Spaces:
Sleeping
Sleeping
| <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <title>Biopesticide-AI Slides</title> | |
| <link href="https://fonts.googleapis.com/css2?family=Fraunces:opsz,wght@9..144,400;9..144,500;9..144,600;9..144,700;9..144,800&family=Inter:wght@300;400;500;600;700&family=JetBrains+Mono:wght@400;500;600&display=swap" rel="stylesheet"> | |
| <style> | |
| @page { size: 1280px 720px; margin: 0; } | |
| * { box-sizing: border-box; margin: 0; padding: 0; } | |
| html, body { | |
| width: 1280px; | |
| height: 720px; | |
| margin: 0; | |
| padding: 0; | |
| background: #faf8f3; | |
| font-family: 'Inter', -apple-system, sans-serif; | |
| color: #2d2d2d; | |
| -webkit-font-smoothing: antialiased; | |
| } | |
| .slide { | |
| width: 1280px; | |
| height: 720px; | |
| position: relative; | |
| overflow: hidden; | |
| page-break-after: always; | |
| background: #faf8f3; | |
| } | |
| .slide:last-child { page-break-after: auto; } | |
| /* Common elements */ | |
| .slide-num { | |
| position: absolute; | |
| bottom: 32px; | |
| right: 48px; | |
| font-family: 'Fraunces', serif; | |
| font-size: 14px; | |
| color: #6b7280; | |
| font-weight: 500; | |
| } | |
| .slide-footer { | |
| position: absolute; | |
| bottom: 32px; | |
| left: 48px; | |
| font-size: 11px; | |
| color: #6b7280; | |
| letter-spacing: 0.5px; | |
| text-transform: uppercase; | |
| } | |
| .brand-mark { | |
| position: absolute; | |
| top: 32px; | |
| left: 48px; | |
| display: flex; | |
| align-items: center; | |
| gap: 10px; | |
| } | |
| .brand-dot { | |
| width: 24px; | |
| height: 24px; | |
| border-radius: 50%; | |
| background: linear-gradient(135deg, #1a3c34 0%, #7fb069 100%); | |
| } | |
| .brand-name { | |
| font-family: 'Fraunces', serif; | |
| font-size: 16px; | |
| font-weight: 700; | |
| color: #1a3c34; | |
| } | |
| .brand-accent { color: #7fb069; } | |
| /* Slide 1: Cover */ | |
| .cover { | |
| background: linear-gradient(135deg, #1a3c34 0%, #2d5a4a 50%, #1a3c34 100%); | |
| color: white; | |
| display: flex; | |
| flex-direction: column; | |
| justify-content: center; | |
| padding: 0 100px; | |
| } | |
| .cover-badge { | |
| display: inline-flex; | |
| align-items: center; | |
| gap: 8px; | |
| padding: 6px 16px; | |
| border-radius: 20px; | |
| background: rgba(127, 176, 105, 0.2); | |
| border: 1px solid rgba(127, 176, 105, 0.4); | |
| font-size: 12px; | |
| font-weight: 500; | |
| color: #a8d5ba; | |
| margin-bottom: 32px; | |
| width: fit-content; | |
| } | |
| .cover-badge-dot { | |
| width: 6px; height: 6px; | |
| border-radius: 50%; | |
| background: #7fb069; | |
| } | |
| .cover h1 { | |
| font-family: 'Fraunces', serif; | |
| font-size: 64px; | |
| font-weight: 700; | |
| line-height: 1.1; | |
| letter-spacing: -1.5px; | |
| margin-bottom: 24px; | |
| } | |
| .cover h1 .accent { | |
| font-style: italic; | |
| color: #7fb069; | |
| font-weight: 600; | |
| } | |
| .cover p { | |
| font-size: 20px; | |
| line-height: 1.5; | |
| opacity: 0.85; | |
| max-width: 800px; | |
| margin-bottom: 48px; | |
| } | |
| .cover-meta { | |
| display: flex; | |
| gap: 48px; | |
| font-size: 14px; | |
| opacity: 0.7; | |
| } | |
| .cover-meta div { display: flex; flex-direction: column; gap: 4px; } | |
| .cover-meta .label { font-size: 10px; text-transform: uppercase; letter-spacing: 1px; opacity: 0.6; } | |
| .cover-meta .value { font-size: 16px; font-weight: 600; } | |
| /* Slide 2: Problem */ | |
| .problem { padding: 80px 100px; display: flex; flex-direction: column; } | |
| .slide-title { | |
| font-family: 'Fraunces', serif; | |
| font-size: 36px; | |
| font-weight: 600; | |
| color: #1a3c34; | |
| margin-bottom: 8px; | |
| letter-spacing: -0.5px; | |
| } | |
| .slide-subtitle { | |
| font-size: 16px; | |
| color: #6b7280; | |
| margin-bottom: 48px; | |
| } | |
| .problem-grid { | |
| display: grid; | |
| grid-template-columns: 1fr 1fr 1fr; | |
| gap: 32px; | |
| flex: 1; | |
| } | |
| .problem-card { | |
| background: white; | |
| border-radius: 12px; | |
| padding: 32px; | |
| border-top: 4px solid #ba5a6a; | |
| box-shadow: 0 2px 8px rgba(0,0,0,0.04); | |
| } | |
| .problem-card h3 { | |
| font-family: 'Fraunces', serif; | |
| font-size: 22px; | |
| color: #1a3c34; | |
| margin-bottom: 12px; | |
| } | |
| .problem-card .stat { | |
| font-family: 'Fraunces', serif; | |
| font-size: 48px; | |
| font-weight: 700; | |
| color: #ba5a6a; | |
| line-height: 1; | |
| margin-bottom: 8px; | |
| } | |
| .problem-card .stat-label { | |
| font-size: 12px; | |
| text-transform: uppercase; | |
| letter-spacing: 0.5px; | |
| color: #6b7280; | |
| margin-bottom: 16px; | |
| } | |
| .problem-card p { | |
| font-size: 14px; | |
| line-height: 1.6; | |
| color: #4b5563; | |
| } | |
| /* Slide 3: Solution */ | |
| .solution { padding: 80px 100px; display: flex; flex-direction: column; } | |
| .solution-hero { | |
| display: flex; | |
| align-items: center; | |
| gap: 48px; | |
