expertise

Family Wisdom

AI-Dad: Always here for you - Combining decades of legal expertise with heartfelt family wisdom

Explore AI-Dad Project →

Image Explorer: Visual Memory Engine

A CLIP (Contrastive Language-Image Pre-training) + pgvector-powered explorer for my photo archives. Nightly clustering keeps similar sets together so I can browse clusters, select many images at once, and annotate entire groups without touching each file. I can also annotate straight from similarity search, including sub-images and video frames, accelerating how visuals become structured context for AI-Steve’s RAG. Built by speaking English into Wispr Flow to orchestrate Droid, Claude Code, Codex, Gemini CLI, similar to Toast apps, AI-Dad, and AI-Steve.

What it does

• 🔍 Similarity search with thresholds
• 🗂️ Nightly clustering; annotate whole sets
• 📝 Inline annotations saved to DB + JSON
• 🖼️ Finder deep links for fast triage

Bulk similarity hits with instant “Annotate Selected” to speed group labeling.

Annotation modal on similarity results to label entire groups in one pass.

Face extraction and clustering from Mac Photos and video frames, enabling rapid tagging and propagation.

Robust matching across sunglasses, hats, and lighting to keep face IDs consistent.

AI-Steve Code Directives: Domain-Specific Auto-Coding

Added into my AI-Steve infrastructure is the ability to auto-code projects in a domain-specific way using simple natural language project descriptions on top of Droid, Claude, and/or Codex. What brought it to the next level is using AI-Steve’s RAG system to wrap a project direction in my voice - imagine enabling all your coders to code given their own past projects and insights. It is akin to saying: build this new OS in the voice of Linus Torvalds.

Domain-specific guidance + RAG voice overlay drive code generation, review loops, and polished reporting.

Key elements: domain prompts, RAG context, peer review, self-healing retries, and packaged reports.

Designed to make project requests feel like they were built by the same voice that created the original system.

Food Health Scan

Food Health Scan turns meals into structured, reviewable nutrition data with photo capture, note capture, AI analysis, and fast edit flows. It is the practical product expression of the March 8, 2026 Renaissance Circle piece, Food Is Medicine. But First It Has to Become Data.

Current Demo

The existing walkthrough shows the current meal-to-data capture flow on the live app.

New V4 Demo

The newer V4 video adds another quick look at the updated Food Health Scan experience.

▶

New Food Health TxD - Spot the meals that spike you

The diabetes-aware companion to Food Health Scan. AI carb and macro estimation paired with continuous glucose monitor (CGM) data, so every meal links directly to the glucose response it produced. Built for people with Type 1, Type 2, and prediabetes who want to see what their food is actually doing - and for the wider 88 to 93 percent of American adults living with at least one metabolic risk factor.

What you see on the right

• Today view: glucose (mg/dL) plus carbs logged at meal times
• Scan Menu, Scan Food, and Log Glucose as one-tap actions
• Per-meal detail with CGM reading, macros, and timing
• Apple Health sync for hands-off CGM ingestion
• Showcase view that includes TxD plates alongside Food Health Scan

Companion essay (May 8, 2026): The Metabolic Crisis Is Not a News Story on Substack or Medium.

Open Food Health TxD →

Share Health: App Store Export Companion

Share Health is the companion iOS app that makes consistent, time‑aligned Apple Health exports simple. It packages daily signals for longitudinal analysis with clean CSV outputs, optional face imagery, and on‑device Face → Health modeling.

Face → Health modeling + export workflows (3×2 layout).

App Store → More Details → GitHub Source →

Apple Health Integration: Quantified Sleep + Recovery

Daily Apple Health exports power a dedicated analytics pipeline inside AI-Steve. Correlation engines, lag analysis, and a sleep-concentration model surface the behaviors most tied to deep sleep and REM recovery. The resulting plots are stored as visual artifacts so they’re searchable and reviewable alongside photos and other memory assets.

Full correlation heatmap across Apple Health metrics.

Sleep-focused correlation matrix highlighting top 30 predictors.

Top 20 features driving sleep concentration prediction.

Top correlates with deep sleep for recovery drivers.

Top correlates with REM sleep for cognitive recovery signals.

Face → Health: Vision as a Longitudinal Signal

Face → Health treats the face as a sensor, not a narrative. Daily images support both retrospective (last night) and predictive (tonight) sleep modeling with strict temporal alignment. Health-specific vision analysis, dual embeddings, and a materialized ML view make this a defensible, longitudinal wellness signal.

