biochemistry

# Biochemistry ## What I Do I provide comprehensive biochemistry tools including enzyme kinetics, metabolic pathways, protein structure analysis, nucleic acid biochemistry, lipid chemistry, and molecular biology calculations for life science applications. ## When to Use Me - Enzyme kinetics analysis - Metabolic pathway modeling - Protein structure prediction - DNA/RNA calculations - Ligand binding analysis - Metabolic engineering ## Core Concepts - **Enzyme Kinetics**: Michaelis-Menten, Lineweaver-Burk - **Metabolic Pathways**: Glycolysis, TCA, oxidative phosphorylation - **Protein Structure**: Primary, secondary, tertiary, quaternary - **Nucleic Acids**: DNA, RNA, transcription, translation - **Thermodynamics**: Gibbs free energy in biological systems - **Ligand Binding**: KD, IC50, Hill equation - **Coenzymes**: NAD+, ATP, Coenzyme A - **Membrane Biology**: Lipid bilayers, transport ## Code Examples ### Enzyme Kinetics ```python import numpy as np from scipy.optimize import curve_fit def michaelis_menten(S, Vmax, Km): return Vmax * S / (Km + S) def lineweaver_burk_linear(S, v): return 1/v, 1/S def inhibition_types(Km_app, Vmax_app, type_name): types = { 'competitive': {'Km': 'increased', 'Vmax': 'unchanged'}, 'noncompetitive': {'Km': 'unchanged', 'Vmax': 'decreased'}, 'uncompetitive': {'Km': 'decreased', 'Vmax': 'decreased'}, 'mixed': {'Km': 'varied', 'Vmax': 'decreased'} } return types.get(type_name, {'Km': 'unknown', 'Vmax': 'unknown'}) S_data = np.array([0.5, 1.0, 2.5, 5.0, 10.0]) v_data = np.array([12, 20, 30, 38, 42]) Vmax, Km = curve_fit(michaelis_menten, S_data, v_data, p0=[50, 2])[0] print(f"Vmax: {Vmax:.2f} μmol/min, Km: {Km:.2f} mM") kcat = Vmax / 0.001 # if [E] = 1 μM print(f"kcat: {kcat:.2f} s⁻¹") ``` ### Protein Calculations ```python AMINO_ACID_MASS = { 'A': 89, 'R': 174, 'N': 132, 'D': 133, 'C': 121, 'E': 147, 'Q': 146, 'G': 75, 'H': 155, 'I': 131, 'L': 131, 'K': 146, 'M': 149, 'F': 165, 'P': 115, 'S': 105, 'T': 119, 'W': 204, 'Y': 181, 'V': 117 } def protein_molecular_weight(sequence): water_loss = 18.015 * (len(sequence) - 1) mass = sum(AMINO_ACID_MID.get(aa, 0) for aa in sequence) + 1.008 return mass - water_loss / 1000 def calculate_extinction_coefficient(sequence, wavelength=280): W = sequence.count('W') Y = sequence.count('Y') C = sequence.count('C') // 2 return 1490 * W + 550 * Y + 125 * C def predict_isoelectric_point(sequence): pKa = {'D': 3.9, 'E': 4.3, 'C': 8.3, 'Y': 10.1, 'H': 6.0, 'K': 10.5, 'R': 12.5} charges = [] for aa in sequence: if aa in ['D', 'E']: pH = pKa.get(aa, 4.0) elif aa in ['K', 'R']: pH = pKa.get(aa, 11.0) elif aa == 'H': pH = pKa.get(aa, 6.0) else: pH = 7.0 charges.append(pH) return np.median(charges) if charges else 7.0 sequence = "MSEQKQUENCE" print(f"MW: {protein_molecular_weight(sequence):.2f} kDa") print(f"ε280: {calculate_extinction_coefficient(sequence)} M⁻¹cm⁻¹") ``` ### DNA/RNA Calculations ```python from collections import Counter DNA_COMPLEMENT = {'A': 'T', 'T': 'A', 'G': 'C', 'C': 'G'} RNA_COMPLEMENT = {'A': 'U', 'U': 'A', 'G': 'C', 'C': 'G'} def gc_content(sequence): gc = sequence.count('G') + sequence.count('C') return gc / len(sequence) * 100 def melting_temperature(sequence): if len(sequence) < 14: return 2 * (sequence.count('A') + sequence.count('T')) + 4 * (sequence.count('G') + sequence.count('C')) return 64.9 + 41 * (gc_content(sequence) - 16.4) / len(sequence) def reverse_complement(sequence, dna=True): complement = DNA_COMPLEMENT if dna else RNA_COMPLEMENT return ''.join(complement.get(base, base) for base in reversed(sequence)) dna = "ATGCGCTA" print(f"GC content: {gc_content(dna):.1f}%") print(f"Tm: {melting_temperature(dna):.1f}°C") print(f"Reverse complement: {reverse_complement(dna)}") ``` ### Metabolic Calculations ```python ATP_YIELD = { 'glycolysis': 2, 'pyruvate_to_acetyl_CoA': 0, 'citric_acid_cycle': 2, 'oxidative_phosphorylation': 26 } def calculate_atp_yield(glucose=1): yield_dict = ATP_YIELD.copy() yield_dict['oxidative_phosphorylation'] *= 2.5 * glucose yield_dict['total'] = sum(yield_dict.values()) return yield_dict def nadh_to_atp_conversion(nadh, proton_pump_efficiency=3): return nadh * 2.5 * proton_pump_efficiency def calculate_gibbs_free_energy(deltaG0, Q, T=298): R = 8.314 return deltaG0 + R * T * np.log(Q) print(f"ATP from glucose: {calculate_atp_yield()['total']:.0f}") ``` ### Ligand Binding Analysis ```python def hill_equation(L, KD, n, Bmax): return Bmax * L**n / (KD + L**n) def ic50_from_kd(KD, inhibitor_conc, Ki): return Ki * (1 + inhibitor_conc / KD) def schild_receptor_agonist(EC50, antagonist_conc, dose_ratio): return antagonist_conc / (dose_ratio - 1) def binding_free_energy(KD): R = 8.314 T = 298 return -R * T * np.log(KD * 1e-6) / 1000 # kcal/mol KD = 1e-9 # 1 nM L = np.logspace(-12, -6, 100) B = hill_equation(L, KD, 1, 100) print(f"Binding free energy: {binding_free_energy(KD):.2f} kcal/mol") ``` ## Best Practices 1. **Enzyme Assays**: Measure initial velocities 2. **Protein Purity**: Use multiple methods for confirmation 3. **Buffer Conditions**: Consider pH and ionic strength 4. **Temperature Control**: Biological systems are temperature sensitive 5. **Controls**: Always include appropriate controls ## Common Patterns ```python # Bradford protein assay def bradford_concentration(od595, intercept=0.045, slope=0.62): return (od595 - intercept) / slope # Circular dichroism secondary structure def estimate_alpha_helix(cd_signal_222, reference=-33000): return cd_signal_222 / reference * 100 # Restriction digest def predict_digest_pattern(sequence, enzyme_sites): sites = [] for site in enzyme_sites: sites.extend([m.start() for m in re.finditer(site, sequence)]) return sorted(set([0] + [s + len(site) for s in sites for site in enzyme_sites if site in sequence])) ``` ## Core Competencies 1. Enzyme kinetics and inhibition 2. Protein structure and properties 3. Nucleic acid calculations 4. Metabolic pathway analysis 5. Ligand binding thermodynamics