| margin-bottom: 40px; | |
| } | |
| .solution-hero-text { flex: 1; } | |
| .solution-hero-text h2 { | |
| font-family: 'Fraunces', serif; | |
| font-size: 42px; | |
| font-weight: 600; | |
| color: #1a3c34; | |
| line-height: 1.2; | |
| margin-bottom: 16px; | |
| } | |
| .solution-hero-text p { | |
| font-size: 16px; | |
| line-height: 1.6; | |
| color: #4b5563; | |
| } | |
| .solution-stats { | |
| display: grid; | |
| grid-template-columns: repeat(4, 1fr); | |
| gap: 24px; | |
| margin-top: 32px; | |
| } | |
| .solution-stat { | |
| text-align: center; | |
| background: white; | |
| border-radius: 10px; | |
| padding: 24px 16px; | |
| border: 1px solid #e5e7eb; | |
| } | |
| .solution-stat .num { | |
| font-family: 'Fraunces', serif; | |
| font-size: 36px; | |
| font-weight: 700; | |
| color: #7fb069; | |
| line-height: 1; | |
| } | |
| .solution-stat .lbl { | |
| font-size: 11px; | |
| text-transform: uppercase; | |
| letter-spacing: 0.5px; | |
| color: #6b7280; | |
| margin-top: 6px; | |
| } | |
| /* Slide 4: Pipeline */ | |
| .pipeline { padding: 80px 100px; display: flex; flex-direction: column; } | |
| .pipeline-grid { | |
| display: grid; | |
| grid-template-columns: repeat(3, 1fr); | |
| grid-template-rows: 1fr 1fr; | |
| gap: 20px; | |
| flex: 1; | |
| } | |
| .pipeline-step { | |
| background: white; | |
| border-radius: 10px; | |
| padding: 24px; | |
| border-left: 4px solid #7fb069; | |
| display: flex; | |
| flex-direction: column; | |
| } | |
| .pipeline-step .num { | |
| font-family: 'Fraunces', serif; | |
| font-size: 28px; | |
| font-weight: 700; | |
| color: #7fb069; | |
| line-height: 1; | |
| margin-bottom: 8px; | |
| } | |
| .pipeline-step h4 { | |
| font-family: 'Fraunces', serif; | |
| font-size: 16px; | |
| color: #1a3c34; | |
| margin-bottom: 6px; | |
| } | |
| .pipeline-step p { | |
| font-size: 12px; | |
| line-height: 1.5; | |
| color: #6b7280; | |
| } | |
| /* Slide 5: Architecture */ | |
| .architecture { padding: 80px 100px; display: flex; flex-direction: column; } | |
| .arch-content { display: flex; gap: 48px; flex: 1; } | |
| .arch-diagram { | |
| flex: 1.2; | |
| background: white; | |
| border-radius: 12px; | |
| padding: 32px; | |
| border: 1px solid #e5e7eb; | |
| } | |
| .arch-diagram .flow { | |
| display: flex; | |
| flex-direction: column; | |
| gap: 12px; | |
| } | |
| .arch-diagram .flow-row { | |
| display: flex; | |
| align-items: center; | |
| gap: 12px; | |
| } | |
| .arch-box { | |
| padding: 10px 16px; | |
| border-radius: 8px; | |
| font-size: 12px; | |
| font-weight: 600; | |
| text-align: center; | |
| color: white; | |
| } | |
| .arch-box.green { background: #7fb069; } | |
| .arch-box.dark { background: #1a3c34; } | |
| .arch-box.accent { background: #2f86b2; } | |
| .arch-box.warm { background: #ba5a6a; } | |
| .arch-arrow { color: #6b7280; font-size: 16px; } | |
| .arch-stack { | |
| flex: 1; | |
| display: flex; | |
| flex-direction: column; | |
| gap: 8px; | |
| } | |
| .arch-stack h4 { | |
| font-family: 'Fraunces', serif; | |
| font-size: 18px; | |
| color: #1a3c34; | |
| margin-bottom: 12px; | |
| } | |
| .arch-stack-item { | |
| display: flex; | |
| justify-content: space-between; | |
| padding: 8px 12px; | |
| background: white; | |
| border-radius: 6px; | |
| font-size: 13px; | |
| border: 1px solid #e5e7eb; | |
| } | |
| .arch-stack-item .tech { font-weight: 600; color: #1a3c34; } | |
| .arch-stack-item .role { color: #6b7280; } | |
| /* Slide 6: Species */ | |
| .species { padding: 80px 100px; display: flex; flex-direction: column; } | |
| .species-cols { display: flex; gap: 48px; flex: 1; } | |
| .species-col { flex: 1; } | |
| .species-col h3 { | |
| font-family: 'Fraunces', serif; | |
| font-size: 20px; | |
| color: #1a3c34; | |
| margin-bottom: 16px; | |
| padding-bottom: 8px; | |
| border-bottom: 2px solid #7fb069; | |
| } | |
| .species-list { | |
| display: grid; | |
| grid-template-columns: 1fr 1fr; | |
| gap: 8px; | |
| } | |
| .species-item { | |
| background: white; | |
| border-radius: 6px; | |
| padding: 10px 14px; | |
| font-size: 12px; | |
| border: 1px solid #e5e7eb; | |
| } | |
| .species-item .common { font-weight: 600; color: #1a3c34; } | |
| .species-item .sci { color: #6b7280; font-style: italic; font-size: 11px; } | |
| /* Slide 7: Demo / Results */ | |
| .demo { padding: 80px 100px; display: flex; flex-direction: column; } | |
| .demo-content { display: flex; gap: 48px; flex: 1; } | |
| .demo-left { flex: 1; } | |
| .demo-right { flex: 1; } | |
| .demo-left h3, .demo-right h3 { | |
| font-family: 'Fraunces', serif; | |
| font-size: 20px; | |
| color: #1a3c34; | |
| margin-bottom: 16px; | |
| } | |
| .demo-candidate { | |
| background: white; | |
| border-radius: 8px; | |
| padding: 14px 18px; | |
| margin-bottom: 8px; | |
| border-left: 4px solid #7fb069; | |
| display: flex; | |
| justify-content: space-between; | |
| align-items: center; | |
| } | |
| .demo-candidate .seq { | |