Temporal self‑awareness: face today → sleep tonight (recorded tomorrow).

CT Viewer Story: DICOM → Interactive 3D

A real-world build story: I received a USB drive full of DICOM CT slices after a root canal, and instead of using a PC-only viewer, I described the problem to an AI coding assistant and walked away. Minutes later, I had a working browser-based viewer with 3D rotation, cross-sectional MPR views, and contrast controls.

Interactive 3D jaw reconstruction with axial, sagittal, and coronal slice navigation.

Screening is a prioritisation problem: a project needs to know which compound to make next and which kinase a series is likely to hit, and an ordering does not require predicting a potency first. Version 2 puts the entire question into one input row and returns the probability that one side wins. A protein sequence is encoded by ESM2 into 480 numbers, a compound becomes a 1,024-bit Morgan count fingerprint plus 14 descriptors, and neither half needs a structure, a docked pose, or a binding-site definition. Everything is trained on the Kinase Knowledgebase and tested on ChEMBL comparisons the models never saw.

Version 2, the current release: two models, each trained directly on ordered comparisons.

Potency ranking · LigASeqLigB

Which of two compounds binds this kinase more tightly?

0.690 accuracy across 1,836,100 ChEMBL comparisons on 477 targets, rising to 0.842 on the fifth of comparisons made at prediction strength 0.70 and above.

Selectivity · SeqALigSeqB

Which of two kinases does this compound prefer?

75.3% accuracy across 3,137,588 unseen ChEMBL comparisons, rising to 92.3% on the 36.8% of the set predicted at 0.70 and above. This is the question a per-target scorer structurally cannot answer.

Why the comparison lives inside the row: predicting a potency for each side and subtracting only works if both predictions share a scale, and per-target scores do not, so a difference between them reports assay scale as if it were selectivity. Training on the ordered pair removes the intermediate quantity altogether. The models rank; they do not estimate a potency, and there is no predicted IC₅₀ to put in a table. Predictions are for research use and are not a substitute for measurement.

Both version 2 models also run locally and offline with nothing transmitted, which is the practical requirement when the compounds are unpublished. Version 1, the original pointwise pIC₅₀ scorer this grew out of, remains published in full on the site. For the companion demonstration that optimises pharmacophore similarity instead of predicted potency, see ChIP.

AI-Driven Drug Discovery

Developing machine learning models for predicting drug-target interactions and optimizing lead compounds to accelerate the path from discovery to clinical trials.

40+ years of neural network and AI research journey

Polypharmacophore / PharmPrint

Multi-conformer 3-point pharmacophore fingerprinting technology for AI-driven virtual screening, food-based drug discovery, and cross-species conservation analysis. Originally published in J. Chem. Inf. Comput. Sci. (1999, 2000) and reborn for AI-era natural-product matching.

Triplet-based pharmacophore matching across drug compounds, natural products, and target binding sites.

The same fingerprint is the objective function inside ChIP, which searches reaction routes for purchasable molecules that match a reference drug's pharmacophore on an unrelated scaffold. Because the exact ensemble fingerprint costs about ten seconds per compound, a neural surrogate now predicts the full 10,560 bits straight from a SMILES at 0.911 Pearson on pairwise similarity, roughly 30,000 times faster, which is what lets a search range over far more chemical space.

🔬 Drug to Table Project (Finding Drugs Hidden in Your Food)

🥂 Toast Our Friend - A New Way to Celebrate

While the world focuses on self-promotion, we're building a place to honor the people around you. Share stories, create tributes, and celebrate the lives that touch yours.

Each app focuses on different communities and ways to celebrate friendships through meaningful connections.

Scott's Circle

A tribute to Scott Miller - celebrating friendship, music, and memories through shared connections.

toastscott.com

Mike's Circle

Honoring Mike Szwajkowski - connecting people through music, friendship, and shared experiences.

toastmike.com

Tom's Circle

Honoring Tom Shearer - celebrating a gentle soul who brought light, laughter, and love to all who knew him.

toasttom.com

Coop's Circle

Celebrating Steve Cooper - building community through shared memories and connections.

toastourfriend.com/coop

SHK Circle

Sung-Hou Kim lab alumni, colleagues, and friends reconnecting through shared stories and appreciation.

toastshk.com

SHK Reunion Stories

First-hand stories and anecdotes from Sung-Hou Kim lab alumni at Duke and UC Berkeley, written after the 2026 reunion.

reunion.toastshk.com

Toast Steve

Friends, colleagues, and family sharing stories, reflections, and appreciation for Steve.

toaststeve.com