appendix-d

Appendix D. Technical Deep Dive into Protein Structure Prediction

This appendix provides comprehensive technical details for readers who want to reproduce, extend, or deeply audit the approaches described in Chapter 12. Each section is designed to be consulted independently as a reference.

D.1 Protein Biophysics and Chemistry

This section expands on the structural biology concepts introduced in Chapter 12, providing the detailed chemical and physical foundations necessary for a deep understanding of protein folding.

D.1.1 Amino Acid Chemistry

Just twenty standard AAs serve as building blocks for protein diversity. Each AA shares a common backbone structure made of N-Cα-C atoms: a central carbon atom (the alpha carbon, denoted Cα) bonded to an amino group (NH2), a carboxyl group (COOH), and a hydrogen atom. What makes each AA unique is the fourth group attached to the central alpha carbon, called the sidechain or R-group.

During protein synthesis, AAs link together through peptide bonds that connect the carboxyl group of one AA to the amino group of the next. This creates a repeating backbone of N–Cα–C atoms running the length of the protein, with sidechains branching off from each alpha carbon. The chemical properties of sidechains drive folding.

D.1.2 Hydrogen Bonding Mechanics

D.1.3 Torsion Angles and the Ramachandran Plot

D.1.4 The Physics of Folding

D.2 SimpleFold End-to-End Example Details

D.2.1 Protein Representation Formats

D.2.2 Stage 1: Configuration

D.2.3 Stage 2: Loading Pretrained Models

D.2.4 Stage 3: Inference Pipeline

D.2.5 Stage 5: Executing Protein Structure Prediction

D.2.6 Alignment-based Validation

D.2.7 Metrics, Metrics, Metrics

D.2.8 Understanding CAMEO and CASP Benchmarks

D.3 Training Protein Language Models

D.3.1 Tokenization: Converting Proteins to Numbers

D.3.2 Scaled Dot-Product Attention

D.3.3 Encoding Position Information

D.3.4 Encoder Layer: Attention + Feed-Forward

D.3.5 Training our Protein Language Model

D.3.6 When to Train Your Own Model

D.4 ESM-2 Case Study: Predicting Mutation Effects

D.5 Advanced SimpleFold Architecture

D.5.1 Invoking the Bitter Lesson in Structural Biology

D.5.2 Flow Matching: From Noise to Native Structure

D.6 Timestep Conditioning with Diffusion Transformer Blocks

D.6.1 SwiGLU Activation Functions

D.6.2 Rotary Position Embeddings

D.6.3 QK Normalization

D.6.4 Diffusion Transformer (DiT) Blocks

D.7 Deconstructing SimpleFold: Encoder-Trunk-Decoder