| font-family: 'JetBrains Mono', monospace; | |
| font-size: 13px; | |
| font-weight: 600; | |
| color: #1a3c34; | |
| } | |
| .demo-candidate .metrics { | |
| display: flex; | |
| gap: 16px; | |
| font-size: 11px; | |
| color: #6b7280; | |
| } | |
| .demo-candidate .metrics .val { font-weight: 700; color: #1a3c34; } | |
| .demo-sim { | |
| background: white; | |
| border-radius: 8px; | |
| padding: 20px; | |
| border: 1px solid #e5e7eb; | |
| } | |
| .demo-sim h4 { | |
| font-family: 'Fraunces', serif; | |
| font-size: 14px; | |
| color: #1a3c34; | |
| margin-bottom: 12px; | |
| } | |
| .sim-row { | |
| display: flex; | |
| justify-content: space-between; | |
| padding: 6px 0; | |
| border-bottom: 1px solid #f3f4f6; | |
| font-size: 12px; | |
| } | |
| .sim-row:last-child { border-bottom: none; } | |
| .sim-row .label { color: #6b7280; } | |
| .sim-row .val { font-weight: 600; color: #1a3c34; } | |
| /* Slide 8: Wet-lab simulation */ | |
| .simulation { padding: 80px 100px; display: flex; flex-direction: column; } | |
| .sim-stages { | |
| display: grid; | |
| grid-template-columns: repeat(3, 1fr); | |
| gap: 16px; | |
| flex: 1; | |
| } | |
| .sim-stage { | |
| background: white; | |
| border-radius: 10px; | |
| padding: 20px; | |
| border-top: 4px solid #7fb069; | |
| display: flex; | |
| flex-direction: column; | |
| } | |
| .sim-stage .stage-num { | |
| font-family: 'Fraunces', serif; | |
| font-size: 14px; | |
| font-weight: 700; | |
| color: #7fb069; | |
| text-transform: uppercase; | |
| letter-spacing: 1px; | |
| margin-bottom: 8px; | |
| } | |
| .sim-stage h4 { | |
| font-family: 'Fraunces', serif; | |
| font-size: 16px; | |
| color: #1a3c34; | |
| margin-bottom: 6px; | |
| } | |
| .sim-stage p { | |
| font-size: 11px; | |
| line-height: 1.5; | |
| color: #6b7280; | |
| } | |
| .sim-stage .eff { | |
| margin-top: auto; | |
| padding-top: 8px; | |
| font-family: 'Fraunces', serif; | |
| font-size: 24px; | |
| font-weight: 700; | |
| color: #1a3c34; | |
| } | |
| /* Slide 9: Production upgrade */ | |
| .production { padding: 80px 100px; display: flex; flex-direction: column; } | |
| .prod-table { | |
| width: 100%; | |
| border-collapse: collapse; | |
| margin-top: 24px; | |
| background: white; | |
| border-radius: 12px; | |
| overflow: hidden; | |
| box-shadow: 0 2px 8px rgba(0,0,0,0.04); | |
| } | |
| .prod-table th, .prod-table td { | |
| padding: 14px 20px; | |
| text-align: left; | |
| font-size: 14px; | |
| border-bottom: 1px solid #e5e7eb; | |
| } | |
| .prod-table th { | |
| background: #1a3c34; | |
| color: white; | |
| font-weight: 600; | |
| font-size: 12px; | |
| text-transform: uppercase; | |
| letter-spacing: 0.5px; | |
| } | |
| .prod-table td:first-child { font-weight: 600; color: #1a3c34; } | |
| .prod-table .demo-col { color: #6b7280; } | |
| .prod-table .prod-col { color: #7fb069; font-weight: 600; } | |
| /* Slide 10: Business case */ | |
| .business { padding: 80px 100px; display: flex; flex-direction: column; } | |
| .business-grid { | |
| display: grid; | |
| grid-template-columns: 1fr 1fr; | |
| gap: 48px; | |
| flex: 1; | |
| } | |
| .business-card { | |
| background: white; | |
| border-radius: 12px; | |
| padding: 32px; | |
| border: 1px solid #e5e7eb; | |
| } | |
| .business-card h3 { | |
| font-family: 'Fraunces', serif; | |
| font-size: 22px; | |
| color: #1a3c34; | |
| margin-bottom: 20px; | |
| padding-bottom: 12px; | |
| border-bottom: 2px solid #7fb069; | |
| } | |
| .business-card .market-stat { | |
| margin-bottom: 16px; | |
| } | |
| .business-card .market-stat .num { | |
| font-family: 'Fraunces', serif; | |
| font-size: 36px; | |
| font-weight: 700; | |
| color: #7fb069; | |
| line-height: 1; | |
| } | |
| .business-card .market-stat .lbl { | |
| font-size: 12px; | |
| color: #6b7280; | |
| margin-top: 4px; | |
| } | |
| .business-card .competitor { | |
| display: flex; | |
| justify-content: space-between; | |
| padding: 8px 0; | |
| border-bottom: 1px solid #f3f4f6; | |
| font-size: 13px; | |
| } | |
| .business-card .competitor:last-child { border-bottom: none; } | |
| .business-card .competitor .name { color: #1a3c34; font-weight: 500; } | |
| .business-card .competitor .time { color: #ba5a6a; font-weight: 600; } | |
| .business-card .competitor.us .name { color: #7fb069; font-weight: 700; } | |
| .business-card .competitor.us .time { color: #7fb069; } | |
| /* Slide 11: Roadmap */ | |
| .roadmap { padding: 80px 100px; display: flex; flex-direction: column; } | |
| .roadmap-timeline { | |
| display: flex; | |
| gap: 24px; | |
| flex: 1; | |
| align-items: stretch; | |
| } | |
| .roadmap-phase { | |
| flex: 1; | |
| background: white; | |
| border-radius: 12px; | |
| padding: 28px; | |
| border-top: 4px solid #7fb069; | |
| display: flex; | |
| flex-direction: column; | |
| } | |
| .roadmap-phase .phase-label { | |
| font-family: 'Fraunces', serif; | |
| font-size: 14px; | |
| font-weight: 700; | |
| color: #7fb069; | |
| text-transform: uppercase; | |
| letter-spacing: 1px; | |
| margin-bottom: 8px; | |
| } | |
| .roadmap-phase h4 { | |
| font-family: 'Fraunces', serif; | |
| font-size: 18px; | |
| color: #1a3c34; | |
| margin-bottom: 12px; | |
| } | |
| .roadmap-phase ul { | |
| list-style: none; | |
| padding: 0; | |
| } | |
| .roadmap-phase li { | |
| font-size: 12px; | |
| line-height: 1.6; | |
| color: #4b5563; | |
| padding-left: 16px; | |
| position: relative; | |
| margin-bottom: 6px; | |
| } | |
| .roadmap-phase li::before { | |
| content: ''; | |
| position: absolute; | |
| left: 0; | |
| top: 7px; | |
| width: 6px; | |
| height: 6px; | |
| border-radius: 50%; | |
| background: #7fb069; | |
| } | |
| /* Slide 12: Closing */ | |
| .closing { | |
| background: linear-gradient(135deg, #1a3c34 0%, #2d5a4a 100%); | |
| color: white; | |
| display: flex; | |
| flex-direction: column; | |
| justify-content: center; | |
| align-items: center; | |
| text-align: center; | |
| padding: 0 100px; | |
| } | |
| .closing h1 { | |
| font-family: 'Fraunces', serif; | |
| font-size: 48px; | |
| font-weight: 700; | |
| line-height: 1.2; | |
| margin-bottom: 24px; | |
| letter-spacing: -1px; | |
| } | |
| .closing h1 .accent { | |
| font-style: italic; | |
| color: #7fb069; | |
| } | |
| .closing p { | |
| font-size: 18px; | |
| line-height: 1.5; | |
| opacity: 0.85; | |
| max-width: 700px; | |
| margin-bottom: 40px; | |
| } | |
| .closing-stats { | |
| display: flex; | |
| gap: 48px; | |
| margin-bottom: 48px; | |
| } | |
| .closing-stat { text-align: center; } | |
| .closing-stat .num { | |
| font-family: 'Fraunces', serif; | |
| font-size: 32px; | |
| font-weight: 700; | |
| color: #7fb069; | |
| } | |
| .closing-stat .lbl { | |
| font-size: 11px; | |
| text-transform: uppercase; | |
| letter-spacing: 0.5px; | |
| opacity: 0.7; | |
| margin-top: 4px; | |
| } | |
| .closing-cta { | |
| font-family: 'Fraunces', serif; | |
| font-size: 20px; | |
| font-style: italic; | |
| color: #a8d5ba; | |
| } | |
| </style> | |
| </head> | |
| <body> | |
| <div class="slide cover"> | |
| <div class="cover-badge"><span class="cover-badge-dot"></span>AMD DEVELOPER HACKATHON · UNICORN TRACK</div> | |
| <h1>Designing the future of<br><span class="accent">biopesticides</span></h1> | |
| <p>An AI pipeline that converts a farmer's pest report into ranked, safety-checked dsRNA candidates — in minutes, not months. Powered by local Llama 3.2 3B, PyTorch, and a 14-species safety panel.</p> | |
| <div class="cover-meta"> | |
| <div><span class="label">Team</span><span class="value">Biopesticide-AI</span></div> | |
| <div><span class="label">Date</span><span class="value">June 2026</span></div> | |
| <div><span class="label">License</span><span class="value">MIT</span></div> | |
| <div><span class="label">Compute</span><span class="value">100% Local</span></div> | |
| </div> | |
| </div> | |
| <div class="slide problem"> | |
| <div class="brand-mark"><span class="brand-dot"></span><span class="brand-name">Biopesticide<span class="brand-accent">-AI</span></span></div> | |
| <h2 class="slide-title">The problem</h2> | |
| <p class="slide-subtitle">Chemical pesticides are failing on three fronts simultaneously</p> | |
| <div class="problem-grid"> | |
| <div class="problem-card"> | |
| <div class="stat">$84B</div> | |
| <div class="stat-label">Annual market</div> | |
| <h3>Resistance collapse</h3> | |
| <p>600+ arthropod species have documented resistance. Brown planthopper alone destroys 30% of Asian rice yields in outbreak years. Farmers apply higher doses that accelerate resistance selection.</p> | |
| </div> | |
| <div class="problem-card"> | |
| <div class="stat">Decades</div> | |
| <div class="stat-label">Environmental persistence</div> | |
| <h3>Ecological damage</h3> | |
| <p>Neonicotinoids linked to pollinator collapse. EU banned outdoor use in 2018. Soil and water contamination persists for years after application. Regulators are tightening globally.</p> | |
| </div> | |
| <div class="problem-card"> | |
| <div class="stat">3-6 mo</div> | |
| <div class="stat-label">Design loop</div> | |
| <h3>Expert-gated RNAi</h3> | |
| <p>RNAi biopesticides are the new chemistry (EPA registered Ledprona in 2023), but dsRNA design takes 3-6 months per target gene. No integrated safety, fate, or regulatory layer exists.</p> | |
| </div> | |
| </div> | |
| <div class="slide-footer">Biopesticide-AI · AMD Hackathon</div> | |
| <div class="slide-num">02</div> | |
| </div> | |
| <div class="slide solution"> | |
| <div class="brand-mark"><span class="brand-dot"></span><span class="brand-name">Biopesticide<span class="brand-accent">-AI</span></span></div> | |
| <h2 class="slide-title">The solution</h2> | |
| <p class="slide-subtitle">Compress the dsRNA design loop from months to minutes</p> | |
| <div class="solution-hero"> | |
| <div class="solution-hero-text"> | |
| <h2>An end-to-end pipeline that any farmer or agronomist can run from a laptop.</h2> | |
| <p>Select a pest target. The pipeline tiles pest transcripts into 200-nt dsRNA precursors, dices them into 21-nt siRNAs, scores each for efficacy, checks off-target risk against 14 non-target species, predicts environmental half-life, and generates safety cards + regulatory memos.</p> | |
| </div> | |
| </div> | |
| <div class="solution-stats"> | |
| <div class="solution-stat"><div class="num">7</div><div class="lbl">Pest targets</div></div> | |
| <div class="solution-stat"><div class="num">14</div><div class="lbl">Safety species</div></div> | |
| <div class="solution-stat"><div class="num">~4 min</div><div class="lbl">Design loop</div></div> | |
| <div class="solution-stat"><div class="num">$0</div><div class="lbl">Per design</div></div> | |
| </div> | |
| <div class="slide-footer">Biopesticide-AI · AMD Hackathon</div> | |
| <div class="slide-num">03</div> | |
| </div> | |
| <div class="slide pipeline"> | |
| <div class="brand-mark"><span class="brand-dot"></span><span class="brand-name">Biopesticide<span class="brand-accent">-AI</span></span></div> | |
| <h2 class="slide-title">How it works</h2> | |
| <p class="slide-subtitle">6-stage pipeline from pest selection to regulatory memo</p> | |
| <div class="pipeline-grid"> | |
| <div class="pipeline-step"> | |
| <div class="num">01</div> | |
| <h4>Select</h4> | |
| <p>Click a pest target card (7 species supported) or describe the problem in natural language.</p> | |
| </div> | |
| <div class="pipeline-step"> | |
| <div class="num">02</div> | |
| <h4>Tile & Dice</h4> | |
| <p>PyTorch backend tiles pest transcripts into 200-nt dsRNA precursors, then dices into 21-nt siRNAs.</p> | |
| </div> | |
| <div class="pipeline-step"> | |
| <div class="num">03</div> | |
| <h4>Score efficacy</h4> | |
| <p>Dilated CNN (HyenaDNA-inspired) scores each siRNA. Caduceus-Ph-1 adapter available for SOTA accuracy.</p> | |
| </div> | |
| <div class="pipeline-step"> | |
| <div class="num">04</div> | |
| <h4>Check safety</h4> | |
| <p>K-mer index checks off-target risk against 14 non-target species (pollinators, livestock, aquatic, human).</p> | |
| </div> | |
| <div class="pipeline-step"> | |
| <div class="num">05</div> | |
| <h4>Predict fate</h4> | |
| <p>Physics-Informed Neural Network predicts environmental half-life based on sequence and field conditions.</p> | |
| </div> | |
| <div class="pipeline-step"> | |
| <div class="num">06</div> | |
| <h4>Simulate & report</h4> | |
| <p>1000-trial Monte Carlo wet-lab simulation. Llama 3.2 3B generates safety cards + EPA-style regulatory memo.</p> | |
| </div> | |
| </div> | |
| <div class="slide-footer">Biopesticide-AI · AMD Hackathon</div> | |
| <div class="slide-num">04</div> | |
| </div> | |
| <div class="slide architecture"> | |
| <div class="brand-mark"><span class="brand-dot"></span><span class="brand-name">Biopesticide<span class="brand-accent">-AI</span></span></div> | |
| <h2 class="slide-title">Architecture</h2> | |
| <p class="slide-subtitle">PyTorch + ROCm-ready + local Ollama LLM</p> | |
| <div class="arch-content"> | |
| <div class="arch-diagram"> | |
| <h4 style="font-family:'Fraunces',serif;font-size:16px;color:#1a3c34;margin-bottom:16px;">Data flow</h4> | |
| <div class="flow"> | |
| <div class="flow-row"><div class="arch-box green" style="flex:1">Pest card selection</div></div> | |
| <div class="flow-row"><div class="arch-box dark" style="flex:1">Tile 200-nt precursors → Dice 21-nt siRNAs</div></div> | |
| <div class="flow-row"> | |
| <div class="arch-box accent" style="flex:1">Dilated CNN<br>efficacy score</div> | |
| <div class="arch-box accent" style="flex:1">K-mer index<br>14-species safety</div> | |
| <div class="arch-box accent" style="flex:1">PINN<br>half-life</div> | |
| </div> | |
| <div class="flow-row"><div class="arch-box dark" style="flex:1">Learned ranker → final score</div></div> | |
| <div class="flow-row"><div class="arch-box green" style="flex:1">Monte Carlo wet-lab simulation (1000 trials)</div></div> | |
| <div class="flow-row"><div class="arch-box warm" style="flex:1">Ollama Llama 3.2 3B → safety cards + regulatory memo</div></div> | |
| </div> | |
| </div> | |
| <div class="arch-stack"> | |
| <h4>Tech stack</h4> | |
| <div class="arch-stack-item"><span class="tech">PyTorch 2.4</span><span class="role">ROCm-ready</span></div> | |
| <div class="arch-stack-item"><span class="tech">Caduceus-Ph-1</span><span class="role">SOTA DNA model</span></div> | |
| <div class="arch-stack-item"><span class="tech">Dilated CNN</span><span class="role">HyenaDNA-inspired</span></div> | |
| <div class="arch-stack-item"><span class="tech">Ollama 3.2 3B</span><span class="role">Local LLM</span></div> | |
| <div class="arch-stack-item"><span class="tech">FastAPI</span><span class="role">REST backend</span></div> | |
| <div class="arch-stack-item"><span class="tech">Chart.js</span><span class="role">Analytics frontend</span></div> | |
| <div class="arch-stack-item"><span class="tech">Docker</span><span class="role">Containerized</span></div> | |
| <div class="arch-stack-item"><span class="tech">MIT</span><span class="role">Open source</span></div> | |
| </div> | |
| </div> | |
| <div class="slide-footer">Biopesticide-AI · AMD Hackathon</div> | |
| <div class="slide-num">05</div> | |
| </div> | |
| <div class="slide species"> | |
| <div class="brand-mark"><span class="brand-dot"></span><span class="brand-name">Biopesticide<span class="brand-accent">-AI</span></span></div> | |
| <h2 class="slide-title">Species coverage</h2> | |
| <p class="slide-subtitle">7 pest targets · 14-species safety panel covering every ecological role regulators evaluate</p> | |
| <div class="species-cols"> | |
| <div class="species-col"> | |
| <h3>7 Pest targets</h3> | |
| <div class="species-list"> | |
| <div class="species-item"><div class="common">Brown planthopper</div><div class="sci">N. lugens · Rice</div></div> | |
| <div class="species-item"><div class="common">Fall armyworm</div><div class="sci">S. frugiperda · Maize</div></div> | |
| <div class="species-item"><div class="common">Desert locust</div><div class="sci">S. gregaria · Wheat</div></div> | |
| <div class="species-item"><div class="common">Stem borer</div><div class="sci">C. suppressalis · Rice</div></div> | |
| <div class="species-item"><div class="common">Peach-potato aphid</div><div class="sci">M. persicae · Veg</div></div> | |
| <div class="species-item"><div class="common">Potato beetle</div><div class="sci">L. decemlineata · Potato</div></div> | |
| <div class="species-item"><div class="common">Tobacco whitefly</div><div class="sci">B. tabaci · Tomato</div></div> | |
| </div> | |
| </div> | |
| <div class="species-col"> | |
| <h3>14 Safety panel species</h3> | |
| <div class="species-list"> | |
| <div class="species-item"><div class="common">Honeybee</div><div class="sci">A. mellifera · Pollinator</div></div> | |
| <div class="species-item"><div class="common">Bumblebee</div><div class="sci">B. terrestris · Pollinator</div></div> | |
| <div class="species-item"><div class="common">Leafcutter bee</div><div class="sci">M. rotundata · Pollinator</div></div> | |
| <div class="species-item"><div class="common">Ladybug</div><div class="sci">A. bipunctata · Predator</div></div> | |
| <div class="species-item"><div class="common">Lacewing</div><div class="sci">C. carnea · Predator</div></div> | |
| <div class="species-item"><div class="common">Earthworm</div><div class="sci">E. fetida · Soil</div></div> | |
| <div class="species-item"><div class="common">Water flea</div><div class="sci">D. magna · Aquatic</div></div> | |
| <div class="species-item"><div class="common">Cattle</div><div class="sci">B. taurus · Livestock</div></div> | |
| <div class="species-item"><div class="common">Zebu</div><div class="sci">B. indicus · Livestock</div></div> | |
| <div class="species-item"><div class="common">Chicken</div><div class="sci">G. gallus · Poultry</div></div> | |
| <div class="species-item"><div class="common">Sheep</div><div class="sci">O. aries · Livestock</div></div> | |
| <div class="species-item"><div class="common">Pig</div><div class="sci">S. scrofa · Livestock</div></div> | |
| <div class="species-item"><div class="common">Zebrafish</div><div class="sci">D. rerio · Aquatic</div></div> | |
| <div class="species-item"><div class="common">Human</div><div class="sci">H. sapiens · Safety</div></div> | |
| </div> | |
| </div> | |
| </div> | |
| <div class="slide-footer">Biopesticide-AI · AMD Hackathon</div> | |
| <div class="slide-num">06</div> | |
| </div> | |
| <div class="slide demo"> | |
| <div class="brand-mark"><span class="brand-dot"></span><span class="brand-name">Biopesticide<span class="brand-accent">-AI</span></span></div> | |
| <h2 class="slide-title">Live demo results</h2> | |
| <p class="slide-subtitle">Brown planthopper · 180 siRNAs scored · results in 0.08 seconds</p> | |
| <div class="demo-content"> | |
| <div class="demo-left"> | |
| <h3>Top 5 candidates</h3> | |
| <div class="demo-candidate"> | |
| <span class="seq">ACAATGAGGTACAGATGTATA</span> | |
| <span class="metrics">Eff: <span class="val">84%</span> · OT: <span class="val">0.000</span> · HL: <span class="val">25.5h</span></span> | |
| </div> | |
| <div class="demo-candidate"> | |
| <span class="seq">TGACGTCCGTAGGCCTTAACC</span> | |
| <span class="metrics">Eff: <span class="val">82%</span> · OT: <span class="val">0.000</span> · HL: <span class="val">37.7h</span></span> | |
| </div> | |
| <div class="demo-candidate"> | |
| <span class="seq">ACATAAGAATTAATATCTAAA</span> | |
| <span class="metrics">Eff: <span class="val">78%</span> · OT: <span class="val">0.000</span> · HL: <span class="val">24.0h</span></span> | |
| </div> | |
| <div class="demo-candidate"> | |
| <span class="seq">AGGGCGGACTTCAGGTGTTGT</span> | |
| <span class="metrics">Eff: <span class="val">74%</span> · OT: <span class="val">0.000</span> · HL: <span class="val">37.7h</span></span> | |
| </div> | |
| <div class="demo-candidate"> | |
| <span class="seq">ACAGGCGGCGGTAGCTTGTAA</span> | |
| <span class="metrics">Eff: <span class="val">69%</span> · OT: <span class="val">0.000</span> · HL: <span class="val">37.7h</span></span> | |
| </div> | |
| </div> | |
| <div class="demo-right"> | |
| <h3>Pipeline stats</h3> | |
| <div class="demo-sim"> | |
| <div class="sim-row"><span class="label">Design loop time</span><span class="val">0.08 seconds</span></div> | |
| <div class="sim-row"><span class="label">Pest transcripts loaded</span><span class="val">5</span></div> | |
| <div class="sim-row"><span class="label">dsRNA precursors tiled</span><span class="val">20</span></div> | |
| <div class="sim-row"><span class="label">siRNAs scored</span><span class="val">180</span></div> | |
| <div class="sim-row"><span class="label">Safety panel species</span><span class="val">14</span></div> | |
| <div class="sim-row"><span class="label">Off-target max (all candidates)</span><span class="val">0.000</span></div> | |
| <div class="sim-row"><span class="label">Cost per design</span><span class="val">$0.0000</span></div> | |
| <div class="sim-row"><span class="label">Compute location</span><span class="val">100% local</span></div> | |
| </div> | |
| </div> | |
| </div> | |
| <div class="slide-footer">Biopesticide-AI · AMD Hackathon</div> | |
| <div class="slide-num">07</div> | |
| </div> | |
| <div class="slide simulation"> | |
| <div class="brand-mark"><span class="brand-dot"></span><span class="brand-name">Biopesticide<span class="brand-accent">-AI</span></span></div> | |
| <h2 class="slide-title">Virtual wet-lab simulation</h2> | |
| <p class="slide-subtitle">1000-trial Monte Carlo · 6-stage cellular knockdown pipeline · literature-informed kinetics</p> | |
| <div class="sim-stages"> | |
| <div class="sim-stage"> | |
| <div class="stage-num">Stage 1</div> | |
| <h4>Delivery</h4> | |
| <p>Lipofection efficiency for in vitro screens. Longer PINN half-life improves delivery stability.</p> | |
| <div class="eff">85-95%</div> | |
| </div> | |
| <div class="sim-stage"> | |
| <div class="stage-num">Stage 2</div> | |
| <h4>Uptake</h4> | |
| <p>Cellular uptake efficiency. GC-content dependent (optimal at 45% GC).</p> | |
| <div class="eff">75-95%</div> | |
| </div> | |
| <div class="sim-stage"> | |
| <div class="stage-num">Stage 3</div> | |
| <h4>Dicer processing</h4> | |
| <p>Dicer processes dsRNA into 21-nt siRNAs. Reynolds score dependent, repeats penalized.</p> | |
| <div class="eff">80-95%</div> | |
| </div> | |
| <div class="sim-stage"> | |
| <div class="stage-num">Stage 4</div> | |
| <h4>RISC loading</h4> | |
| <p>Thermodynamic asymmetry determines guide vs passenger strand. Reynolds rules 3-7.</p> | |
| <div class="eff">70-95%</div> | |
| </div> | |
| <div class="sim-stage"> | |
| <div class="stage-num">Stage 5</div> | |
| <h4>Target cleavage</h4> | |
| <p>mRNA cleavage rate. CNN-predicted efficacy is the primary driver.</p> | |
| <div class="eff">20-98%</div> | |
| </div> | |
| <div class="sim-stage"> | |
| <div class="stage-num">Stage 6</div> | |
| <h4>Phenotype</h4> | |
| <p>Soft-saturation dose-response. Reports mean KD, 95% CI, P(KD>70%).</p> | |
| <div class="eff">38-51%</div> | |
| </div> | |
| </div> | |
| <div class="slide-footer">Biopesticide-AI · AMD Hackathon</div> | |
| <div class="slide-num">08</div> | |
| </div> | |
| <div class="slide production"> | |
| <div class="brand-mark"><span class="brand-dot"></span><span class="brand-name">Biopesticide<span class="brand-accent">-AI</span></span></div> | |
| <h2 class="slide-title">Production upgrade path</h2> | |
| <p class="slide-subtitle">Real measured data + AMD GPU training · architecture is production-ready, only training data is synthetic</p> | |
| <table class="prod-table"> | |
| <tr><th>Component</th><th>Demo (synthetic)</th><th>Production (real data + AMD GPU)</th></tr> | |
| <tr><td>Training set</td><td class="demo-col">1,000 synthetic siRNAs</td><td class="prod-col">30,000+ measured siRNAs (siRecords)</td></tr> | |
| <tr><td>Safety panel</td><td class="demo-col">14 synthetic transcriptomes</td><td class="prod-col">14 real NCBI transcriptomes (~2 GB)</td></tr> | |
| <tr><td>Model</td><td class="demo-col">Dilated CNN, 2 min on CPU</td><td class="prod-col">Caduceus fine-tune, 15 min on MI250</td></tr> | |
| <tr><td>Validation AUC</td><td class="demo-col">1.00 (trivially separable)</td><td class="prod-col">0.82-0.92 (realistic)</td></tr> | |
| <tr><td>Off-target accuracy</td><td class="demo-col">0% (random sequences)</td><td class="prod-col">Real per-species risk scores</td></tr> | |
| <tr><td>Training cost</td><td class="demo-col">$0 (local CPU)</td><td class="prod-col">~$1.50 (1 hour MI250)</td></tr> | |
| </table> | |
| <p style="margin-top:20px;font-size:14px;color:#4b5563;line-height:1.6;">Codebase already supports production via three CLI flags: <code style="background:#e8f5ec;padding:2px 6px;border-radius:4px;font-family:monospace;font-size:12px;">--source real</code> · <code style="background:#e8f5ec;padding:2px 6px;border-radius:4px;font-family:monospace;font-size:12px;">--device cuda</code> · <code style="background:#e8f5ec;padding:2px 6px;border-radius:4px;font-family:monospace;font-size:12px;">--use-caduceus</code></p> | |
| <div class="slide-footer">Biopesticide-AI · AMD Hackathon</div> | |
| <div class="slide-num">09</div> | |
| </div> | |
| <div class="slide business"> | |
| <div class="brand-mark"><span class="brand-dot"></span><span class="brand-name">Biopesticide<span class="brand-accent">-AI</span></span></div> | |
| <h2 class="slide-title">Business case</h2> | |
| <p class="slide-subtitle">$84B market · EPA regulatory precedent set · no competitors with integrated AI pipeline</p> | |
| <div class="business-grid"> | |
| <div class="business-card"> | |
| <h3>Market opportunity</h3> | |
| <div class="market-stat"><div class="num">$84B</div><div class="lbl">Total pesticide market (TAM)</div></div> | |
| <div class="market-stat"><div class="num">$12B</div><div class="lbl">Biopesticide segment (SAM, 15% CAGR)</div></div> | |
| <div class="market-stat"><div class="num">$480M</div><div class="lbl">RNAi biopesticides by 2030 (SOM)</div></div> | |
| <div class="market-stat"><div class="num">2023</div><div class="lbl">EPA registered Ledprona (first dsRNA)</div></div> | |
| </div> | |
| <div class="business-card"> | |
| <h3>Competitive landscape</h3> | |
| <div class="competitor"><span class="name">Greenlight Biosciences</span><span class="time">2-4 weeks</span></div> | |
| <div class="competitor"><span class="name">AgroSpheres</span><span class="time">2-3 weeks</span></div> | |
| <div class="competitor"><span class="name">RNAissance Ag</span><span class="time">3-6 weeks</span></div> | |
| <div class="competitor"><span class="name">Academic tools (DeepRiPE)</span><span class="time">1-2 weeks</span></div> | |
| <div class="competitor us"><span class="name">Biopesticide-AI</span><span class="time">< 4 minutes</span></div> | |
| <p style="margin-top:16px;font-size:12px;color:#6b7280;line-height:1.5;">Only platform combining SOTA sequence models, PINN fate prediction, 14-species safety panel, and LLM-generated regulatory docs. 100-1000x faster than competitors.</p> | |
| </div> | |
| </div> | |
| <div class="slide-footer">Biopesticide-AI · AMD Hackathon</div> | |
| <div class="slide-num">10</div> | |
| </div> | |
| <div class="slide roadmap"> | |
| <div class="brand-mark"><span class="brand-dot"></span><span class="brand-name">Biopesticide<span class="brand-accent">-AI</span></span></div> | |
| <h2 class="slide-title">Roadmap</h2> | |
| <p class="slide-subtitle">From hackathon MVP to Series A in 12 months</p> | |
| <div class="roadmap-timeline"> | |
| <div class="roadmap-phase"> | |
| <div class="phase-label">0-3 months</div> | |
| <h4>BPH MVP</h4> | |
| <ul> | |
| <li>Train on real siRecords data (30k siRNAs)</li> | |
| <li>Customer discovery with 3 Indian rice cooperatives</li> | |
| <li>Validate against published BPH RNAi literature</li> | |
| <li>Deploy on AMD MI250 via ROCm 6.1</li> | |
| </ul> | |
| </div> | |
| <div class="roadmap-phase"> | |
| <div class="phase-label">3-6 months</div> | |
| <h4>Multi-pest expansion</h4> | |
| <ul> | |
| <li>Extend to fall armyworm (maize)</li> | |
| <li>Extend to desert locust (wheat)</li> | |
| <li>Add GNN for seed-region off-target modeling</li> | |
| <li>Partner with university ag biotech labs</li> | |
| </ul> | |
| </div> | |
| <div class="roadmap-phase"> | |
| <div class="phase-label">6-12 months</div> | |
| <h4>Series A</h4> | |
| <ul> | |
| <li>Raise $5M Series A</li> | |
| <li>Wet-lab partnership (TNAU or UC Davis)</li> | |
| <li>Expand safety panel to 30+ species</li> | |
| <li>EPA FIFRA Section 3 registration filing</li> | |
| </ul> | |
| </div> | |
| </div> | |
| <div class="slide-footer">Biopesticide-AI · AMD Hackathon</div> | |
| <div class="slide-num">11</div> | |
| </div> | |
| <div class="slide closing"> | |
| <h1>Building the first<br><span class="accent">LLM-native biopesticide company</span></h1> | |
| <p>The hackathon is the proving ground. The market is $84 billion. The regulatory pathway is open. The technology works. We are ready to build what's next on AMD.</p> | |
| <div class="closing-stats"> | |
| <div class="closing-stat"><div class="num">$84B</div><div class="lbl">Market</div></div> | |
| <div class="closing-stat"><div class="num">4 min</div><div class="lbl">Design loop</div></div> | |
| <div class="closing-stat"><div class="num">14 sp.</div><div class="lbl">Safety panel</div></div> | |
| <div class="closing-stat"><div class="num">$0</div><div class="lbl">Per design</div></div> | |
| </div> | |
| <div class="closing-cta">MIT licensed · AMD Developer Hackathon Unicorn Track · June 2026</div> | |
| </div> | |
| </body> | |
| </html> |